Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

39

Transcript of Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

Page 1: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.
Page 2: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

Copyright © 2011 Pearson Education, Inc.

Association between Categorical

Variables

Chapter 5

Page 3: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Which hosts send more buyers to Amazon.com?

To answer this question we must gather data on two categorical variables: Host and Purchase

Host identifies the originating site: MSN, RecipeSource, or Yahoo; Purchase indicates whether or not the visit results in a sale

Copyright © 2011 Pearson Education, Inc.

3 of 39

Page 4: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Consider Two Categorical Variables Simultaneously

A table that shows counts of cases on one categorical variable contingent on the value of another (for every combination of both variables)

Cells in a contingency table are mutually exclusive

Copyright © 2011 Pearson Education, Inc.

4 of 39

Page 5: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Contingency Table for Web Shopping

Copyright © 2011 Pearson Education, Inc.

5 of 39

Page 6: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Marginal and Conditional Distributions

• Marginal distributions appear in the “margins” of a contingency table and represent the totals (frequencies) for each categorical variable separately

• Conditional distributions refer to counts within a row or column of a contingency table (restricted to cases satisfying a condition)

Copyright © 2011 Pearson Education, Inc.

6 of 39

Page 7: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Conditional Distribution of Purchase for each Host (Column Counts and Percentages)

Copyright © 2011 Pearson Education, Inc.

7 of 39

Page 8: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Conditional Distribution

• Reveals the percentage of purchases among visitors from RecipeSource to be much less than for MSN and Yahoo

• Host and Purchase are associated

Copyright © 2011 Pearson Education, Inc.

8 of 39

Page 9: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Segmented Bar Charts

• Used to display conditional distributions

• Divides the bars in a bar chart into segments that are proportional to the percentage in each category of a second variable

Copyright © 2011 Pearson Education, Inc.

9 of 39

Page 10: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Contingency Table of Purchase by Region

Copyright © 2011 Pearson Education, Inc.

10 of 39

Page 11: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Segmented Bar Chart Shows Association

Copyright © 2011 Pearson Education, Inc.

11 of 39

Page 12: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Mosaic Plots

Alternative to segmented bar chart

A plot in which the size of each “tile” is proportional to the count in a cell of a contingency table

Copyright © 2011 Pearson Education, Inc.

12 of 39

Page 13: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Contingency Table of Shirt Size by Style

Copyright © 2011 Pearson Education, Inc.

13 of 39

Page 14: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.1 Contingency Tables

Mosaic Plot Shows Association

Copyright © 2011 Pearson Education, Inc.

14 of 39

Page 15: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.1: CAR THEFT

Motivation

Should insurance companies vary the premiums for different car models (are some cars more likely to be stolen than others)?

Copyright © 2011 Pearson Education, Inc.

15 of 39

Page 16: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.1: CAR THEFT

Method

Data obtained from the National Highway Traffic Safety Administration (NHTSA) on car theft for seven popular models (two categorical variables: type of car and whether the car was stolen).

Copyright © 2011 Pearson Education, Inc.

16 of 39

Page 17: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.1: CAR THEFT

Mechanics

Copyright © 2011 Pearson Education, Inc.

17 of 39

Page 18: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.1: CAR THEFT

Mechanics

Copyright © 2011 Pearson Education, Inc.

18 of 39

Page 19: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.1: CAR THEFT

Message

The Dodge Intrepid is more likely to be stolen than other popular models. The data suggest that higher premiums for theft insurance should be charged for models that are more likely to be stolen.

Copyright © 2011 Pearson Education, Inc.

19 of 39

Page 20: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.2 Lurking Variables and Simpson’s Paradox

Association Not Necessarily Causation

Lurking Variable: a concealed variable that affects the apparent relationship between two other variables

Simpson’s Paradox: a change in the association between two variables when data are separated into groups defined by a third variable

Copyright © 2011 Pearson Education, Inc.

20 of 39

Page 21: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.2: AIRLINE ARRIVALS

Motivation

Does it matter which of two airlines a corporate CEO chooses when flying to meetings if he wants to avoid delays?

Copyright © 2011 Pearson Education, Inc.

