Research Methodology The study of conducting research is Research Methodology. Research: The word research is composed of two syllables “Re” and “Search”.
“Re” is the prefix meaning ‘Again or oer again or a new! and “Search” is the latter meaning ‘to examine closely and carefully! or ‘to test and try!. Together they form" a careful" systematic" patient study and inestigation in some field of #nowledge underta#en to establish principles $ policies. Research can also be defined as
%. Sear Search ch for for #now #nowle ledg dgee &. System Systematic atic and scientifi scientificc search search for getting getting releant releant answers answers on any ta#en up specific specific topic. '. Scient Scientific ific en(uiry en(uiry into into a sub) sub)ect ect.. *. Research Research is a moement moement from from the un#nown un#nown to the #nown. #nown. +. ,t is is the the oy oyage of of disco discoe ery ry According to -ulmer" Research is primarily committed to establishing systematic" reliable and alid #nowledge about the social world. According to lifford /oody /oody"" Research comprises of •
0efining
and
redefining
•
6aluating datas
•
Ma#ing decisions
•
Suggesting solutions
problems. •
1ormu 1ormulati lating ng idea3
hypot hypothesi hesiss
2basic 2basic
•
ollecting
•
Reaching conclusions
•
4rgani5ing
•
1ina 1inall lly y"
care carefu full lly y
test testin ing g
the the
conclusions To determine whether they fit the formulated 7ypothesis. understood d as all those methods methods or techni(ues techni(ues that that are used by a Research Methods: May be understoo researcher for conducting a Research depending upon the methods. 2%3 Library Research: Analysis Analysis of historical historica l records and documents. -
Statistical compilation" references" abstracts" guides manipulation 2handle with s#ill3
2&3 Field Research: 4bseration" (uestionnaires" personal" 8roup or telephonic interiews" case study. 2'3 Laboratory Research: 8roup 2team3 study" use of audio isual tools.
Research Methodology9 is the way do systematically sole the research problem. ,n it we study the arious steps that are generally adopted by a researcher in studying his research problem logically. /hen we tal# of Research Methodology" we not only tal# of research methods but also consider the logic behind the methods we use in the context of our research study and explain why we are using a particular method or we are not using a particular method or techni(ue so that research results are capable of being ealuated either by the researcher or others. Steps9 %3 /hy a particular particular research research study has been been underta# underta#en: en: &3 7ow the the Resear Research ch probl problem em has been been defi defined ned:: '3 /hat way and why why the hypothesi hypothesiss 2basic idea3 idea3 has been been formulated formulated:: *3 /hy a particular particular techni(u techni(uee of analy5ing analy5ing data is used: used: 2or3 7ow the data data were collected: collected: +3 7ow the the colle collected cted data data were were interp interprete reted: d: ;3 /hat /hat dele deleti tion on was was mad made: e: <3 /hat /hat was was the the conc conclu lusi sion on:: 1inally what was the solution for the Research problem: Importance of knowing the subject – research Methodology:
%3 A student student preparin preparing g himself himself for a career of carrying carrying out research research as his profession profession = -
/ill be trained better to do research
-
/ill help him deelop disciplined thin#ing
-
/ill help him obsere the field ob)ectiely. ob)ectiely.
-
/ill enable thoroughly to understand the logic behind the research problem.
-
/ill increase the ability to ealuate the results.
-
1ace the ealuated results with confidence.
-
>sef >seful ul in ario arious us fiel fields ds such such as 8ot 8ot.. -usi -usine ness" ss" admi admini nist strat ratio ion" n" comm commun unity ity deelopment ? social wor#.
To ualify a Research or study:
To be a 8ood or perfect one" The Research adapted should process certain characteristics" ,t must as far as possible be %3 ontrolled &3 Rigorous '3 Systematic *3 @alid
+3 @erifiable ;3 6mpirical <3 ritical
!" #ontrolled: The research problem should not be affected or influenced by external factors 2i.e. ariables other than the participating facts3.
The proc proced edur ures es foll follow owed ed to find find answ answers ers to (uest (uestio ions ns shou should ld be rele relea ant nt"" $" Rigorous: The approp appropria riate te ? )ustif )ustified ied.. -ut the degree degree of rigiou rigiourr may ary from from one problem problem to anothe another r problem. %" &ystematic: The inestigation should follow a certain logical se(uence 2ot in a hapha5ard manner3 '" (alid (alid ) (erifiabl (erifiable: e: any time.
The findings should be alid ? can be erified by you or others at
*" +mpirical: The conclusions drawn should be based on hard eidence" gathered from real life experiences or obserations.
The process of inestigation must be foolproof and free from drawbac#s. The ," #ritical: process adapted and the procedures used must be able to withstand any critical scrutiny. scrutiny.
Types of Research Research can be classified from the iew point or perspecties as" from the iew point
-pplication
.bjecti/e
Inuiry mode
%3 Bure Research
%3 0escriptie
%3 Cuantitatie Research
&3 Applied Research
&3 orrelatie
&3 Cualitatie Research
'3 6xploratory *3 6xplanatory %3 0ure Research:
12asic or Fundamental Research3
8athering" #nowledge is termed as ‘pure! or ‘basic! research. Dust to gather #nowledge in order to formulate or generali5e theories or policies. 6g3 Research on mathematics. This types of research res earch adds #nowledge to the already existing organi5ed body. -pplied Research:
To find an immediate solution for a pressing practical problem.
6g9 Social" economical and political trends preailing in a country. -pplied (s Fundamental 2ased on the objecti/es of Research: !3 4escr 4escript ipti/e i/e Resea Researc rch: h: •
Surey or fact finding en(uires of different #inds. ,t describes the actual preailing state of affairs" existing at present.
•
4therwise #nown as ex post facts means existing position of facts $ issues.
•
7ere the ariable influencing the research has no control or the researcher has no control oer the ariables.
6g9 1re(uency of shopping" customer preference etc. $3 #orre #orrelat lati/e i/e Resear Research ch9 •
8oes on to discoer the existing relationship or interdependence between two or more aspects $ ariables.
•
4therwise #nown as comparatie study.
•
,nestigates association between ariables. 6g9 Sum of humour and )ob satisfaction" 2related ariable3 Research problem is wor#ers turnoer
-nalytical Research9
The researcher has to use facts $ information already existing and analy5e these data to ma#e a critical ealuation. 6g9 document study $ historical eidence. 4escripti/e (s -nalytical Research 9 +5planatory Research 9
Attempts to clarify or explain why and how" any particular research problem arises and can be soled. '" +5ploratory Research:
Study underta#e to explore a new area or an un#nown destination.
,,,. 2ased on the Inuiry Mode: !3 6uanti 6uantita tati/ ti/ee Resear Research ch:: •
Relates to aspects that can be (uantified and expressed in terms of (uantity.
•
4therwise #nown as structured Research.
•
,n this type of Research" the ob)ecties" design" sample and all the other factors influencing the research is pre determined.
The research problem and its solution will be expressed in terms of (uantity and hence statistical and economic analysis is adapted in this type of Research. 6uantitati/e Research: •
4therwise #nown as unstructured research.
•
The aspects related to (uality $ #ind or texture. 6g9 -ehaiour science
-part from the abo/e7 other types of Research are " #onceptual Research: Research related to some abstract idea or theory •
>sed by philosophers or thin#ers for deeloping new concepts.
+mpirical research
2based on experiments or experience3 •
4therwise #nown as experimental type of Research.
•
The result obtained by adapting 6mpirical Research is considered to be most powerful 2eidence enclosed3
-ased on the the time consumed to complete a particular research" a3 one time Research9 Research9 restricted restricted to a single time period. period. b3 Eongitudinal Research9
onducted oer seeral time period.
6ualities of a Researcher Top !8 ualities of a Researcher
%3 -n analytical mind: onstant analysis on a ariety of factors. &3 - people person: 1or respondents to get the best out of interiews $ focus groups. '3 The ability to stay calm: 6specially when you hae pressing deadlines. Feep well focused and thin# logically there will always be an end point. *3 Intelligence: Researcher re(uires critical analysis" but most of all common sense. +3 #uriosity: 7ae curiosity and be passionate about deeloping deeper to unearth more insight. ;3 6uick thinker: Things don!t always go as you plan" so you need to be able to thin# fast. <3 #ommitment: ‘
Research is a tough )ob" the hours may be long" the deadlines short.
G3 +5cellent written and /erbal communication skills: So that different audience can clearly understand the findings. H3 &ympathetic: 7aing a sympathetic sympathetic ear when listening to some respondents respondents 2cry etc3 is a good s#ill" to hae. %I3 &ystematic:hec#" chec# and chec# again. Spending a proper proper amount of time for for chec#ing always pays.
