# Chapter 11

Other Chi-Square Tests

McGraw-Hill, Bluman, 7th ed., Chapter 11

1

Chapter 11 Overview

Introduction
11-1 Test for Goodness of Fit

11-2 Tests Using Contingency Tables

Bluman, Chapter 11

2

Chapter 11 Objectives
1. Test a distribution for goodness of fit, using
chi-square.
2. Test two variables for independence, using
chi-square.
3. Test proportions for homogeneity, using
chi-square.

Bluman, Chapter 11

3

11.1 Test for Goodness of Fit

The chi-square statistic can be used to
see whether a frequency distribution fits
a specific pattern. This is referred to as
the chi-square goodness-of-fit test.

Bluman, Chapter 11

4

= number of categories minus 1 O = observed frequency E = expected frequency   2  O  E 2 E Bluman. Chapter 11 5 .f.Test for Goodness of Fit Formula for the test for goodness of fit: where d.

The data are obtained from a random sample. Chapter 11 6 . The expected frequency for each category must be 5 or more. 2. Bluman.Assumptions for Goodness of Fit 1.

Chapter 11 7 .Chapter 11 Other Chi-Square Tests Section 11-1 Example 11-1 Page #592 Bluman.

using the data shown previously? Let α = 0.Example 11-1: Fruit Soda Flavors A market analyst wished to see whether consumers have any preference among five flavors of a new fruit soda. Is there enough evidence to reject the claim that there is no preference in the selection of fruit soda flavors.05. Chapter 11 8 . Cherry Strawberry Orange Lime Grape Observed 32 28 16 14 10 Expected 20 20 20 20 20 Step 1: State the hypotheses and identify the claim. Bluman. A sample of 100 people provided the following data. H1: Consumers show a preference. H0: Consumers show no preference (claim).

and α = 0. Step 3: Compute the test value. = 5 – 1 = 4. Chapter 11 9 .Example 11-1: Fruit Soda Flavors Cherry Strawberry Orange Lime Grape Observed 32 28 16 14 10 Expected 20 20 20 20 20 Step 2: Find the critical value.f. D. CV = 9.0 Bluman.05. 2    O  E 2 E2 2 2 2 32  20  28  20  16  20  14  20          20 20 20 20 10  20    20 2  18.488.

since 18. Chapter 11 10 . Bluman.0 > 9. The decision is to reject the null hypothesis. There is enough evidence to reject the claim that consumers show no preference for the flavors.488.Example 11-1: Fruit Soda Flavors Step 4: Make the decision. Step 5: Summarize the results.

Chapter 11 11 .Chapter 11 Other Chi-Square Tests Section 11-1 Example 11-2 Page #594 Bluman.

Bluman.10. test the claim that the percentages are the same for those people in Allegheny County. and 17 had formed their own companies. 38% were employed by another organization. 32% were self-employed. 23% were either freelancing or consulting. and 7% had formed their own companies. a local researcher surveyed 300 retired executives who had returned to work and found that 122 were working for another company. To see if these percentages are consistent with those of Allegheny County residents. 76 were either freelancing or consulting.Example 11-2: Retirees The Russel Reynold Association surveyed retired senior executives who had returned to work. Chapter 11 12 . At α = 0. They found that after returning to work. 85 were self-employed.

38(300)= 114 .Example 11-2: Retirees New Company SelfEmployed Freelancing Owns Company Observed 122 85 76 17 Expected . Chapter 11 13 . H1: The distribution is not the same as stated in the null hypothesis.23(300)= 69 . 32% are self-employed.07(300)= 21 Step 1: State the hypotheses and identify the claim. Bluman. and 7% have formed their own companies (claim).32(300)= 96 . H0: The retired executives who returned to work are distributed as follows: 38% are employed by another organization. 23% are either freelancing or consulting.

2939 Bluman.Example 11-2: Retirees New Company SelfEmployed Freelancing Owns Company Observed 122 85 76 17 Expected . D. Chapter 11 14 .23(300)= 69 . and α = 0.32(300)= 96 .38(300)= 114 . Step 3: Compute the test value.10. CV = 6.251. 2    O  E 2 E 2 2 2 2 122  114 85  96 76  69 17  21          114 96 69 21  3.07(300)= 21 Step 2: Find the critical value.f. = 4 – 1 = 3.

It can be concluded that the percentages are not significantly different from those given in the null hypothesis. Since 3.251. There is not enough evidence to reject the claim. Bluman. Step 5: Summarize the results. the decision is not to reject the null hypothesis. Chapter 11 15 .2939 < 6.Example 11-2: Retirees Step 4: Make the decision.

Chapter 11 Other Chi-Square Tests Section 11-1 Example 11-3 Page #595 Bluman. Chapter 11 16 .

