Business Busines s Anal Analytics ytics Course Catalogue Driven on R
1
Course Cours e Content of Statistical Analytics
2
1. Random Variables, Probability Distributions a. Motivate the use of statistical methods for managerial decision making b. Discuss the concepts of probability distributions and random variables c. Review methods of representing data, pictorially and through summary statistics 2. Properties of Normal Distribution a. Introduce standard normal distribution b. Discuss applications of normal distribution 3. Sampling Distributions and the Central Limit Theorem a. Introduce the concept of statistical inference b. Recognize the existence of sample-to-sample variations c. Understand central limit theorem and its implications for statistical inference
3
4. Confidence Intervals (I) a. Introduce the concept of confidence intervals as a way to make statistical inferences b. Calculate confidence intervals for population mean with known and unknown population 5. Confidence Intervals (II) a. Calculate confidence intervals for population proportions b. Calculate confidence intervals for population variance c. Quantify minimum sample sizes to achieve certain margin of error in predictions 6. Hypothesis Tests (I) a. Learn how to state null and alternative hypotheses b. Understand type-I and type-II errors c. Conduct one-sided hypothesis test for population proportion / mean
4
7. Hypothesis Tests (II) a. Conduct two-sided hypothesis tests for population proportion / mean 8. Comparison of Two Populations a. Compare the means using paired observations b. Test for the difference of two population means using independent samples c. Test for the difference of two population proportions 9. Analysis of Variance a. Introduce Design of Experiments b. Conduct one way Analysis of Variance (ANOVA) 10. Nonparametric Statistics a. Introduce the notion of statistical tests on ordinal data b. Test for the difference between mean ranks using paired observations c. Compare mean ranks in two independent samples
5
11. Introduction to regression methods; Bivariate data; Scatter plot; Covariance; Correlation coefficient; Uses and issues; Correlation and causality; Linear regression; Assumptions. 12. Several regressors; Scatter plot matrix; Multiple linear regression; Assumptions; Ordinary Least Squares method (OLS); Basic regression summary; Interpretation of coefficient estimates, standard errors, t-values and p-values, and adjusted ; ANOVA table; Basic tests. 13.Anscombe’s data sets; Need for deeper analysis; Residuals; Deletion diagnostics; Added variable plots; Partial correlation; Model adequacy checks; Plots – Fitted values vs Residuals, Regressors vs Residuals, Normal probability plot. 14. Problem of insignificance of important regressors – Collinearity; Detection – correlation matrix, VIF, variance proportion s table; Remedies; subset selection, best subset; Criteria – R2, Adjusted R2, AIC, BIC, Mallows Cp
6
15. Ridge regression; Dummy variables; Transformations – Power transformation, Box-Cox transformation. 16. Heteroscedasticity; Possible causes; Detection – graphical methods, formal tests; Remedies – Transformations, Adjustment to standard errors of OLS estimates, Generalized least squares 17. Autocorrelation; Possible causes; Detection – graphical methods, formal tests; Remedies – First differences, Adjustment to standard errors of OLS estimates, Generalized least squares, Dummy variables and autocorrelation, forecasting in the presence of autocorrelation. 18. Big data Regression analysis- R and Hadoop 19. Binary response; Linear Probability Model; Advantages and issues; Guidelines for Linear Regression Modeling
7
20. Regression Models for count data a. Generalized Linear Models b. Binary and multinomial logistic regressions c. Poisson regression d. Zero-inflated Poisson regression e. Negative Binomial regression 21. Missing Value Analysis a. Missing value patterns: Missing completely at random (MCAR). Missing at random (MAR). Missing not at random (MNAR) b. List wise deletion. Pairwise deletion c. Various imputation methods: Hot deck imputation. Mean substitution. Regression imputation. EM imputation
8
22. Survival Analysis