According to Micheal 1oster" %3 Truthful Truthful data data $ facts facts = desire desire for accuracy accuracy of obserati obseration. on. &3 o expression expressionss li#e approxim approximately ately"" almost almost or nearly. nearly. '3 Should Should poccess poccess alert mind. mind. ature is constan constantly tly changi changing" ng" be #een #een and and watchfu watchfull to notice such changes" no matter how small or insignificant they may. *3 Scientific Scientific in(uiry in(uiry = desire for for #nowledge #nowledge = it re(uires re(uires moral moral courage" Steadfas Steadfastt 2constant $ not changing3 c hanging3 endurance 2to tolerate the difficulty" suffer patiently3 -
/hen a research scientist feel defeated or completely lost" he needs immense courage and the sense of coniction 2found guilty3
&ignificance or Importance of &earch
%3 0oubt 0oubt is better than oer confiden confidence ce for it leads to in(uiry" in(uiry" in(uiry leads leads to inention. inention. Brocess or the three stages of research to bring out economic policies. %3 ,nestigati ,nestigation on of preailing preailing econom economic ic structure structure with the the aailable aailable facts. &3 Analy Analyse se or or diagn diagnose ose the data. data. '3 Bredic Bredictio tion n for futur futuree deelo deelopme pments nts.. &3 Research Research encourage encouragess scientific scientific and and inducti inductiee thin#ing thin#ing.. 6g9J Role of Research in 9 !3 +con omic omicss:
Researches done on applied 2production and sales of goods in a profitable manner3 economics is increasing in modern days. 8ot. ? business sectors hae become more comple complex" x" they they face seeral seeral operati operationa onall problem problemss to sole sole these these proble problems" ms" and Research is carried on.
To frame 8ot. economic policies.
8ot. budget a formulation depends on the analysis of needs ? desires of the people" aailable of reenues needs research.
0ecision ma#ing = re(uires proper research.
Allocation of a countries scarce resource = also needs research.
$3 -usiness 0ecisions9
,n business sectors there are both planning and operational problems.
a3 Broblems Resea search9 ,nesti stigati ation of the presen sent str structure and deelopmen deelopmentt of the mar#et = relating relating to purchase" purchase" production" production" promotion promotion and sales. b3 4perational Research9 Relates to application of logical" mathematical and analytical techni(ues = to sole mar#et problems = there by minimi5e cost and profit maximi5ation. c3 Motia Motiatio tional nal Research Research99 7elps 7elps to determ determine ine people people behaior behaior or consum consumer er response. All the aboe three are responsible for business decision ma#ing. %3 Social sectors9 To gain #nowledge on un#nown aspects and do something better and more efficiently.
Social scientist gains their #nowledge for their own sa#e and for the deelopment of the society. %.
1ormulating the Research problem9J
a3 The formulation of a general topic into a specific Research problem thus constitutes the first step in a scientific in(uiry. Two Two steps are inoled in formulating the Research problem" a3 >nderst >nderstand anding ing the the problem problem thoroug thoroughly hly.. b3 Rephrasing the same into meaningful terms from an analytical point of iew. iew. %. ,dentify ,dentify a broad broad field field or or sub)ect sub)ect area area of interest interest to you. you. &. 0issect 0issect the the broad broad area into into small small area. area. '. Select Select what what is is of most most inte interest rest to to you. you. *. Rais Raisee Resear Research ch (ue (uest stio ions ns.. +. 1orm 1ormul ulate ate ob)ec ob)ecti tie ess ;. Asses Assesss you yourr ob)ec ob)ecti tie ess <. 0ouble che chec#
The best way to understand the problem is to discuss with his own colleague or guide.
6xamine 6xamine all aailable aailable literatures literatures to get himself himself ac(uainted ac(uainted 2get used to 3 with the selected problem.
Reiew two types of literature
onceptual literature9 oncerning concepts ? theories 6mpirical 6mpirical Eiterature9 Eiterature9 oncerning oncerning studies studies made earlier earlier which are similar similar to the one proposed. proposed.
4utcome of the reiew will be the #nowledge so as to pre determine what data or materials are aailable for operational purposes.
ext step = the Researcher rephrases the problem into Analytical Analytical or operational terms. 09T T+ 0R.2L+M I;T. &0+#IFI# T+RM&
This step is of greatest importance in the entire research process. The problem to be inestigated must be defined unambiguously or clearly. clearl y. Brof /.A. /.A. eiswanger States"
The statement of the ob)ectie of the Research problem is of basic importance because" 2i3 2i3
,t dete determ rmin ines es the the data data whic which h are are to be coll collec ecte ted d
2ii3 2ii3
har harac acte teri rist stic icss of of the the rele relea an nt dat dataa
2iii 2iii33
hoi hoice ce of of tech techni ni(u (ues es to to be used used in the these se exp explo lora rati tion onss
2i3
1rame a 1inal report
Step ,, +5tensi/e Literature &ur/ey:
A brief summary of the problem should be written down.
Ma#e extensie literature surey
Sources of surey can be" )ournals" bioJgraphics" 8ot. reports" boo#s" conference proceedings etc. -ased on the nature of the problem.
6arlier study if any which is similar to the study in hand should be carefully studied.
A good library will be a great help to the researcher at this stage.
Stage ,,,9 4e/eloping ypothesis :
20eelopment of wor#ing 7ypothesis3
State in clear terms the wor#ing hypothesis 2-asic ,dea of the Research problem3
,t is a tentatie assumption in order to test to logical or empirical conse(uences.
Broide the focal point for research.
7ypothesis should be ery specific and ery well limited to the place of research in hand because it has to be tested.
7ypothesis guides the researched by limiting the area of Research and #eep him on the right trac#.
,t sharpens his thin#ing and focuses attention on important facets of the problem.
,t indicates the type of data re(uired for the study.
Type Type of methods of data analysis done.
ow to de/elop working ypothesis<
%3 0iscuss with with collogues collogues $ experts" experts" about about the problems" problems" its origin" origin" its ob)ectie ob)ectiess and solutions. &3 6xami 6xaminati nation on of data$ data$ record recordss if aailab aailable. le. '3 Reiew Reiew similar similar studi studies es $ similar similar problem problems. s. *3 To secure greater greater insight insight into the the practical practical aspects of the problem problem = conduc conductt personnel personnel inestigation or field interiews. ST6B ,@9 0reparing the Research 4esign:
Researc Research h design design is the concep conceptua tuall structu structure re within within which which researc research h is conduc conductio tion. n. ,t constitutes the blue print for the collection" measurement and analysis of data. The function function of the Research Research design design is to proid proidee relea releant nt eiden eidence ce with with minima minimall expenditur expendituree of effort" time and money. money. ,t proides proides an outline outline of what the researcher researcher is going to do in terms of %3 1raming the hypothesis" &3 its operational implications and '3 finally data analysis The Research design highlights certain decision" %3 The The natu nature re of of the the stud study y &3 Burp Burpos osee of of the the study study '3 Eocation Eocation where where the the study study would be condu conducted cted *3 The The natur naturee of data data re(u re(uir ired ed +3 1rom 1rom where where the the data data would would be coll collecte ected d ;3 The techni techni(ues (ues of of data collection collection that that would would be be used <3 /hat /hat time time period period the the study study would would coer coer G3 The The type type of sample sample design design that that would would be used used H3 The method method of data data analysis analysis that would would be adapted adapted %I3 The manner in which which the report would be prepared Type of Research 4esign:
* types
%3 &ling Research 4esign : 0eal with selection of releant items
&3 .bser/ational .bser/ational Research Research 4esign: 0eals with the obserations 2field obserations3 that is to be made. '3 &tatistical Research design: 0eal 0ealss with with the the info inform rmat atio ion n on the the data data coll collec ecte ted d ? analysed. *3 .perational Research 4esign: 7ow the aboe three are carried out. 4etermining sample 4esign:
All the items considered in any field of in(uiry constitutes a “unierse” or population. Study of the entire population without leaing out a single item is #nown as “ensus Study”
This type of census study is practically not possible.
So we select few items from the entire population for our study purpose. The items so selected constitute what is technically called “sample”.
The way of selecting such a “sample” is #nown as the “Sample 0esign”.
These samples can be either probability samples or non probability samples. Brobability9 6ach item in the population has on e(ual chance of being selected for the study. %3 Simp Simple le rand random om sam sampl plin ing g &3 System Systematic atic random random sampli sampling ng '3 Strati Stratifie fied d rand random om sampli sampling ng *3 luste lusterr $ area area rando random m sampl sampling ing.. on Brobability sampling9 All the items do not hae an e(ual chance of being selected for the study. The selection depends upon the conenience ? )udgment of the Researcher. Mixed sampling9 /hen more than one type t ype of sampling techni(ue is used for a study" study" it is mixed sampling. The sample design to be used in a Research study must be decided by the researcher considering the nature of the study. ;.
#ollecting the 4ata:
“=athering appropriate data> which are made use in Research study. study. 0ata can be collected in seeral ways either through 2%3 6xperiment 2or3 2&3 through sureys.
,n experimental means" when a researcher conducts a research" some (uantitatie meas measur urem emen ents ts are are obse obser red ed"" based based on whic which" h" he exam examin ines es the the truth truth of the the underlying hypothesis.
,n case of sureys" data are collected by
%3 -y obse obser rat atio ions ns &3 Throug Through h perso personne nnell inter interiew iew '3 Throug Through h telep telephon honee inter interiew iewss *3 -y mailin mailing g of (uesti (uestionn onnair aires es +3 Throug Through h schedu schedules les $ enum enumerat erators ors The Researcher should select one of these methods of collecting the data ta#ing in account the !3 ature of inestigation $3 4b)ectie ? scope of ,n(uiry %3 1inancial Resources '3 Time frame
Accuracy. *3 0esired degree of Accuracy. ,3 +5ecution +5ecution of the the 0roje 0roject: ct: 10utt 10utting ing a plan3 plan3
,mportant step in Research Rese arch study.
See that the pro)ect is executed in a systematic manner and in time. 6g3 ,f the surey done in a pro)ect is ia Cuestionnaire the answers can be machine coded $ processed
,f interiew were conducted" ma#e sure that the interiewers are well trained = to #eep the surey as much as realistic as possible.
