Chapter 12 Inference on Categorical Data © 2010 Pearson Prentice Hall. All rights reserved Section 12.1 Goodness-of-Fit Test © 2010 Pearson Prentice Hall. All rights reserved Objective • Perform a goodness-of-fit test © 2010 Pearson Prentice Hall. All rights reserved 12-104 Characteristics of the Chi-Square Distribution 1. It is not symmetric. © 2010 Pearson Prentice Hall. All rights reserved 12-105 Characteristics of the Chi-Square Distribution 1. It is not symmetric. 2. The shape of the chi-square distribution depends on the degrees of freedom, just like Student’s t-distribution. © 2010 Pearson Prentice Hall. All rights reserved 12-106 Characteristics of the Chi-Square Distribution 1. It is not symmetric. 2. The shape of the chi-square distribution depends on the degrees of freedom, just like Student’s t-distribution. 3. As the number of degrees of freedom increases, the chi-square distribution becomes more nearly symmetric. © 2010 Pearson Prentice Hall. All rights reserved 12-107 Characteristics of the Chi-Square Distribution 1. It is not symmetric. 2. The shape of the chi-square distribution depends on the degrees of freedom, just like Student’s t-distribution. 3. As the number of degrees of freedom increases, the chi-square distribution becomes more nearly symmetric. 4. The values of 2 are nonnegative, i.e., the values of 2 are greater than or equal to 0. © 2010 Pearson Prentice Hall. All rights reserved 12-108 © 2010 Pearson Prentice Hall. All rights reserved 12-109 A goodness-of-fit test is an inferential procedure used to determine whether a frequency distribution follows a specific distribution. © 2010 Pearson Prentice Hall. All rights reserved 12-110 Expected Counts Suppose that there are n independent trials of an experiment with k ≥ 3 mutually exclusive possible outcomes. Let p1 represent the probability of observing the first outcome and E1 represent the expected count of the first outcome; p2 represent the probability of observing the second outcome and E2 represent the expected count of the second outcome; and so on. The expected counts for each possible outcome are given by Ei = i = npi for i = 1, 2, …, k © 2010 Pearson Prentice Hall. All rights reserved 12-111 Parallel Example 1: Finding Expected Counts A sociologist wishes to determine whether the distribution for the number of years care-giving grandparents are responsible for their grandchildren is different today than it was in 2000. According to the United States Census Bureau, in 2000, 22.8% of grandparents have been responsible for their grandchildren less than 1 year; 23.9% of grandparents have been responsible for their grandchildren for 1 or 2 years; 17.6% of grandparents have been responsible for their grandchildren 3 or 4 years; and 35.7% of grandparents have been responsible for their grandchildren for 5 or more years. If the sociologist randomly selects 1,000 care-giving grandparents, compute the expected number within each category assuming the distribution has not changed from 2000. © 2010 Pearson Prentice Hall. All rights reserved 12-112 Solution Step 1: The probabilities are the relative frequencies from the 2000 distribution: p<1yr = 0.228 p1-2yr = 0.239 p3-4yr = 0.176 p ≥5yr = 0.357 © 2010 Pearson Prentice Hall. All rights reserved 12-113 Solution Step 2: There are n=1,000 trials of the experiment so the expected counts are: E<1yr = np<1yr = 1000(0.228) = 228 E1-2yr = np1-2yr = 1000(0.239) = 239 E3-4yr = np3-4yr =1000(0.176) = 176 E≥5yr = np ≥5yr = 1000(0.357) = 357 © 2010 Pearson Prentice Hall. All rights reserved 12-114 Test Statistic for Goodness-of-Fit Tests Let Oi represent the observed counts of category i, Ei represent the expected counts of category i, k represent the number of categories, and n represent the number of independent trials of an experiment. Then the formula 2 Oi E i 2 Ei i 1, 2, ,k approximately follows the chi-square distribution with k-1 degrees of freedom, provided that 1. all expected frequencies are greater than or equal to 1 (all Ei ≥ 1) and 2. no more than 20% of the expected frequencies are less than 5. © 2010 Pearson Prentice Hall. All rights reserved 12-115 CAUTION! Goodness-of-fit tests are used to test hypotheses regarding the distribution of a variable based on a single population. If you wish to compare two or more populations, you must use the tests for homogeneity presented in Section 12.2. © 2010 Pearson Prentice Hall. All rights reserved 12-116 The Goodness-of-Fit Test To test the hypotheses regarding a distribution, we use the steps that follow. Step 1: Determine the null and alternative hypotheses. H0: The random variable follows a certain distribution H1: The random variable does not follow a certain distribution © 2010 Pearson Prentice Hall. All rights reserved 12-117 Step 2: Decide on a level of significance, , depending on the seriousness of making a Type I error. © 2010 Pearson Prentice Hall. All rights reserved 12-118 Step 3: a) Calculate the expected counts for each of the k categories. The expected counts are Ei=npi for i = 1, 2, … , k where n is the number of trials and pi is the probability of the ith category, assuming that the null hypothesis is true. © 2010 Pearson Prentice Hall. All rights reserved 12-119 Step 3: b) Verify that the requirements for the goodnessof-fit test are satisfied. 