a. Censoring and truncation. Characteristics of survival analysis data b. Time-to-event data. Hazard and survival functions c. Kaplan-Meier estimate of survival function d. Cox proportional hazards model (ph), estimation and its analysis. Extensions e. Stratified ph; ph with time-varying covariates f. Parametric survival analysis with standard distributions g. Accelerated failure time models
9
23. Design of Experiments
a. Basic concepts: randomization, replication and control b. Experimental design for testing differences in several means: Completely randomized and randomized complete block designs. Cross-over designs c. Two-level factorial experiments---full and fractional. PlackettBurman designs d. Designs for three or more levels. Taguchi designs. Response surface designs e. Case-Control designs for campaign evaluation f. Designs for conjoint analysis
10
Course Content of Forecasting Analytics
11
1. Introduction to forecasting; Types and methods; Exploring data patterns 2. Forecasting techniques; Forecasting error; Forecasting adequacy 3. Components of time series; Trend and seasonal adjustments; Smoothing 4. AR and MA models 5. The Box-Jenkins (ARIMA) Methodology 6. Simple Linear Regression; Model fitting and forecasting 7. Multiple Regression Models; Model fitting and forecasting 8. Forecasting binary outcomes; logistic regression; Growth models 9. ARCH and GARCH; and Nonlinear models
12
Course Content of Data Mining
13
Data Mining -1 (Unsupervised Learning)
1. Basic matrix algebra 2. Introduction to data mining 3. Dimension reduction techniques: Principal component Analysis(PCA) 4. Singular Value Decomposition (SVD) 5. Association rules 6. Sequential pattern mining 7. Recommender Systems (collaborative Filtering) 8. Network Analytics: Degree centrality, Closeness Centrality etc. 9. Cluster Analysis- Application on segmentation, anomaly detection 10. Hierarchical clustering and K-means clustering with various distance measures and for continuous/ categorical variables
14
Data Mining-2 (Supervised Learning)
11. Overview of machine learning/supervised learning 12. Data exploration methods: Understanding data(distributions, visualizations), Data nuances, data transformations 13. Basic classification algorithms a. Version spaces and decision trees classifier b. K-Nearest Neighbors and Parzwen window c. Bayesian classifiers: naïve Bayes and other discriminant classifiers d. Perceptron and Logistic regression e. Neural networks 14. Advanced classification algorithms a. Bayesian Networks b. Support Vector machines 15
15. Model validation and interpretation 16. Multi class classification problem 17. Bagging(random forest) and Boosting( Gradient Boosted Decision Trees) 18. Regression Analysis 19. Recommendation engines 20. Information retrieval 21. Practical tips in modeling: Bias vs trade off, Feature engineering and incorporating domain knowledge.
16
Course Content of Data Visualization
17
PART 1: NodeXL focused
1. 3 important principles of Visualization 2. Lie Factor 3. Using consistent scales 4. Presenting data in the context 5. Data-ink ratio 6. Tufte’s Graphical Integrity Rules 7. Tufte’s Principles for Analytical Design 8. Various chart junks & how to avoid chart junks 9. Dashboards – Good, Bad & Ugly 10. Affordance Theory
18
PART 1: NodeXL focused
11. Network theory – using NodeXL a. Degree (In-degree, Out-degree) b. Centrality (Closeness, Betweeness, Eigenvector) c. Grouping / Clustering d. Facebook network hands-on 12. Big data visualization problems
19
PART 2: Tableau focused
1. Introduction to the various file types 2. How to access help 3. Quick introduction to the user interface in Tableau 4. How to connect to the data sources 5. How to join the various data sources 6. How to create data visualization using Tableau feature “Show Me” 7. Reorder & remove visualization fields 8. How to sort & filter data 9. How to create a calculated field 10. How to perform operations using cross-tab
20
PART 2: Tableau focused
11. Working with workbook data & worksheets 12. How to create a packaged workbook 13. Creating various charts such as a. Heat map b. Box and Whisker plot c. Pareto chart, etc. 14. Creating maps & setting map options 15. Creating dashboards & working with dashboard
21
Thank You
22