G. -nalysis of 4ata :
After the data are collected the researcher turns to the tas# of analy5ing the data the analy analysis sis of data data re(ui re(uire re close closely ly relat related ed opera operati tion ons" s" li#e li#e ‘codi ‘coding ng"" 6dit 6ditin ing g ? Tabulation!.
The wide data collected should be condensed into small manageable groups" for easy analysis.
oding9 The collected data are transformed into symbols that may be tabulated or counted.
6diting9 >nwanted ? irreleant data will be remoed.
Tabulation9 Tabulation9 Technical Technical procedure where the t he data are put in the form of tables.
Research 4esign:
The most important step after defining the ‘Research problem! is preparing the Research 0esign
Research design is the conceptual structure within which the research is conducted.
,t constitutes the ‘-E>6 BR,T” for collection" measurement and analysis of data.
Research Research design proides an answer to the (uestion" (uestion" what the Researcher Researcher is going going to do with regards to framing hypothesis" its operational implications and how to analyse the data:
Research 4esign: ? 4ecisions
7ighlights certain decisions" %3 atu ature re of of the the stud study y &3 Burp Burpos osee of of the the study study '3 Eocation Eocation where where the the study study would be condu conducted cted *3 ature ature of of “0AT “0ATA” re(u re(uire ired d +3 1rom where the the “0A “0ATA” can be be collected collected ;3 Time ime peri period od of of the the stud study y <3 Type Type of sample sample desi design gn to to be used used G3 Techni echni(ue (uess of data data coll collect ection ion H3 Meth Method odss of 0ata 0ata Ana Analy lysi siss %I3 Breparation Breparation of Report. Research 4esign
May be sub diided into" %3 Sampling Sampling design9 design9 0eals with" with" the the method method of ‘selectin ‘selecting g items! items! for the study. study. &3 4bserational design9 Relates to the condition under which the obserations are to be made. '3 Statistical 0esign9 0eals with the “no of items” selected or the study and how the selected data will be analysed. *3 4peration design9 The techni(ue by which the sampling" obserational and statistical designs can be carried out. Research 4esign – Features:
%3 7elps to identify the type and source of information needed for the study. &3 Specifies the methods to be adopted in collecting ? analy5ing data. '3 Specifies the time schedule of the research and the monetary budget inoled. #oncepts Relating to Research 4esign
%3 4ependent and Independent /ariables :
(ariables 9A magnitude that aries is #nown as “ariable”
9@alues that can be expressed een in decimal poins are #nown as #ontinuous /ariable 9@alues continuous ariables 6g9 6g9
age age 2* years ears ' mont months hs33
7eig 7eight ht 2+.& 2+.& cm3 cm3
/eight ight 2*+. 2*+.' ' #g3 #g3
;on continuous (ariables: @alue that can be expressed only in integer alues are called on continuous ariables
6g9
o. o. of stu student dentss in a clas classs 2 *+3 o. of children in a family 2'3
Statistically #nown as “discrete ariables” 4ependent or +ndogenous /ariables 9
/hen the change in one ariable depends on the change in other ariable" it is #nown as dependent or 6ndogenous ariable. 0emand
JJJJJ
Brice 2independent3
Independent or +5ogenous /ariable
The ariable that causes the change in the dependent ariable is #nown as independent or exogenous ariable. 0emand 20ependent3 JJJJJJJ Brice ",ncome 7ere demand is a dependent ariable while price $ income is an independent ariable. +5traneous /ariable :
The independent ariable which is not directly related to the purpose of the study but affects the dependent ariable is #nown as extraneous ariables.
The influence caused by the extraneous ariable on the dependent alue is technically #nown as “6xperimental 6rror”
A research study or a Research design should always be framed in such a manner that the influence of ‘6xtraneous ariables! on the dependent ariable is completely controlled and the influence of the independent ariable is clearly eident.
#ontrol:
8ood Research design should minimi5e the effect for extraneous ariables. #onfounded Relationship
The relationship between dependent and independent ariable is said to be confounded by an extraneous ariables. Research ypothesis:
/hen the formulated hypothesis is tested by adopting scientific methods" it is #nown as Research 7ypothesis.
+5perimental ) ;on +5perimental ypothesis testing:
/hen the ob)ectie of the Research is to test the hypothesis" it is Research hypothesis.
Research in which the independent ariable are 2handled with s#ill3 manipulated" it is experimental hypothesis testing.
/hen the ariables are not manipulated" it is non experimental hypothesis testing.
+5perimental ) #ontrol =roups 9
/hen a group is exposed to usual conditions in an experimental hypothesis" research it is control 8roups.
/hen the group is exposed to special or certain new conditions" it is experimental groups.
G. Treatments: The different conditions to which the experimental ? control groups are sub)ect to is #nown as treatments. H" +5periment:
1ertili5ers and crops3
Brocess of erifying the truth. -bsolute +5periment9
0etermine the fact
#omparati/e +5periment:
0etermine the impact in comparison with another fact.
%I. +5perimental units
BreJdetermined bloc# to which different treatments are applied. 6g 9 animal testing
Types Types of Research 4esign There are three different types of Research design" !3 +5plo +5plora rator tory y Resear Research ch 4esig 4esign: n:
,s a “1ormulatie Research design”
Main purpose is the discoery of ideas ? insights
Should be flexible enough considering different dimensions of the problem under study.
$3 4escript 4escripti/e i/e and and 4iagnost 4iagnostic ic Resear Research ch 4esign: 4esign:
0escriptie Research 0esign is concerned with describing the characteristics of a particular indiidual or a group.
Study concerned with narration of facts or characters related to an indiidual" group or institution is descriptie research studies.
0iagnostic Research design determines the fre(uency with which a ariable occurs or its relationship with another ariables.
-oth the Research designs des igns should be planned carefully.
Research design should be Rigid 2o flexibility3
%3 ypothes ypothesis is testing testing Researc Research h 4esig 4esign n9
Test the hypothesis of causal relationship between two or more ariables.
Adopt procedure that not only reduce bias but enhance reliability = and facilitates deriing ,nferences 2results3 about the Research problem.
Importance of Research 4esign:
1acilitates the smooth flow of the arious stages of Research.
7elps yield maximum information with minimum effort" time and money.
7elps to plan in adance data collecting and analysis techni(ues.
Brepare with utmost care to aoid errors.
Attain reliability
#haracteristics of a =ood Research 4esign
Bosses the (ualities of being flexible" suitable efficient ? economical.
Should minimi5e ‘bias! and maximi5e reliability of data collection ? Analysis.
o experimental error should be allowed
Should yield maximum information
Research problem should be iewed from different angles or dimensions.
The choice of Research design depends on"
ature of the Research problem 4b)ecties of the Research problem
S#ills $ ability of the Researcher
Methods of gathering information
Aailability Aailability of monetary support
Time schedule
@0.T+&I&
A Research hypothesis is a predictie statement" which is capable of being ‘tested! using scienti scientific fic metho methods" ds" which which inol inoles es indepe independe ndent nt and depend dependent ent aluab aluables. les. 2eg3 2eg3 the female female students perform as well as the male students. This statement is a hypothesis that can be ob)ectiely tested and erified. ,t is a proposition that can be put to test in order to examine its alidity. #haracteristics #haracteristics of ypothesis
%3 A hypothe hypothesis sis should be precise precise and clear. clear. ,f not clear" clear" the inferences inferences will not be reliable. reliable. &3 ,t must must be capab capable le of bein being g put put to test. test. '3 ,t should should state the relationsh relationship ip between the the ariables" ariables" in case relational relational hypothes hypothesis. is. *3 ,t should should be be stated stated in a simple simple langu language age.. +3 ,t should should be consistan consistantt and deried deried from all all #nown #nown facts. facts. ;3 7ypothesis 7ypothesis must must be amenable amenable to testing testing within within a reasonable reasonable period period of time time <3 7ypot 7ypothesi hesiss should should explain explain what what it actually actually to explai explain. n. 2the solut solution ion for for the Researc Research h problem3. The explanation should should be on empirical reference. #oncepts Relating to Testing of ypothesis
%3 ull ull 7ypot 7ypothes hesis is ? Alte Alterna rnati tiee 7ypothesis 2Statistical Analysis3 ull 7ypothesis9 0enoted by 7I. ,f both both the ariables 2say male or female3 or 27ead or Tail3 Tail3 are e(ually good" it is ull 7ypothesis. Alternatie 7ypothesis9 0enoted by 7a or 7%. ,f one ariable is considered superior to other or ice ersa or if there is a difference" it is alternatie hypothesis. Mean 0opulation 1u3 or 1p3
Total Total $ o. of ariables ;ull ypothesis
7o 9
u K %II
-lternati/e ypothesis
7a
9
u K %II
7a
9
u L %II
7a
9
u %II
-spects to be considered while formulating ;ull ypothesis
%3 The researcher researcher always always tries to re)ect ull hypothesi hypothesiss since Alternati Alternatie e 7ypothesis 7ypothesis should should be proed. &3 ull ull hypot hypothesi hesiss when when it is actually actually true" true" when re)ected re)ected inol inoles es great ris#" ris#" the leel of significance should be considered. '3 ull hypo hypothesis thesis should should be ery specific specific 2o approxim approximation ation33 The leel of significance9 •
,mportant concept of hypothesis testing.