Chapter 11 17 . In her district. 27 homicides. there were 68 accidental deaths. At α= 0. 16% were homicides. and 5 suicides during the past year. Accidental Homicides Suicides Observed 68 27 5 Expected 74 16 10 Bluman.10. test the claim that the percentages are equal. and 10% were suicides.Example 11-3: Firearm Deaths A researcher read that firearm-related deaths for people aged 1 to 18 were distributed as follows: 74% were accidental.

Example 11-3: Firearm Deaths Accidental Homicides Suicides Observed 68 27 5 Expected 74 16 10 Step 1: State the hypotheses and identify the claim. H0: Deaths due to firearms for people aged 1 through 18 are distributed as follows: 74% accidental. H1: The distribution is not the same as stated in the null hypothesis. Bluman. 16% homicides. Chapter 11 18 . and 10% suicides (claim).

Chapter 11 19 .   2  O  E 2 E 2 2 2 68  74  27  16  5  10        74 16 10  10.549 Bluman. and α = 0. CV = 4. = 3 – 1 = 2.605.10. D.Example 11-3: Firearm Deaths Accidental Homicides Suicides Observed 68 27 5 Expected 74 16 10 Step 2: Find the critical value. Step 3: Compute the test value.f.

Bluman. and 10% suicides.Example 11-3: Firearm Deaths Step 4: Make the decision. Step 5: Summarize the results.605. There is enough evidence to reject the claim that the distribution is 74% accidental.549 > 4. Reject the null hypothesis. since 10. Chapter 11 20 . 16% homicides.

This procedure is somewhat complicated. The calculations are shown in example 11-4 on page 597 in the text. Bluman. The hypotheses are:  H0: The variable is normally distributed.  H1:  The variable is not normally distributed. Chapter 11 21 .Test for Normality (Optional)   The chi-square goodness-of-fit test can be used to test a variable to see if it is normally distributed.

Chapter 11 22 .  The test of independence of variables is used to determine whether two variables are independent of or related to each other when a single sample is selected. Bluman. several types of hypotheses can be tested by using the chi-square test.  The test of homogeneity of proportions is used to determine whether the proportions for a variable are equal when several samples are selected from different populations.11.2 Tests Using Contingency Tables  When data can be tabulated in table form in terms of frequencies.

Test for Independence    The chi-square goodness-of-fit test can be used to test the independence of two variables. there is some relationship between the variables. The hypotheses are:  H0: There is no relationship between two variables. If the null hypothesis is rejected. Bluman.  H1: There is a relationship between two variables. Chapter 11 23 .

one must compute the expected frequencies.Test for Independence   In order to test the null hypothesis. assuming the null hypothesis is true. When data are arranged in table form for the independence test. Chapter 11 24 . the table is called a contingency table. table Bluman.

Contingency Tables  The degrees of freedom for any contingency table are d. = (rows – 1) (columns – 1) = (R – 1)(C – 1). Chapter 11 25 . Bluman.f.

Test for Independence The formula for the test for independence: where d. Chapter 11 26 . = (R – 1)(C – 1) O = observed frequency E = expected frequency =   2  O  E 2 E  row sum   column sum  grand total Bluman.f.

Chapter 11 Other Chi-Square Tests Section 11-2 Example 11-5 Page #606 Bluman. Chapter 11 27 .

05.Example 11-5: College Education and Place of Residence A sociologist wishes to see whether the number of years of college a person has completed is related to her or his place of residence. Chapter 11 Total 28 . At α = 0. can the sociologist conclude that a person’s location is dependent on the number of years of college? Location No College Four-Year Advanced Degree Degree Urban 15 12 8 35 Suburban 8 15 9 32 Rural 6 8 7 21 Total 29 35 24 88 Bluman. A sample of 88 people is selected and classified as shown.

The critical value is 4. since the degrees of freedom are (2 – 1)(3 – 1) = 2. Chapter 11 29 . Bluman. H0: A person’s place of residence is independent of the number of years of college completed. H1: A person’s place of residence is dependent on the number of years of college completed (claim).605.Example 11-5: College Education and Place of Residence Step 1: State the hypotheses and identify the claim. Step 2: Find the critical value.

73) 24  11.Example 11-5: College Education and Place of Residence Compute the expected values. Chapter 11 8 (9.55) 6 (6.73) 8 (8.  row sum   column sum  E grand total Location Urban Suburban Rural Total No College 15 (11.53) 8 (10.92) 29 E1.92) 15 (12.1 35   29    88 Four-Year Advanced Degree Degree 12 (13.55) 9 (8.73) 7 (5.35) 35 Bluman.53 Total 35 32 21 88 30 .

53 12  13. 2    O  E 2 E 15  11.55  15  12.92 8  9.01 Bluman.92    2 13.73  9  8.73  3.73        10.73 8.35 2 7  5.73 2 6  6.92    6.55    2 9.55 8  10.53   2 11.73    2 2 5.35    8. Chapter 11 31 .92 2 2 8  8.55 12.Example 11-5: College Education and Place of Residence Step 3: Compute the test value.