1. All expected counts are greater than or equal to 1 (all Ei ≥ 1). 2. No more than 20% of the expected counts are less than 5. c) Compute the test statistic: 2 0 Oi E i 2 Ei Note: Oi is the observed count for the ith category. © 2010 Pearson Prentice Hall. All rights reserved 12-120 CAUTION! If the requirements in Step 3(b) are not satisfied, one option is to combine two or more of the lowfrequency categories into a single category. © 2010 Pearson Prentice Hall. All rights reserved 12-121 Classical Approach Step 4: Determine the critical value. All goodnessof-fit tests are right-tailed tests, so the 2 critical value is with k-1 degrees of freedom. © 2010 Pearson Prentice Hall. All rights reserved 12-122 Classical Approach Step 5: Compare the critical value to the test 2 2 statistic. If 0 , reject the null hypothesis. © 2010 Pearson Prentice Hall. All rights reserved 12-123 P-Value Approach Step 4: Use Table VII to obtain an approximate P-value by determining the area under the chi-square distribution with k-1 degrees of freedom to the right of the test statistic. © 2010 Pearson Prentice Hall. All rights reserved 12-124 P-Value Approach Step 5: If the P-value < , reject the null hypothesis. © 2010 Pearson Prentice Hall. All rights reserved 12-125 Step 6: State the conclusion. © 2010 Pearson Prentice Hall. All rights reserved 12-126 Parallel Example 2: Conducting a Goodness-of -Fit Test A sociologist wishes to determine whether the distribution for the number of years care-giving grandparents are responsible for their grandchildren is different today than it was in 2000. According to the United States Census Bureau, in 2000, 22.8% of grandparents have been responsible for their grandchildren less than 1 year; 23.9% of grandparents have been responsible for their grandchildren for 1 or 2 years; 17.6% of grandparents have been responsible for their grandchildren 3 or 4 years; and 35.7% of grandparents have been responsible for their grandchildren for 5 or more years. The sociologist randomly selects 1,000 care-giving grandparents and obtains the following data. © 2010 Pearson Prentice Hall. All rights reserved 12-127 Test the claim that the distribution is different today than it was in 2000 at the = 0.05 level of significance. © 2010 Pearson Prentice Hall. All rights reserved 12-128 Solution Step 1: We want to know if the distribution today is different than it was in 2000. The hypotheses are then: H0: The distribution for the number of years care-giving grandparents are responsible for their grandchildren is the same today as it was in 2000 H1: The distribution for the number of years care-giving grandparents are responsible for their grandchildren is different today than it was in 2000 © 2010 Pearson Prentice Hall. All rights reserved 12-129 Solution Step 2: The level of significance is =0.05. Step 3: (a) The expected counts were computed in Example 1. Number of Years Observed Counts Expected Counts <1 252 228 1-2 255 239 3-4 162 176 ≥5 331 357 © 2010 Pearson Prentice Hall. All rights reserved 12-130 Solution Step 3: (b) Since all expected counts are greater than or equal to 5, the requirements for the goodness-of-fit test are satisfied. (c) The test statistic is 252 228 2 2 0 228 255 239 2 239 162 176 2 176 331 357 2 357 6.605 © 2010 Pearson Prentice Hall. All rights reserved 12-131 Solution: Classical Approach Step 4: There are k = 4 categories, so we find the critical value using 4-1=3 degrees of freedom. 