•
,t is a certain percentage chosen with great ‘care" reason and thought! 2eg3 let us consider the leel of significance to be +N. ,t means the Researcher ta#es a ris# of re)ecting ull hypothesis 27o3 by +N when 7o is actually true.
%"
4ecision Rule •
The researcher should ma#e a decision" if to accept or Re)ect 7o.
•
The decision rule should be decided on the number of items to be tested and the basic of which to accept or re)ect.
*.
Type I and Type II +rrors
2i3
Resea Researc rche herr may re)ec re)ectt 7o" when when it is tru truee = Type Type , 6rror 6rror 2whi 2which ch must must hae hae been been accepted3.
2ii3 2ii3
Rese Resear arch cher er may may accep acceptt 7o" whe when n it is false false = Type Type ,, 6rro 6rrorr 2whic 2which h must must hae hae been been re)ected3
+.
.ne tailed and Two tailed Tests9
2i3 2i3
4ne 4ne taile tailed d test test re)ec re)ects ts the the ull ull hypo hypoth thes esis is when when the the sampl samplee mean mean is eithe eitherr great greater er or lower than the hypothesi5ed alue of the population mean.
/hen the sample mean is both greater and lower than the Two tailed Test9 hypothesi5ed alue of the population mean. 0rocedure for ypothesis Testing:
%. Testing Testing hypo hypothesis thesis refers refers whether whether the formulated formulated hypo hypothesis thesis is alid alid or not not &. /hethe /hetherr to Accep Acceptt or Re)ect Re)ect ull ull 7ypoth 7ypothesis esis..
2i3
Making a formal statement: •
2ii3 2ii3
2iii 2iii33
Sele Select ctin ing g a sign signif ific ican antt le leel el of test testin ing g •
A preJdetermined leel of significance should be specified.
•
6ither +N or %N leel can be considered for the purpose.
0eci 0ecidi ding ng the the 0is 0istr trib ibut utio ion n to to use use99 •
2i3 2i3
23
hoice should be made generally relates to ormal distribution or tJdistribution.
Sele Select ctio ion n of rand random om sam sampl plee ? compu computi ting ng an Appro ppropr pria iate te alu aluee •
Selection of Random sample
•
omputing suitable alue
•
0rawing a sample for furnishing 6mpirical data.
alculation of Brobability9 •
2i3 2i3
Ma#ing a formal statement of the null hypothesis and alternatie hypothesis.
The dierged results from the expected results" when 7o is true.
om omparin aring g the the pro proba bab bilit ility y9 •
-y ma#ing a comparison with the assumed significance leel.
•
,f the alue is less than or e(ual to 7o" in case of oneJtailed test" 7o is re)ected. 7ere type , error is committed.
•
,f the alue is greater than the mean" 7o is accepted. /e /ere re typeJ, error is committed.
•
compile" compare ? compute the data and come out with the inference.
;ull ypothesis: The null hypothesis is the proposition or proposal that implies no effect on the phenomena.
the one one pred predict icti iee statem statement ent that that impl implie iess some some effe effect ct on the the -lternati/e ypothesis 9 ,s the phenomena. #oncepts Relating to Testing of ypothesis: &-M0L+ &9R(+@ &ling 4esign:
An art of obtaining a sample from a gien population. The techni(ue or procedure the researcher adopts for selecting items for the sample from the population or unierse.
&teps in sampling 4esign Type of 9ni/erse:
%3 The first step step in sampling sampling design" design" is to clearly clearly define the the total number number of items $ cases to be studied" which is technically #nown as “>,@6RS6” “>,@6RS6” 1inite >nierse ,nfinite Finite 9ni/erse:
6g9
The number of items is certain.
o. of stu students in a class. ss. o. of wor#ers in a factory. factory.
Infinite 9ni/erse:
6g9
The number of items is infinite. 2o idea about the number of items3
hen henn nai popul opulat atio ion" n" o. o. of of sta stars rs
&3 Samp Sampli ling ng >nit >nit99 •
A geographical area li#e a state" district or illage.
•
1amily" 1amily" religious community or a school. s chool.
•
,ndiidual 2Researcher can select one or two such units3.
'3 Sour Source ce Eis Eist9 t9
4the 4therw rwis isee #now #nown n as “Sam “Sampl plin ing g 1ra 1ram me”
•
onsists of names of all items of a unierse.
•
,f not aailable the researcher has to prepare a “Source list”.
•
,t must be reliable" comprehensie" correct and appropriate.
•
,t should be the representatie of the population $ unierse.
*3 Si5e Si5e of samp sample le99 •
Refers to the “number of items” to be chosen from the unierse.
•
Si5e of sample must be optimum. optimum. An optimum optimum sample sample may defined as the one that satisfies.
•
The re(uirements of representaties.
•
1lexibility
•
6fficiency
•
Reliability
•
osts or budget should be considered.
Factors Influencing siAe of sample 9 0arameters of Interest:
The items or parameters are selected based on the researchers own interest.
2udgetary constraint :
ost consideration exercises a ma)or influence.
a3 &ling 0rocedure:
The type or techni(ue used by the researcher to select the items.
The techni(ue should be selected so that for a gien sample si5e ? budget" the sampling error must be ery small or negligible.
&ling +rror: may be caused 2,n case of on probability sampling3 due to
2%3 ,nteriewer -ias 2&3 Mista#es 2'3 on response problems 2*3 Cuestionnaire design flaws 2+3 0ata processing ? analysis errors ,n case of probability sampling" 2homogenous items 3 the sampling error is negligible since the sample is more accurate. haracteristics of a 8ood sample 9
Should bind a truly representatie sample.
Small sampling error
Should fit into the budgetary constraints.
Result should be applicable in general.
haracteristics of sample techni(ues9 %3 Much Much chea cheap per &3 Saes time ime '3 Much Much reli reliab able le *3 Suitable Suitable for for carry carrying ing out different different sureys sureys +3 Scien Scienti tific fic in atu ature re
Adantages of sampling9 %3 @ery accu accura rate te &3 6con 6conom omica icall in in at atur uree '3 @ery rel relia iabl blee *3 Suitab Suitable le for for diffe differen rentt surey sureyss +3 Eess Eess tim timee cons consum umpt ptio ion n ;3 ,n case of large large unierse" unierse" sampling sampling method method is the only practical practical method method for collectin collecting g the data. 4ifferent types of sample 4esign 9
lassified under two general categories. %3 Brob Brobab abil ility ity samp sampli ling ng &3 on = Brob Brobabi ability lity sampli sampling. ng. Brobability sampling9
4therwise #nown as ‘choice sampling! or ‘random sampling!.
6ery item has an e(ual chance of being included in the sample.
6g9 Eotteries 2or3 subscribers
/hen /hen done done prop propert erty y" prob probab abil ilit ity y sampl samplin ing g ensu ensure ress that that the the samp sample le has has a simi simila lar r composition and profile as that of the entire population.
< different types of probability sampling" %3 Simp Simple le Rand Random om samp sampli ling ng
&3 Strati Stratifie fied d Rand Random om sampli sampling ng '3 lus luste terr samp sampli ling ng *3 Syste Systema matic tic sampl samplin ing g +3 Area rea sam samplin pling g ;3 Mult Multii sta stage ge samp sampli ling ng <3 Sampling Sampling with probability probability propotion propotional al to si5e 2%3
Sample Random Sampling
The sample is drawn so that each person or item has an e(ual chance of being drawn during the selection. 6g9
2&3 2&3
Eotteries ies 2in a ball box3
Stra Strati tifi fied ed Rand Random om sam samplin pling9 g9 2str 2strat ataa = lay layer ers3 s3 -
Stratified sampling techni(ue is generally used when the population is heterogeneous.
-
The The entire entire popula populatio tion n is diide diided d into into sub popula populatio tion n 2sub 2sub groups groups33 2i.e. 2i.e. the sub population being homogenous3. homogenous3.
-
,tems are selected from each stratum.
-
This method is more reliable ? accurate.
-
6g9 6g9 +I stud studen ents ts of a scho school ol hai haing ng %III %III stude student ntss on a tota totall were were sele select cted ed ? interiewed on the interest in music.
The students were grouped based on their age" < years" G years" H years" %I years ? %% years. 1rom each age group" + students were chosen and totally +I students were interiewed. 2'3
luster sampling9 •
The entire population is sub diided into mutually exclusie groups or clusters
•
Simple Random sampling is applied and the need clusters are selected for the study.
•
,f all the elements found in the selected cluster is ta#en for the study" then it is one stage cluster sampling.
•
,f random sampling is applied in selecting elements found within the clusters" it is two stage cluster sampling.
2*3
Systematic sampling9 -
Selecting eery nth element for the study. %st" +th" %Ith" %+th" &Ith OOOOOOOOOOOOO.
2+3 Area sampling9 diisions. 2;3
when the clusters are in the form of some geographical sub
Multi stage sampling9 -
,f the researcher selects elements or items at different stages" it is multi stage sampling.
-
6g9 Surey of wor# efficiency in nationali5ed baul#s
-
Stage leel
-
0istrict leel
-
Towns
-
@illages
,tems are selected at four stages $ leels. 2<3 2<3
Samp Sampli ling ng with with pro proba babi bili lity ty pro propo port rtio iona nall to si5e si5e99 -
The probability of inclusion into the study is directly proportional to the si5e of the clusters.
-
This techni(ue is used when the no. of elements present in each cluster aries.
-
0epending on re(uirement of the researcher the cluster which is more appropriate can be selected for the study.
,,.
