17-11-2020

Data Analysis
for Contents:
Management • Learnings from Trimester-I (Pre-requisites)

II • Design of Experiments (Experimental Design)

• Estimation of Causal Relationships

Session-2 • Forecasting in Business Decision-making

A Prologue • Syllabus cum session plan (in TSM Moodle)

Course Instructor:
Dr. Goutam Sutar

1 2

Chi-Squared Test Chi-Squared Test

(for goodness-of-fit)

• Chi-squared goodness-of-fit test

• Multinomial Experiments

• Chi-Squared test of a contingency table or Test for independency

• When to use:
𝐻 : There is no significant difference between Observed and Expected frequencies
𝐻 :There is significant difference between…
𝑓 : 𝐹𝑟𝑒𝑞𝑢𝑒𝑛𝑐𝑦

𝑒 : 𝐹𝑟𝑒𝑞𝑢𝑒𝑛𝑐𝑦

𝑘: no. of categories
𝐷𝑜𝐹: 𝑘 − 1

4 5

Illustration CHI-SQUARED TEST OF A CONTINGENCY TABLE

Company A has recently conducted aggressive advertising campaigns to maintain and possibly (Test of Independency)
increase its share of the market (currently 45%) for fabric softener. Its main competitor,
• Comparable to cross-classification table for data with nominal measure.
company B, has 40% of the market, and a number of other competitors account for the
• The goal for the test is to infer whether two categorical (nominal) variables
remaining 15%. To determine whether the market shares changed after the advertising related with each other or not.

campaign, the marketing manager for company A solicited the preferences of a random sample • Also, to infer that differences exists or not among two or more population of
nominal variables.
of 200 customers of fabric softener. Of the 200 customers, 102 indicated a preference for
• Hypotheses
company A’s product, 82 preferred company B’s fabric softener, and the remaining 16
•𝐻 : Two variables are independent (There is no relationship)
preferred the products of one of the competitors. Can the analyst infer at the 5% significance
•𝐻 : Two Variables are dependant.
level that customer preferences have changed from their levels before the advertising
• Test Statistics : k is no. of cells in cross-classification table.
campaigns were launched?

6 7

1
 17-11-2020

Illustration
The MBA program was experiencing problems scheduling its courses. The demand for the program’s
optional courses and majors was quite variable from one year to the next. In one year, students seem
Graphical representation
to want marketing courses; in other years, accounting or finance are the rage. In desperation, the dean

of the business school turned to a statistics professor for assistance. The statistics professor believed
that the problem may be the variability in the academic background of the students and that the
under- graduate degree affects the choice of major. As a start, he took a random sample of last year’s

MBA students and recorded the undergraduate degree and the major selected in the graduate
program. The undergraduate degrees were BA, BEng, BBA, and several others. There are three
possible majors for the MBA students: accounting, finance, and marketing. The results were

summarized in a cross-classification table, which is shown here. Can the statistician conclude that the
undergraduate degree affects the choice of major?

Data

8 9

Step 2: Calculate probabilities of variables Step 3: Calculate Expected Frequencies by using

probabilities in step 1.

10 11

Step 4: Preparing the Contingency Table

Step 6: Decision

Step 5

12 13