2 The critical value is 0.05 7.815 © 2010 Pearson Prentice Hall. All rights reserved 12-132 Solution: Classical Approach Step 5: Since the test statistic, 02 6.605 is less than 2 7.815 , we fail to reject the critical value 0.05 the null hypothesis. © 2010 Pearson Prentice Hall. All rights reserved 12-133 Solution: P-Value Approach Step 4: There are k = 4 categories. The P-value is the area under the chi-square distribution with 4-1=3 degrees of freedom to the right of 02 6.605 . Thus, P-value ≈ 0.09. © 2010 Pearson Prentice Hall. All rights reserved 12-134 Solution: P-Value Approach Step 5: Since the P-value ≈ 0.09 is greater than the level of significance = 0.05, we fail to reject the null hypothesis. © 2010 Pearson Prentice Hall. All rights reserved 12-135 Solution Step 6: There is insufficient evidence to conclude that the distribution for the number of years care-giving grandparents are responsible for their grandchildren is different today than it was in 2000 at the = 0.05 level of significance. © 2010 Pearson Prentice Hall. All rights reserved 12-136 Section 12.2 Tests for Independence and the Homogeneity of Proportions © 2010 Pearson Prentice Hall. All rights reserved Objectives 1. Perform a test for independence 2. Perform a test for homogeneity of proportions © 2010 Pearson Prentice Hall. All rights reserved 12-138 Objective 1 • Perform a Test for Independence © 2010 Pearson Prentice Hall. All rights reserved 12-139 The chi-square test for independence is used to determine whether there is an association between a row variable and column variable in a contingency table constructed from sample data. The null hypothesis is that the variables are not associated; in other words, they are independent. The alternative hypothesis is that the variables are associated, or dependent. © 2010 Pearson Prentice Hall. All rights reserved 12-140 “In Other Words” In a chi-square independence test, the null hypothesis is always H0: The variables are independent The alternative hypothesis is always H0: The variables are not independent © 2010 Pearson Prentice Hall. All rights reserved 12-141 The idea behind testing these types of claims is to compare actual counts to the counts we would expect if the null hypothesis were true (if the variables are independent). If a significant difference between the actual counts and expected counts exists, we would take this as evidence against the null hypothesis. © 2010 Pearson Prentice Hall. All rights reserved 12-142 If two events are independent, then P(A and B) = P(A)P(B) We can use the Multiplication Principle for independent events to obtain the expected proportion of observations within each cell under the assumption of independence and multiply this result by n, the sample size, in order to obtain the expected count within each cell. © 2010 Pearson Prentice Hall. All rights reserved 12-143 Parallel Example 1: Determining the Expected Counts in a Test for Independence In a poll, 883 males and 893 females were asked “If you could have only one of the following, which would you pick: money, health, or love?” Their responses are presented in the table below. Determine the expected counts within each cell assuming that gender and response are independent. Source: Based on a Fox News Poll conducted in January, 1999 © 2010 Pearson Prentice Hall. All rights reserved 12-144 Solution Step 1: We first compute the row and column totals: Money Health Love Row Totals Men 82 446 355 883 Women 46 574 273 893 Column totals 128 1020 628 1776 © 2010 Pearson Prentice Hall. All rights reserved 12-145 Solution Step 2: Next compute the relative marginal frequencies for the row variable and column variable: Money Health Love Relative Frequency Men 82 446 355 883/1776 ≈ 0.4972 Women 46 574 273 893/1776 ≈0.5028 Relative 128/1776 1020/1776 628/1776 Frequency ≈0.0721 ≈0.5743 ≈0.3536 © 2010 Pearson Prentice Hall. All rights reserved 1 12-146 Solution Step 3: Assuming gender and response are independent, we use the Multiplication Rule for Independent Events to compute the proportion of observations we would expect in each cell. Men Women Money 0.0358 0.0362 Health 0.2855 0.2888 © 2010 Pearson Prentice Hall. All rights reserved Love 0.1758 0.1778 12-147 Solution Step 4: We multiply the expected proportions from step 3 by 1776, the sample size, to obtain the expected counts under the assumption of independence. Men Wome n Money Health Love 1776(0.0358) 1776(0.2855) 1776(0.1758) ≈ 63.5808 ≈ 507.048 ≈ 312.2208 1776(0.0362) 1776(0.2888) 1776(0.1778) ≈ 64.2912 ≈ 512.9088 ≈ 315.7728 © 2010 Pearson Prentice Hall. All rights reserved 12-148 Expected Frequencies in a Chi-Square Test for Independence To find the expected frequencies in a cell when performing a chi-square independence test, multiply the row total of the row containing the cell by the column total of the column containing the cell and divide this result by the table total. That is, (row total)(column total) Expected frequency = table total © 2010 Pearson Prentice Hall. All rights reserved 12-149 Test Statistic for the Test of Independence Let Oi represent the observed number of counts in the ith cell and Ei represent the expected number of counts 2 in the ith cell. Then Oi E i 2 Ei approximately follows the chi-square