;on 0robability sampling: -
6ach item does not hae an e(ual chance of being included in the sample.
-
' types of non probability samplings are" %3 on onen enie ienc ncee sampl samplin ing g &3 Cuot Cuotaa sam sampl plin ing g '3 Dudg Dudgme menta ntall sam sampl plin ing g
%3
#on/enience sampling: -
hoosing items at the conenience of the Researcher. 6g9 Street interiews 2sampling of people who are at easy access3
0rawbac#9 Eac# of accuracy &.
6uota sampling
The researcher simply assume (uotas" with certain restrictions imposed on how they should be selected. 6g9 aste basic -enefits9 less expensie" ery conenient
'.
Budgment sampling : 2otherwise #nown as purposie sampling3
Researcher employs his own “6xpert” )udgment about who to include in the sample frame. 4isad/antages 4isad/antages of sampling:
%3 ,nad ,nade( e(ua uacy cy of of samp samples les &3 han hance cess of of bia biass '3 Brob Broble lems ms of accur accuracy acy *3 0ifficulty 0ifficulty of getting getting the representatie representatie sample. sample. +3 >ntra >ntrain ined ed Manpo Manpowe wer. r. ;3 Absen Absence ce of of ,nfo ,nform rman ants ts <3 hance hancess of commit committin ting g error errors. s. &ling +rror: Sampling error is the deiation of the selected sample from the true characteristics" traits" behaior" (ualities or figures of the entire population. 4ata #ollection
0ata ollection is the systematic gathering of information 2data3 for a particular purpose from arious sources. 2@arious sources can be (uestionnaires" interiews" obserations existing records and electronic deices3. Two Two ,mportant sources of ,nformation are" 2i3
Brimary 0ata
2ii3 Secondary 0ata 0rimary 4ata:
Refers to the data collected for the first time 24riginal data3 +5ample: Broceedings from conferences meetings" Students records. &econdary 4ata:
Refers to the data that hae already been collected and used earlier by somebody or some agency. +5ample: 4nline database" 7istorical boo#s etc. +5ample: Ta#ing Ta#ing census 2total population3 of 8oernment of ,ndia = Brimary 0ata.
/hen research is done by some other scientist on the basis of this data" it is secondary data. Selecting A particular source of 0ata depends on" 2%3 Burpose Burpose ? Scope Scope of the study study..
2&3 2'3 2*3 2+3 2;3
Aailabi Aailability lity of of time. time. Aailabi Aailability lity of Resource Resources. s. The degree degree of Accuracy Accuracy desired desired.. Statistical Statistical tools tools to be used. used. Sources Sources of ,nform ,nformation ation 2data3. 2data3.
!" 0urpose ) &cope of 4ata #ollection:
Should be clearly stated at the ery beginning of the study.
A statement indicating the Research problem and the type of information needed for the
study in order to sole the Research Broblem" is needed. ,ts purpose is to establish a factual information for ma#ing decisions.
Scope of the en(uiry means the coerage with regard to the type of information" the sub)ect matter and geographical area.
1b3 -/ailability of Time:?
The inestigation should be done within a reasonable period of time.
Ta#ing Ta#ing which the information collected may become outdated. 6xample9 0emand of a new product launched is studied" if the result comes out after & years" by the time the producer may attain great lose.
So" ma#e sure the inestigation is carried out within a reasonable period of time.
1c3 -/ailability of Resources:
,nestigation or data collection greatly depends" on resources aailable li#e" %. o. o. of of s#il s#ille led d pers person onne nell &. The The 1ina 1inanc ncia iall Bosi Bositi tion on..
,f the no.of s#illed personnel to carry our the en(uiry is sufficient and the aailability of
funds is not a problem" the datas can be collected from a big area coering a good number of samples. 1d3 The desiredCe5pected 4egree of -ccuracy:?
0eciding the degree of accuracy is a must for the inestigator.
-ecause “Absolute Accuracy” is not possible in statistical wor#s.
Since “Statistics” is based on estimates" tools used for measurements in not always
perfect ? there may be unintentional bias on the part of the inestigator" enumerator or informant. 8enerally the degree of accuracy depends upon the ob)ections of the en(uiry.
6xample9 0uring purchase of 8old" een %$%I th gram in its weight is significant. -ut it is not the same in case of purchasing rice or wheat. 1e3 &tatistical Tools to be used:
/ell defined or identifiable ob)ect or group of ob)ects that can be measured or counted in
a statistical inestigation is called statistical >nit. ,n the absence absence of a clear and precise “Statistical “Statistical >nit” Serious errors may be committed committed
by collecting irreleant data. This will ultimately lead to fallacious 2/rong3 2/rong3 conclusions. 1f3 &ources of Information:
The researcher has to decide about the source from which the information can be obtained or collected.
%. 1irst hand data. &. The data from other published sources. 2Bublications" Dournal" Maga5ines etc.3 1g3 Method of 4ata #ollection:?
%. Brimary 0ata. &. Secondary 0ata.
0rimary 4ata:?
1irst hand data.
6ither ‘ensus! or ‘Sample! techni(ue techni(ue is to be used.
#ensus: Total Total no.of items hae to be inestigated. &le: Selected representaties from the total population hae to be inestigated. #+;&9&
&-M0L+
Total tal o. o. of item items" s" %IIN %IIN Accur ccurac acy y Selected Representations" %IIN Accuracy attain attained" ed" Time Time consum consuming ing"" 6xpensi 6xpensie e cannot be attained" Eess time ta#en" Eess More Eabour. expensie" Eess Eaborious.
Should be ery cautious and careful while choosing a particular method.
Methods of #ollecting 0rimary 4ata:
May be obtained by applying any of the following methods"
%. 0irect Bersonal ,nteriews. &. ,ndirect 4ral ,nteriews. '. ,nformation from orrespondents. *. Mailed (uestionnaire methods" +. Schedule sent through 6numerators. !" 4irect 0ersonal Inter/iews:
A face to face contact is made with the informants.
,nte ,nter rie iewe werr as#s as#s them them (uest (uestio ions ns regard regardin ing g the the study study and and trie triess to get get the the desi desired red information.
The information thus collected is first hand and original.
Merits:
2i3 2i3 2ii3 2ii3 2iii 2iii33 2i3 2i3 23 23
Resp Respon onse se is enco encour urag agin ing g whe when n per perso sona nall lly y con conta tact cted ed.. ,nform ,nformatio ation n are more more accur accurate ate 2if not found found accurate accurate"" he can be reex reexami amined ned or ros rossJ sJ examined" there by try to obtain the information3. Bro Broid ides es hope hope for for gettin getting g supp supplem lemen enta tary ry infor informa matio tion" n" which which may be of grea greate terr use use latter. A delic delicat atee situ situat atio ion n 2Som 2Somee Bers Berson onne nell Cues Cuesti tion ons3 s3 can can usua usuall lly y be hand handle led d more more effectiely by a personnel interiew than other surey techni(ues. The The inter interie iewe werr can ad)us ad)ustt the lang langua uage ge accor accordi ding ng to the the status status and and educat educatio iona nall leel leel of the person interiewed" thereby can aoid inconenience and misinterpretation.
4emerits:
2i3 2i3 2ii3 2ii3
6xpe 6xpens nsi iee = when when the the no. no. of info inform rman ants ts is larg large. e. 8rea 8reate terr chance chance of perso personn nnel el bias bias and pre)u pre)udi dice ce.. 2ta#in 2ta#ing g a deci decisio sion n befor beforee findi finding ng the the full facts3. 2iii 2iii33 ,nter ,nteri iew ewer er shou should ld be thor thorou ough ghly ly traine trained d ? expe experie rienc nced ed.. 2unt 2untrai raine ned d pers person onal al will will spoil the wor#3 2i3 2i3 Time ime cons consum umin ing g 2,nt 2,nter eri iew ewer erss can can be cont contac acte ted d only only at the the con conen enie ienc ncee of the informants3 #onclusion:
0irect personal ,nteriews can be used in ,ntensie 1ield Surey rather than 6xtensie
1ield Surey. The present day of extreme adancement in communication system" a good number of
surey" can be conducted by ews papers ? teleision channels by replying through e.mails ? SMS. They are less expensie ? extremely (uic#.
0efects = o Bhone or Teleision" delicate ? sensitie Cuestions cannot be as#ed" alue
answers. $" Indirect .ral Inter/iews:
The inestigator contact a third party called “/itnesses” who is capable of supplying
necessary information. 8enerally adopted when the information to be obtained is complex or the informer is not
willing to reeal the answers. 6xample9 /hen a drug addicted person is interiewed" he will not be willing to response directly" so the information are gathered ia agents 2may be relaties3. The accuracy of this method depends on" 2i3 2i3 2ii3 2ii3 2iii 2iii33
The pro proe en n int integ egri rity ty of the the Ag Agency ency$B $Ber erso son. n. Abil Ability ity of of the int inter eri iew ewer er to act act the the right right info inform rmati ation on fro from m the wit witne ness. ss. -rib -ribery ery or othe otherr reason reasonss may twist twist the the witness witness to gie gie false false infor informa mati tion on there there by bringing a wrong conclusion. conclusion. #onclusion: 2i3 Eet more care should be ta#en in the selection of ‘/itness! because it is on their iews" the final conclusion is reached.
%" Information From #orrespondents:
The inestigator appoints local agents or correspondents in different places to collect
information under this method. These correspondents collect the information and transfer or transmit the information to
the central office where the data are processed. +5ample: ews paper Agencies.
