Certification in Business AnalyticsFull description
Good for ChEng who are interested on modeling.
Good for ChEng who are interested on modeling.
Good for ChEng who are interested on modeling.Full description
e-Book Gerando Insights Com Big Data e BiDescrição completa
Good for ChEng who are interested on modeling.Deskripsi lengkap
With economic globalization and continuous development of e commerce, customer relationship management CRM has become an important factor in growth of a company. CRM requires huge expenses. One way to profit from your CRM investment and drive better
With economic globalization and continuous development of e commerce, customer relationship management CRM has become an important factor in growth of a company.CRM requires huge expenses. One way to profit from your CRM investment and drive better r
Lâm Quang Vũ
Business analysis
Descripción completa
Business Analytics became the most effective thing for business in the last decade. Different multinational corporate companies like Google, IBM, Face book, Yahoo and eBay are the frontrunners in big data and business analytics in their respective bu
All the mathematical methodes you'll need
modelado matematico
Descripción: A business plan if you're just starting a business or doing a reboot. Offers key incites on how to secure financing and covers the key components of how to right a good plan
Data AnalyticsFull description
Introduction Introduc tion to t o Multi-Attribute Multi-Att ribute Decision-Making Deci sion-Making in Business Analytics A nalytics
121
4.2.3 Strengths and Limitations to to Data Envelopment Envelopment Analysis
DEA can be a very useful tool when used wisely according to Trick (1996) (1 996).. A few of the strength st rengthss that make ma ke DEA extremely useful usefu l are (Trick, 1996): (1) DEA can handle multiple input and multiple output models, (2) DEA does not require an assumption of a functional form relating inputs to outputs, (3) DMUs are directly compared against a peer or combination of peers, and (4) Inputs and outputs can have very different units. For example, X 1 could be in units of lives saved and X 2 could be in un units its of doll dollar arss wit without hout req requi uiri ring ng any a prio priori ri tr tradeade-off off bet between ween the two t wo.. The same characteristics that make DEA a powerful tool can also create limitations to the process and analysis. An analyst should keep these limitations in mind when choosing whether or not to use DEA. A few additional limitations include the following: 1. As DEA is an extreme point technique, noise in the data such as measurement error can cause significant problems. 2. DEA is good at estimati estimating ng relative relative efficiency efficiency of a DMU, but it converges very slowly to absolute absolute efficiency. efficiency. In other words, it can tell you how well you are doing compared to your peers but not compared to a theoretical maximum. maximum. 3. As DEA is a nonparametric techn technique ique,, statistical hypothesis tests are difficult and are the focus of ongoing research. 4. As a standard formulation of DEA with multip multiple le inputs and outputs creates a separate linear li near program for each DMU, large problems problems can be computationally computationally intensive. intensive. 5. Linear programmi programming ng does not ensure that all weigh weights ts are considered. We find that the values for weights are only for those that optimally determine an efficiency rating. If having all criteria weighted (inputs, outputs) is essential to the decision-maker, then do not use DEA.
4.2.4 Sensitivity Analysis
Sensitivity analysis ana lysis is always an important i mportant element element in i n analysis. ana lysis. According According to Neralic (1998), an increase in any output cannot make a solution worse rating nor a decrease in inputs alone can worsen an already achieved efficiency rating. As a result, in our examples we only decrease outputs and increase inputs as just described (Neralic, 1998). We will illustrate some sensitivity analysis, as applicable, in our illustrative examples in Section 4.2.5. 4.2.5.