21 of 39

Page 22: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.2: AIRLINE ARRIVALS

Method

Data obtained from US Bureau of Transportation Statistics on flight delays for two airlines (two categorical variables: airline and whether the flight arrived on time).

Copyright © 2011 Pearson Education, Inc.

22 of 39

Page 23: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.2: AIRLINE ARRIVALS

Mechanics

Copyright © 2011 Pearson Education, Inc.

23 of 39

Page 24: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.2: AIRLINE ARRIVALS

Mechanics – Is destination a lurking variable?

Copyright © 2011 Pearson Education, Inc.

24 of 39

Page 25: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.2: AIRLINE ARRIVALS

Mechanics – This is Simpson’s Paradox

Copyright © 2011 Pearson Education, Inc.

25 of 39

Page 26: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.2: AIRLINE ARRIVALS

Message

The CEO should book on US Airways as it is more likely to arrive on time regardless of destination.

Copyright © 2011 Pearson Education, Inc.

26 of 39

Page 27: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.3 Strength of Association

Chi-Squared Statistic

A measure of association in a contingency table

Calculated based on a comparison of the observed contingency table to an artificial table with the same marginal totals but no association

Copyright © 2011 Pearson Education, Inc.

27 of 39

Page 28: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.3 Strength of Association

Contingency Table

Copyright © 2011 Pearson Education, Inc.

28 of 39

Page 29: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.3 Strength of Association

Calculating the Chi-Squared Statistic

Copyright © 2011 Pearson Education, Inc.

29 of 39

Page 30: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.3 Strength of Association

Calculating the Chi-Squared Statistic

Copyright © 2011 Pearson Education, Inc.

30 of 39

2

2 2 2 230 40 70 60 50 40 (50 60)

40 60 40 60x

2 2 2 210 10 10 10

40 60 40 60

2.5 1.67 2.5 1.67

8.33

Page 31: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.3 Strength of Association

Cramer’s V

Derived from the Chi-Squared Statistic

Ranges in value from 0 (variables are not associated) to 1(variables are perfectly associated)

Copyright © 2011 Pearson Education, Inc.

31 of 39

Page 32: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.3 Strength of Association

Calculating Cramer’s V

V = 0.20 for our exampleThere is a weak association between group

(students or staff) and attitude toward sharing copyrighted music

Copyright © 2011 Pearson Education, Inc.

32 of 39

2

min 1, 1

xV

n r c

Page 33: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

5.3 Strength of Association

Checklist: Chi-Squared and Cramer’s V

Verify that variables are categorical

Verify that there are no obvious lurking variables

Copyright © 2011 Pearson Education, Inc.

33 of 39

Page 34: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.3: REAL ESTATE

Motivation

Do people who heat their homes with gas prefer to cook with gas as well? What heating systems and appliances should a developer select for newly built homes?

Copyright © 2011 Pearson Education, Inc.

34 of 39

Page 35: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.3: REAL ESTATE

Method

The developer contacts homeowners to obtain the data. Two categorical variables: type of fuel used for home heating (gas or electric) and type of fuel used for cooking (gas or electric).

Copyright © 2011 Pearson Education, Inc.

35 of 39

Page 36: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.3: REAL ESTATE

Mechanics

Chi-Squared = 98.62; Cramer’s V = 0.47

Copyright © 2011 Pearson Education, Inc.

36 of 39

Page 37: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

4M Example 5.3: REAL ESTATE

MessageHomeowners prefer gas to electric heat by

about 2 to 1. The developer should build about two-thirds of new homes with gas heat. Put electric appliances in all homes with electric heat and in half of the homes with gas heat (assuming that buyers for new homes have the same preferences).

Copyright © 2011 Pearson Education, Inc.

37 of 39

Page 38: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

Best Practices

Use contingency tables to find and summarize association between two categorical variables.

Be on the lookout for lurking variables.

Use plots to show association.

Exploit the absence of association.

Copyright © 2011 Pearson Education, Inc.

38 of 39

Page 39: Copyright © 2011 Pearson Education, Inc. Association between Categorical Variables Chapter 5.

Pitfalls

Don’t interpret association as causation.

Don’t display too many numbers in a table.

Copyright © 2011 Pearson Education, Inc.

39 of 39