8enerally these Agencies are paid staff" sometimes honorary.
-d/antages:
%. heap &. an be used to get get regular informat information ion at regular regular interals interals 2daily" 2daily" wee#ly or or monthly3. monthly3. 4isad/antages: 2 i3
Eac#s Accuracy.
'" Mailed 6uestionnaire Method:
A list of (uestions pertaining to the surey is #nown as “Cuestionnaire”. ,t is prepared
and sent to arious informants by post. The (uestionnaire contains (uestions and proides space for answers.
A re(uest is made to the informants through a coering letter to fill up the (uestionnaire
and sent it bac# within a specified time. The (uestionnaire studied can be classified as" %3 &3 '3 *3
The degree degree to which the (uestion (uestionnaire naire is formali5ed formali5ed or structu structure. re. The disgui disguise$lac# se$lac# of disguise disguise of the the (uestionn (uestionnaire. aire. The commun communica ication tion method method used. used. /hen /hen no formal formal (uestio (uestionna nnaire ire is used" used" interie interiewer werss adopt adopt other tactics tactics li#e li#e showin showing g pictures on which respondents comments. /hen a research follows a prescribed se(uence of Cuestions it is ‘structured study!.
/hen no prescribed se(uence of Cuestion exists" the study is onJStructured.
/hen the (uestionnaire is constructed in such a way that the “4b)ectie is clear” 2the
(uestionnaire3 it is #nown as onJdisguised. /hen the ob)ectie is not clear" the (uestionnaire is a “0isguised” one.
4n this basis" * types of studies can be distinguished"
2i3 onJdisguised Structured. 2ii3 2ii3 onJd onJdis isg guise uised d on onJstr Jstru uctur ctured ed.. 2iii3 0isgu sguised sed Str Structu ctured. ed. 2i 2i3 0isg isguise uised d onJ onJSt Stru ruct ctu ured red. Merits: Cuestionnaire Methods" 2%3 6asily adopted in large populations and when the informants are wide spread oer a large large geographical area. 2&3 Relatiely Relatiely cheap cheap ? timely timely..
2'3 ,nformation ,nformation pertaining pertaining to personnel personnel life or family or confidential confidential matters will be reealed in written rather than personal interiews or telephones. 4emerits: 2%3 Applicable Applicable only only among among literate people. people. 2&3 >ncertainty >ncertainty of the Respondents Respondents lac#s lac#s coJoperation. coJoperation. 2'3 Eac#s Accuracy Accuracy because because the information information may not be correct. =uideline to make this method more +ffecti/e: 2i3 2i3 Brep repaid aid po postag stagee sta stam mp sho shoul uld d be be aff affix ixed ed.. 2ii3 Sample sh should be large. 2iii 2iii33 Cues Cuesti tion onna nair iree shou should ld be be inte intere rest stin ing. g. 2i3 2i3 Eega Eegall omp ompuls ulsio ion n shou should ld be be made made to pro proi ide de in in form format atio ions ns.. *" &chedules sent through +numerators:? Sending Schedules through enumerators or interiewers.
The enumerators contacts the informants" gets replied to the (uestions contained in the
schedule and fill them in their own handwriting. 7ere the (uestions are as#ed face to face and the response is papered.
Merits:
2%3 Applicable Applicable among among illiterate illiterates. s. 2&3 @ery @ery little scope for onJresponse" as the enumerators go personally. personally. 2'3 ,nformation ,nformation are more Reliable Reliable ? Accurate Accurate.. 4emerits: 2%3 6xpensie 6xpensie = Since enumerators enumerators are paid personals personals.. 2&3 Success Success = depends on the efficiency efficiency of the enumerato enumerators. rs. 2'3 ,nteriewer ,nteriewer re(uires re(uires training and experience experience.. 2*3 @ariations @ariations in answers must must be remoed remoed to aoid ariations. &econdary 4ata: Are those data which hae already been collected and analy5ed by some earlier agency for its own use and later the same data is used by a different agency. agency. Sources of Secondary 0ata9 2%3 Bublished Bublished Sources. Sources. 2&3 >npublishe >npublished d Sources. Sources. !" 0ublished &ources: The 8oernment" ,nter ational and local agencies publish statistical data. hief Among them" 1i3 Inter ;ational 0ublications:? 0ublications:?
,nter ational ,nstitutions ? bodies li#e ,.M.D.2,nternational Monetary 1und3" ,.-.R.0. 2,nternational -an# of Reconstruction and 0eelopment3" ,..A.1.6. 2,nternational onference on Agriculture ? 1ood 6ngineering3 and >..4. >nited ations 4rgani5ation publish regular ? occasional reports on 6conomics ? Statistical matters.
1ii3 .fficial 0ublications of #entral ) &tate =o/ernments:
Seeral departments of the entral and State 8oernments publish reports on different sub)ects. +5ample:? Bublications are"
2a3 Resere Resere -an# of ,ndia ,ndia -ulletin. -ulletin. 2b3 ensus ensus of of ,ndia. ,ndia. 2c3 Statistical Statistical Abstrac Abstractt of the states. 2d3 Agricultural Agricultural Statistic Statisticss of ,ndia. ,ndia. 2e3 ,ndian Trade Trade Dournal. Dournal. 1iii3 &emi .fficial 0ublications: 2a3 ,ndian Statistical Statistical ,nstitut ,nstitutee 2,.S.,3 2,.S.,3 2b3 ,ndian ouncil ouncil of Agricultu Agricultural ral Research 2,..A.R.3 2,..A.R.3 2c3 ,ndian Agricul Agricultural tural Statistics Statistics Research ,nstitute 2,.A.S.R.,.3 2,.A.S.R.,.3 Bublish the findings of their research programs.
1i/3 0ublications of /arious commercial and financial institutions" 1/3 Reports of /arious committees ) commissions appointed by the =o/ernment"
2a3 Ra) ommittee!s Report on Agricultural Taxation. 2b3 /anchoo ommittee!s Report on Taxation ? -lac# Money. 1/i3 Bournals ) ;ews 0apers:?
Bowerful source of secondary data.
urrent ? important matter can be obtained.
1rom Dournals ? ews papers li#e 6conomic Times" ommerce apital" ,ndian 1inance"
etc." 9npublished &ources:
Records maintained by 8oernment ? Briate 4ffices.
Theses of Research Scholars from uniersities ? institutions.
0recautions in the use of secondary 4ata:
Broper scrutiny is made before they are used by inestigator.
-e 6xtraJautious while using secondary data.
Should not be accepted as such because the secondary data may process" 2-ias" ,nade(uate Si5e" Substitution" errors of definition or arithmetical errors3
Factors to be #onsidered before using the secondary 4ata: 1i3 &uitability of 4ata:
ma#e sure that the data aailable is suitable for the purpose of en(uiry.
1ii3 -deuacy of 4ata:
Ma#e sure that the data are sufficient or ade(uate for the present analysis.
1iii3 Reliability of 4ata:
The reliability of data is must" without which there is no meaning in the research.
The reliability of data can be tested by finding the agency that has collected the data" if
the agency has used proper methods for collection the data. +4ITI;=: 4nce data hae been obtained from primary or secondary sources the next step in a statistical inestigation is to edit the data. 2to Scrutini5e3.
4b)ectie" editing is to detect possible errors and irregulations.
6diting needs great care and attention.
6diting Secondary data is simple but the data collected from surey 2Brimary 0ata3 need
excessie editing. +diting 0rimary 4ata7 2i3 2i3 The dat dataa sh should ould be com complet pletee in in ee eery ry resp respec ect. t. 2ii3 The dat dataa sh should be be ac accurate. 2iii 2iii33 The dat dataa sh should ould be cons consis ista tant nt.. 2i 2i3 The dat dataa sh should ould be homog omogen enou ouss !" +diting For #ompleteness:
The editor should see that each schedule or (uestionnaire is complete in all respects.
Answers to eery (uestions is furnished.
,f not answered" try to meet them in person to get the answers.
,f not )ust mar# “o Answer”.
$" +diting For -ccuracy:
The reliability of conclusions depends on the correctness of in formations.
,f the information is wrong" the conclusion can neer be alid.
6ditor should see that the in formations are accurate in all respects.
Arithmetic errors can be detected easily ? corrected.
,f the error is due to fault information supplied" it may be difficult difficult to erify.
%" +diting For #onsistency: #onsistency:
6ditor should see that the answer to (uestions are not contradictory in nature.
+5ample: Are you a student: o which class do you study: P
The answers are contradictory and such answers should be classified. '" +diting For omogeneity:
>nderstand the (uestions in the same sense.
hec# uniform interpretation and ma#e sure the information supplied by the arious
informants are homogenous ? uniform. +5ample: ,ncome 2Qearly" Monthly" /ee#ly" 0aily3 #hoice 2etween 0rimary ) &econdary 4ata:
A proper choice between the type of data 2Brimary or Secondary3 needed for a particular statistical inestigations is to be made by considering the nature" ob)ectie" scope of the study" time frame ? finances and the degree of precision aimed at" and the status of the Agency.
ow" Secondary data are generally used from fairly reliable published data by
8oernment" Briate organi5ations and research agencies" periodicals maga5ines etc." ,n fact" primary data are collected only if there do not exist any secondary data.
,n some cases both Brimary ? Secondary data may be used.