distribution with (r-1)(c-1) degrees of freedom, where r is the number of rows and c is the number of columns in the contingency table, provided that (1) all expected frequencies are greater than or equal to 1 and (2) no more than 20% of the expected frequencies are less than 5. © 2010 Pearson Prentice Hall. All rights reserved 12-150 Chi-Square Test for Independence To test the association (or independence of) two variables in a contingency table: Step 1: Determine the null and alternative hypotheses. H0: The row variable and column variable are independent. H1: The row variable and column variables are dependent. © 2010 Pearson Prentice Hall. All rights reserved 12-151 Step 2: Choose a level of significance, , depending on the seriousness of making a Type I error. © 2010 Pearson Prentice Hall. All rights reserved 12-152 Step 3: a) Calculate the expected frequencies (counts) for each cell in the contingency table. b) Verify that the requirements for the chisquare test for independence are satisfied: 1. All expected frequencies are greater than or equal to 1 (all Ei ≥ 1). 2. No more than 20% of the expected frequencies are less than 5. © 2010 Pearson Prentice Hall. All rights reserved 12-153 Step 3: c) Compute the test statistic: 2 0 Oi E i 2 Ei Note: Oi is the observed count for the ith category. © 2010 Pearson Prentice Hall. All rights reserved 12-154 Classical Approach Step 4: Determine the critical value. All chi-square tests for independence are right-tailed tests, so the critical value is 2 with (r-1)(c-1) degrees of freedom, where r is the number of rows and c is the number of columns in the contingency table. © 2010 Pearson Prentice Hall. All rights reserved 12-155 © 2010 Pearson Prentice Hall. All rights reserved 12-156 Classical Approach Step 5: Compare the critical value to the test 2 2 statistic. If 0 , reject the null hypothesis. © 2010 Pearson Prentice Hall. All rights reserved 12-157 P-Value Approach Step 4: Use Table VII to determine an approximate Pvalue by determining the area under the chisquare distribution with (r-1)(c-1) degrees of freedom to the right of the test statistic. © 2010 Pearson Prentice Hall. All rights reserved 12-158 P-Value Approach Step 5: If the P-value < , reject the null hypothesis. © 2010 Pearson Prentice Hall. All rights reserved 12-159 Step 6: State the conclusion. © 2010 Pearson Prentice Hall. All rights reserved 12-160 Parallel Example 2: Performing a Chi-Square Test for Independence In a poll, 883 males and 893 females were asked “If you could have only one of the following, which would you pick: money, health, or love?” Their responses are presented in the table below. Test the claim that gender and response are independent at the = 0.05 level of significance. Source: Based on a Fox News Poll conducted in January, 1999 © 2010 Pearson Prentice Hall. All rights reserved 12-161 Solution Step 1: We want to know whether gender and response are dependent or independent so the hypotheses are: H0: gender and response are independent H1: gender and response are dependent Step 2: The level of significance is =0.05. © 2010 Pearson Prentice Hall. All rights reserved 12-162 Solution Step 3: (a) The expected frequencies were computed in Example 1 and are given in parentheses in the table below, along with the observed frequencies. Money Health Men 82 446 (63.5808) (507.048) Women 46 574 (64.2912) (512.9088) Love 355 (312.2208) 273 (315.7728) © 2010 Pearson Prentice Hall. All rights reserved 12-163 Solution Step 3: (b) Since none of the expected frequencies are less than 5, the requirements for the goodness-of-fit test are satisfied. (c) The test statistic is 82 63.5808 2 2 0 63.5808 446 507.048 2 507.048 273 315.7728 2 315.7728 36.82 © 2010 Pearson Prentice Hall. All rights reserved 12-164 Solution: Classical Approach Step 4: There are r = 2 rows and c =3 columns, so we find the critical value using (2-1)(3-1) = 2 degrees of freedom. The critical value is 2 0.05 5.99 . © 2010 Pearson Prentice Hall. All rights reserved 12-165 Solution: Classical Approach Step 5: Since the test statistic, 02 36.82 is greater 2 5.99, we reject than the critical value 0.05 the null hypothesis. © 2010 Pearson Prentice Hall. All rights reserved 12-166 Solution: P-Value Approach Step 4: There are r = 2 rows and c =3 columns so we find the P-value using (2-1)(3-1) = 2 degrees of freedom. The P-value is the area under the chisquare distribution with 2 degrees of freedom 2 36.82 to the right of is 0 which approximately 0. © 2010 Pearson Prentice Hall. All rights reserved 12-167 Solution: P-Value Approach Step 5: Since the P-value is less than the level of significance = 0.05, we reject the null