488.01<9. Step 5: Summarize the results. Bluman. since 3. Do not reject the null hypothesis. Chapter 11 32 .Example 11-5: College Education and Place of Residence Step 4: Make the decision. There is not enough evidence to support the claim that a person’s place of residence is dependent on the number of years of college completed.

Chapter 11 Other Chi-Square Tests Section 11-2 Example 11-6 Page #608 Bluman. Chapter 11 33 .

At α = 0. can the researcher conclude that alcohol consumption is related to gender? Alcohol Consumption Gender Low Moderate High Total Male 10 9 8 27 Female 13 16 12 41 Total 23 25 20 68 Bluman. A sample of 68 people is selected. and the following data are obtained. Chapter 11 34 .10.Example 11-6: Alcohol and Gender A researcher wishes to determine whether there is a relationship between the gender of an individual and the amount of alcohol consumed.

Bluman.488.Example 11-6: Alcohol and Gender Step 1: State the hypotheses and identify the claim. The critical value is 9. since the degrees of freedom are (3 – 1 )(3 – 1) = (2)(2) = 4. Chapter 11 35 . Step 2: Find the critical value. H1: The amount of alcohol that a person consumes is dependent on the individual’s gender (claim). H0: The amount of alcohol that a person consumes is independent of the individual’s gender.

13) 13 (13.Example 11-6: Alcohol and Gender Compute the expected values. row sum   column sum   E grand total E1.06) 20 Bluman.93) 16 (15.1 27   23   68  9.94) 12 (12.07) 25 8 (7. Chapter 11 Total 27 41 68 36 .13 Alcohol Consumption Gender Male Female Total Low Moderate High 10 (9.87) 23 9 (9.

06    2 12.87 2 2 8  7.Example 11-6: Alcohol and Gender Step 3: Compute the test value.93 13  13.06  0.93    9.283 Bluman. Chapter 11 37 .94 2 12  12.07    15. 2    O  E 2 E 10  9.94    16  15.87    13.07 2 7.13 9  9.13   2 9.

Chapter 11 38 . since .283 < 4. Do not reject the null hypothesis. 0.Example 11-6: Alcohol and Gender Step 4: Make the decision. There is not enough evidence to support the claim that the amount of alcohol a person consumes is dependent on the individual’s gender. Step 5: Summarize the results.605. Bluman.

Chapter 11 39 .Test for Homogeneity of Proportions  Homogeneity of proportions test is used when samples are selected from several different populations and the researcher is interested in determining whether the proportions of elements that have a common characteristic are the same for each population. Bluman.

Chapter 11 40 . When the null hypothesis is rejected. Bluman.Test for Homogeneity of Proportions  The hypotheses are:  H0: p1 = p2 = p3 = … = pn  H1:  At least one proportion is different from the others. it can be assumed that the proportions are not all equal.

Chapter 11 41 . Bluman. The data are obtained from a random sample.Assumptions for Homogeneity of Proportions 1. The expected frequency for each category must be 5 or more. 2.

Chapter 11 Other Chi-Square Tests Section 11-2 Example 11-7 Page #610 Bluman. Chapter 11 42 .

At α = 0. Chapter 11 43 . test the claim that the proportion of passengers from each airline who lost luggage on the flight is the same for each airline.Example 11-7: Lost Luggage A researcher selected 100 passengers from each of 3 airlines and asked them if the airline had lost their luggage on their last flight.05. Airline 1 Airline 2 Airline 3 Total Yes 10 7 4 21 No 90 93 96 279 Total 100 100 100 300 Bluman. The data are shown in the table.

991. Chapter 11 44 . since the degrees of freedom are (2 – 1 )(3 – 1) = (1)(2) = 2. The critical value is 5. Step 2: Find the critical value. H0: p1 = p2 = p3 = … = pn H1: At least one mean differs from the other. Bluman.Example 11-7: Lost Luggage Step 1: State the hypotheses.

Chapter 11 7 Total 21 279 300 45 . row sum   column sum   E grand total Yes No Total E1.Example 11-7: Lost Luggage Compute the expected values.1 21  100    300 Airline 1 Airline 2 Airline 3 10 (7) 90 (93) 100 7 (7) 93 (93) 100 4 (7) 96 (93) 100 Bluman.

765 Bluman. 2    O  E 2 E 10  7    2 7 7  7   90  93   93 7 2 2 4  7   2 7 93  93   93 2 96  93    2 93  2. Chapter 11 46 .Example 11-7: Luggage Step 3: Compute the test value.

Chapter 11 47 . Hence it seems that there is no difference in the proportions of the luggage lost by each airline. Bluman. Step 5: Summarize the results.991. since 2.Example 11-7: Lost Luggage Step 4: Make the decision. Do not reject the null hypothesis.765 < 5. There is not enough evidence to reject the claim that the proportions are equal. .