69+&TI.;;-IR+
Cuestionnaire can be defined as a group of (uestions designed to collect information from a specific sub)ect. 2or3 Eist of (uestions sent to a number of persons for getting answers and which obtains standardi5ed results that can be tabulated and treated statistically. 2or3 Media of communication between the inestigator and the respondent. 8ene 8enera rally lly used used in soci social al resear research ch when when the the popu popula lati tion on is ari aried ed"" larg large" e" die diers rsee ? Scattered.
Should be designed with utmost care ? caution so that all the needed information are
collected without any difficulty. 0raft 0raftin ing g a 8ood 8ood (ues (uesti tion onna nair iree Re(u Re(uir ires es = are are"" S#il S#ill" l" /isdo isdom" m" effi effici cien ency cy and and experience. 0oints to Remember: Dhile 4rafting - 6uestionnaire
1!3 &iAe of the 6uestionnaire:
2a3 o. of (uestions should be as small as possible depending on the nature" ob)ecties ? scope of the study. 2b3 Earge no.of (uestions may irritate the informants and may be difficult to 6dit or Scrutini5e by the inestigator. 2c3 Aoid Aoid irreleant and unimportant (uestions. 2d3 Aerage Aerage o. of (uestions should be %+ to &+ 2at the most3. 2e3 ,f it is more than &+" diide it into arious sections. $" The 6uestions should be #lear:
Should be 6asy" -rief" >nambiguous2lear in meaning3" on offending" courteous in
tone" corroboratie 2Supportie3 in nature ? to the point. %" The 6uestions should be arranged in a Logical &euence:
/hen arranged Eogically" the answers can be easily tabulated or coded = and does not
leae any chance of omissions. owns a teleision. +5ample: To find if a person owns '" 6uestions should be simple to understand: understand:
@ague @ague ? 0ouble meaning words should be aoided.
+5ample: Brice$ost$Rate$ apital ,ncome$Salary. *" 6uestions should be #omprehensi/e1Includes +/erything3 and +asily -nswerable:
Cuestions should be comprehensie 2i.e.3 it should include all the needed in formations.
6asy to be answered. answere d. Aoid Aoid mathematical calculations li#e Ratios" Bercentages etc."
," 6uestions of 0ersonal -nd &ensiti/e ;ature &hould ;ot 2e -sked:
Aoid Aoid personal (uestions which the respondent may feel shy or irritated to answer.
+5ample: 0o do drin# :
,f such (uestions are unaoidable" a highest amount of politeness should be used.
E" Types of 6uestionnaire: 1a3 &hut 6uestions:
/here possible possible answers are suggested suggested by the frames ? the respondents respondents are re(uested re(uested to
the tic# one of them. Two Two types of shut Cuestions.
1i3 &imple -lternati/e -lternati/e 6uestions:
24therwise #nown as 0ichotomous (uestions3 hoose from two clear cut alternaties alter naties Qes Qes or o$ Right or /rong. 1ii3 Multiple #hoice 6uestions:
/hen it is difficult to define a clear cut alternatie" additional Cuestions between Qes ? o is inserted" +5ample: To find find if a person smo#es: 0o you smo#e:
2a3 Qes" Qes" Regularly Regular ly
2
3
2b3 o" eer
2
3
2c3 4ccasionally
2
3
2d3 Seldom 2rarely3 2
3
6asy ? onenient to answer.
Sae Time.
6asy to tabulate.
" Leading 6uestions should be -/oided:
Eong Cuestions leading to seeral answers should be aoided. ,t should be framed into short (uestions.
/hy do you use a particula particularr type type of car" say Maruti ar" +5ample: /hy
Aoid oid this this continu continuous ous
(uestions. ,nstead as#" /hich car do you use : /hy do you prefer it : G" #ross #hecks:
Should be designed to proide internal chec#s on the accuracy of the in formations gien
by the respondents. !8" 0re?Testing the 6uestionnaire:
Try out the Cuestionnaire on a small scale before using in a large scale.
The drawbac#s" short comings and problems faced in the small scale informants can be
improed or modified when used in large scale. !!" - #o/ering Letter:
A oering Eetter should be enclosed for the purpose regarding definitions" concepts ? purpose. Attach a self addressed enelope in case of mailed (uestionnaire.
Mentions about Awards Awards or incenties for (uic# reply.
Bromise to send a surey copy of the report.
&-M0LI;=
A carefully designed sample may actually be better than a poorly planned and executed census. Merits: !" It sa/es time:
Saes time because fewer items are collected and processed. $" It Reduces #ost:
Since only few items are studied" there is reduction in cost ? reduction in man power. %" More Reliable Results can be obtained:
Sampling is more Reliable because 2i3 1ewer chance of sampling error. 2ii3 6xperience" Trained ? Technical Technical people can be employed to process ? analy5e the data. '" It pro/ides more detailed in formations:?
More detailed information can be obtained by sample surey. *" .nly &ling Method to depend upon:
/hen the population is large and finite" the only method applicable is sampling. ," -dministration #on/enience:
The organi5ation and administration is easy in sample surey s urey.. E" More &cientific:
Results can be tested since more scientific. &hortcomings 1or3 4emerits !" Illusory 1False3 #onclusion:
,f sampling is not carefully planned ? executed" the conclusions may be false. $" &le ;ot Representati/e:
,f the sample ta#en from the population is not the right representatie" the result may be false or misleading. %" Lack of +5perts:
,f there is a lac# of experts to plan" execute and analy5e the samples" the result would be unsatisfactory. '" 0ersonal 2ias:
There may be personal bias ? pre)udice in choosing the sampling techni(ues. *" &iAe of &le:
,f the si5e of the sample is not appropriate" it leads to untrue conclusions. +ssentials of &ling: !" It must be the right representati/e:
The Sample selected should process the similar characteristics of the original unierse. $" omogeneity:
Selected samples should be homogenous with the samples ? the unierse. %" -deuate &les:
A good number number of items should be included for the study. '" .ptimiAation:
A proper proper si5e of sample should be maintained maintained to hae optimi5ed optimi5ed results in terms of cost ? efficiency. &tatistical Laws: Induction:
The logical process of drawing a general conclusion from the study of representatie items is called ,nduction. Sampling is based on two fundamental principles of Statistics theory 2i3 Eaw of Statistical Regularity 2ii3 The Eaw of ,nertia of Earge umbers. The Law of &tatistical: Regularity: 2Mathematical Theory of Brobability3" States"
“ A moderately large number of items chosen at random from a ery large group are almost sure to hae the characteristics of the large group.” 0roof:
%. Aerage Aerage income of %"III people is to be found out" &. /e ta#e a sample of %II people ? find the aerage. '. Another Another person ta#es %II people ? find the aerage. a erage. The Aerage Aerage income found by both the persons will hae least difference. ,f the aerage income of the same %III people is found out by census" the result will be more or less the same.
$" Law of Inertia of Large ;umbers:
,t States" 4ther >sing being e(ual" as the sample si5e increases" the results tend to be more accurate ? reliable. &ling +rror:
The deiations or difference between the actual population and the sample representatie. Reasons For &ling +rror:
%. 1aulty Selection of Sample &. Substitution %" Faulty 4emarcation 14emographic limit3 of sampling 9nit:
,n case of Area sampling the sampling units at the borders should be decided if to ta#e it or re)ect it. '" Faulty estimation techniues 9
/rong selection of sampling techni(ues. Types of &ling +rrors: 1i3 2ias +rror:
aused due to bias or pre)udice on the part of the informant. 1ii3 9nbias +rror:
6rror caused due to the ormal ourse of inestigation. Reducing &ling +rror:
Sampling 6rror can be reduced by increasing the si5e of the sample.
+H0+RIM+;T&
6xperiment is the process of examining the truth of a statistical 7ypothesis related to some research problem. 6xperiments are of two types" %. Absolute 6xperiment. &. omparatie 6xperiment. Absolute 6xperiment9 /hen a researcher wants to determine the impact of a fertili5er on the yield of a crop" it is a case of Absolute 6xperiment. omparatie 6xperiment9 /hen a researcher wants to determine the impact of one fertili5er as compared to the impact of some other fertili5er" it will be called as omparatie 6xperiment. Research 4esign are of three types7
%. Research design in case of descriptie ? diagnostic studies. &. Research design in case of exploratory Research studies. '. Research design in case of 7ypothesis Testing Research Studies. Research 4esign In case of ypothesis Testing Research &tudies:
7ypothesis testing research studies are generally #nown as 6xperimental studies.
The researcher test the casual relationship between the ariables.
Brofess Brofessor or 1isher 1isher is consid considere ered d as the pionee pioneerr of this this type type of studie studies. s. 26xper 26xperime imenta ntall
Studies3 7e performed this study when he was wor#ing at a Agricultural Research Station in
Eondon. “7is found out that" by diiding plots into different bloc#s and then by conducting
experiments in each of these bloc#s" whateer in formations is collected and inference draw drawn n from from them them can be more more relia reliabl blee Brof Brofes esso sorr 1ish 1isher er laid laid three three prin princip ciple less of 6xperimental 0esigns" %. The Brincipal of Replication
&. The Brincipal of Randomi5ation. '. The Brincipal of Eocal ontrol. The 0rincipal of Replication:
“The 6xperiment should be repeated more than once”.
The treatment is applied to many experimental units.
The information collected and the inference drawn from these experimental units will be
more reliable and statistically accruable. Aim9 To examine examine the effect of two arieties of paddy. +5ample: +5ample: A paddy field is diided into & parts. 8row one ariety in one part and the other ariety in the other. Then we compare the yield of the two parts.