hypothesis. © 2010 Pearson Prentice Hall. All rights reserved 12-168 Solution Step 6: There is sufficient evidence to conclude that gender and response are dependent at the = 0.05 level of significance. © 2010 Pearson Prentice Hall. All rights reserved 12-169 To see the relation between response and gender, we draw bar graphs of the conditional distributions of response by gender. Recall that a conditional distribution lists the relative frequency of each category of a variable, given a specific value of the other variable in a contingency table. © 2010 Pearson Prentice Hall. All rights reserved 12-170 Parallel Example 3: Constructing a Conditional Distribution and Bar Graph Find the conditional distribution of response by gender for the data from the previous example, reproduced below. Source: Based on a Fox News Poll conducted in January, 1999 © 2010 Pearson Prentice Hall. All rights reserved 12-171 Solution We first compute the conditional distribution of response by gender. Men Women Money 82/883 ≈ 0.0929 46/893 ≈ 0.0515 Health Love 446/883 355/883 ≈ 0.5051 ≈ 0.4020 574/893 273/893 ≈ 0.6428 ≈ 0.3057 © 2010 Pearson Prentice Hall. All rights reserved 12-172 Solution © 2010 Pearson Prentice Hall. All rights reserved 12-173 Objective 2 • Perform a Test for Homogeneity of Proportions © 2010 Pearson Prentice Hall. All rights reserved 12-174 In a chi-square test for homogeneity of proportions, we test whether different populations have the same proportion of individuals with some characteristic. © 2010 Pearson Prentice Hall. All rights reserved 12-175 The procedures for performing a test of homogeneity are identical to those for a test of independence. © 2010 Pearson Prentice Hall. All rights reserved 12-176 Parallel Example 5: A Test for Homogeneity of Proportions The following question was asked of a random sample of individuals in 1992, 2002, and 2008: “Would you tell me if you feel being a teacher is an occupation of very great prestige?” The results of the survey are presented below: 1992 2002 2008 Yes 418 479 525 No 602 541 485 Test the claim that the proportion of individuals that feel being a teacher is an occupation of very great prestige is the same for each year at the = 0.01 level of significance. Source: The Harris Poll © 2010 Pearson Prentice Hall. All rights reserved 12-177 Solution Step 1: The null hypothesis is a statement of “no difference” so the proportions for each year who feel that being a teacher is an occupation of very great prestige are equal. We state the hypotheses as follows: H0: p1= p2= p3 H1: At least one of the proportions is different from the others. Step 2: The level of significance is =0.01. © 2010 Pearson Prentice Hall. All rights reserved 12-178 Solution Step 3: (a) The expected frequencies are found by multiplying the appropriate row and column totals and then dividing by the total sample size. They are given in parentheses in the table below, along with the observed frequencies. Yes No 1992 418 (475.554) 602 (544.446) 2002 479 (475.554) 541 (544.446) 2008 525 (470.892) 485 (539.108) © 2010 Pearson Prentice Hall. All rights reserved 12-179 Solution Step 3: (b) Since none of the expected frequencies are less than 5, the requirements are satisfied. (c) The test statistic is 418 475.554 2 2 0 475.554 479 475.554 2 475.554 485 539.108 2 539.108 24.74 © 2010 Pearson Prentice Hall. All rights reserved 12-180 Solution: Classical Approach Step 4: There are r = 2 rows and c =3 columns, so we find the critical value using (2-1)(3-1) = 2 degrees of freedom. 2 The critical value is 0.01 9.210. © 2010 Pearson Prentice Hall. All rights reserved 12-181 Solution: Classical Approach Step 5: Since the test statistic, 02 24.74 is greater 2 9.210 , we reject than the critical value 0.01 the null hypothesis. © 2010 Pearson Prentice Hall. All rights reserved 12-182 Solution: P-Value Approach Step 4: There are r = 2 rows and c =3 columns so we find the P-value using (2-1)(3-1) = 2 degrees of freedom. The P-value is the area under the chisquare distribution with 2 degrees of freedom 2 which to the right of is 0 24.74 approximately 0. © 2010 Pearson Prentice Hall. All rights reserved 12-183 Solution: P-Value Approach Step 5: Since the P-value is less than the level of significance = 0.01, we reject the null hypothesis. © 2010 Pearson Prentice Hall. All rights reserved 12-184 Solution Step 6: There is sufficient evidence to reject the null hypothesis at the = 0.01 level of significance. We conclude that the proportion of individuals who believe that teaching is a very prestigious career is different for at least one of the three years. © 2010 Pearson Prentice Hall. All rights reserved 12-185