0raw conclusion on that basis. ;o 0rinciple of Replication is
1ield Bart , Treatment
rrrrr
rrrrr
rrrrr
rrrrr
rr
rr
rrrrr 4ne ariety
of Baddy
Bart , ompare the yield of the two parts.
rrrrr
Another @ariety @ariety of Baddy.
Dhen 0rinciple 0rinciple of Replication is used:
1irst diide the field into seeral parts.
8row one ariety in half of the parts and the other ariety in the remaining parts.
ollect the information of the two arieties and draw the conclusion by comparing both.
The Results so obtained will be more reliable and accurate compared to the results drawn without using the principle of Replication. The 6xperiment can be repeated seeral times.
1ield
rr
rr
R
r
r
rr
rr
R
r
r
rr
rr
R
r
r
rr
rr
R
r
r
rr
rr
R
r
r
Treated
onclusion drawn.
Barts $" The 0rinciple of RandomiAation: RandomiAation:
“Brinciple of Randomi5ation “Broides us a protection against the effects of “6xtraneous
@ariables.” The ariations or effects caused by these extraneous ariables can be combined under the
heading “hance”. researcher grows one ariety of paddy in the first half of the field and the +5ample: /hen the researcher other ariety in the next half of the field" there may be a possibility or chance that the soil fertility of the first half of the field may be different in comparison to the next half.
,n this case" he may go on to cultiate the two arieties of paddy in different parts of the
field on the basis of some random sampling techni(ue. 2i.e.3 7e may apply Randomi5ation principle and protect himself from the effects of the 6xtraneous 1actors.
/hen
-y using Randomi5ation Brinciple a better estimate can be drawn.
treated
rr
rr
r
r
r
rr
rr
r
r
r
rr
rr
r
r
r
rr
rr
r
r
r
rr
rr
r
r
r
onclusion drawn is more
accurate. 2an protect 6ffects of 6xtraneous @ariables3
%" The 0rinciple of Local #ontrol:
The extraneous ariable which is a #nown source of ariability can be made to ary extensiely or deliberately oer a wide range. ow the ariability it causes can be measured and eliminated.
,n short" through the principle of Eocal ontrol" we can eliminate the ariability due to
extraneous factors from the experimental error. The extraneous ariable is brought to a control.
inds of +5perimental 4esign:
6xperimental 0esign refers to the framewor# of the structure of an experiment.
lassified into & -road ategories" %. ,nform ,nformal al 6xperim 6xperiment ental al design designs. s. &. 1orma 1ormall 6xper 6xperime imental ntal design designs" s" Informal +5perimental 4esigns:
0esigned based only on the difference between the magnitudes or performance.
Three Types"
%. -efore -efore and and after after with without out con contro troll design design.. &. After After 4nly 4nly with with ont ontrol rol design design.. '. -efore -efore and after after with with cont control rol design design.. 2efore and after without control design: onsider a test group" &tep"!: The dependent ariable is measured before introduction of the treatment. &tep"$: The treatment is introduced. &tep"%: The dependent ariable is measured after the treatment has been introduced. &tep"': ,nference9 The effect of the Treatment : The leel o the phenomenon after the treatment.
The leel of the phenomenon before the treatment.
Test Test Area Eeel of Bhenomenon Treatment Eeel of
Bhenomenon
,ntroduced
-efore Treatment 2P3
After Treatment 2Q3
6ffect of the Treatment K 2Q3 = 2P3 4emerit:
/ith the passage of time" seeral extraneous ariable may be there in the treatment effect. 1$3 -fter only with control 4esign:
&tep"!: test
Two Areas are selected" the control Area ? the a re a.
&tep"$: alone.
The The trea treatm tmen entt is intro introdu duce ced d in the the test test area area
&tep"%: The dependent ariable in both the areas are measured" at the same time. &tep"': Treatment 6ffect is calculated by subtracting the alue of the dependent ariable in the control area from its alue in the test area. Treatment: Tr eatment: !
@alue of dependent ariable in the +ffect K @alue control Area = @alue @alue of 0ependent @ariable @ariable in the test area. Test Test Area ontrol Area
Treatment ,ntroduced o
Eeel of Bhenomenon 2Q3 Eeel of Bhenomenon 23
Treatment 1%3 2efore -nd -fter with #ontrol 4esign: &tep"!: ,n this design" two areas are selected and the dependent ariables in both the areas are measured for an identical time period before treatment. &tep"$: Treatment is introduced only in the test area. &tep % : The dependent aluable is measured on both the areas 2control
area ? test area3 for an identical time period. period. effect of the treatment is determined determined by subtracting subtracting the change change in the dependent dependent &etp' : The effect aluable in the control area with the charge in the dependent aluable of the test area.
Treatment Tr eatment :?
6ffect K 223J2A33 Merits: Aoid Aoidss 6xtraneous ariables resulting from passage of time and non
22Q3 = 2P33 =
comparability of control and test areas. II Formal +5perimental 4esign:
4ffer relatiely more control and use specific statistical procedures for analysis types" %3 omplete omplete Randomi Randomi5ed 5ed design design 28enerally 28enerally called .R. .R. 0esign3 0esign3 &3 Random Randomi5ed i5ed -loc -loc# # 0esign 0esign 2R.-. 2R.-. 0esig 0esign3 n3 '3 Eatin Eatin S(uar S(uaree 0esign 0esign 2E.S. 2E.S. 0esi 0esign3 gn3 *3 1act 1actor oria iall 0es 0esig igns ns . 2%3 ompletely Randomi5ed 0esign 9J
,noles two principals" the principle of replication and the principle of Randomi5ed of the the experimental designs.
The items are randomly assigned do experimental treatments.
This design is simpler and easier. 6xample9 ,t the research has & items of &I parts and if he wishes to test to under treatment -" this completely randomi5ed design gies eery possible group of %I items selected from a set of &I" an e(ual chance of being assigned to treatment tre atment A ? treatment -.
4ne way analysis of ariance 2one way A4@A A4@A3 is used to analy5e such a design.
$" RandomiAes 2lock
The sub)ects or
4esign:?
items are first diided into groups" #nown as
J2locks> See that" the items in each group or blac# is homogenous.
Randomly select items from each gien bloc# and assign treatment.
6xtraneous ariables can be be fixed and can be be measured. measured.
The main feature of this study is" each treatment appears the same no of times in each bloc#.
This design is analy5ed anal y5ed two way analyses of ariance 2two way A4@A A4@A3 techni(ue.
%" Latin &uare 4esign:?
>sed in Agricultural Research.
E.S 0esign is used when two or more extraneous ariables is found.
+5ample: +ffect of fertiliAer on the field of wheat is do be determined"
7ere along with the effect of fertili5er" the fertility of the soil must be considered.
,f the facility of the soil is not considered along with the fertili5er the result obtained may be dependable.
Similarly the impact of the arious seeds used many also ary the yield.
To oer come this difficulty E.S design is used.
6ach fertili5er 2P%" P&" P'" P*" P+3 will appear + items but will be used only once in each
row and in each coloumn. +5ample: o treatment occurs more than once. ,
,,
,,,
,@
@
P%
A
-
0
6
P&
-
0
6
A
P'
0
6
A
-
P*
0
6
A
-
P+
6
A
-
0
#onclusion :
The field is diided into seeral bloc#s 2," ,," ,,," ,@ ? @3 and there are ariety of fertili5er 2P%" P&" P'"
P*" P+3.
-ut each fertili5er is used in each bloc# only once.
a two way -;.(- techni(ue.
'" Factorial 4esign :
Are used in experiments where the effect of the depended depended ariable" when affected by more than
one ariable is to be determined. >sed in social ? economic studies where usually large no of factors affect a particular problem.
1actorial design are of two types9 , . Simple 1actorial design ,,. omplex 1actorial designs.
&imple Factorial 4esign :
/hen the effect of the dependent ariable is affect by only two factors" it is simple factorial
designs. 4therwise #nown as “ T/4 factors 1actorial 0esign”.
#omple5 Factorial 4esign :
This design is used when more than two factors at a time affects the dependent ariable.
4r the design considers three or more independent ariable.
The greater the no of independent ariable" the higher the order of interaction" analysis possible.
-d/antage :
Accuracy
an determine the effects of more ariable in a single experiment.
.2&+R(-TI.;
4bseration is defined as a planned method of watching that inoles constraints 2steps3 to improe accuracy. #haracteristics of .bser/ation :
i. 4bseration are direct ii. ta#es place in natural situations iii. Eess Structured. i. Ma#es only (uantitatie study. study. -pplicable in :
%. Eife styles &. 6ncounters $ Settlement. '. Relationships *. 8roups $ 4rgani5ation. -cc" to to 2lock ) #amion :
%. 4bsered in natural surroundings &. >nderstands eents affecting social relations. '. ,dentifies regulaties in social life.
*. 7ypothesis free en(uiry. en(uiry. +. Aoids Aoids manipulations of independent ariable. ;. Recording is not selectie. 4ifferentiate +5perimental Techniue ) .bser/ation Techniue : +5perimental Techniue
.bser/ation Techniue
o such controls
1ew ontrols.
ot Always Always
4bseration is natural conducted in large unit. 1ewer sub)ects are watched for long period .Study is directed towards sensiti5ing the obserer $ eents.
onducted in smaller units o so. Study is towards sharpening the the )udgment. o so.
-ehaior obsered is more different.
