1. 1 Pertemuan 18 Pembandingan Dua Populasi-2 Matakuliah: A0064 / Statistik Ekonomi Tahun: 2005 Versi: 1/1

2. 2 Learning Outcomes Pada akhir pertemuan ini, diharapkan mahasiswa akan mampu : Membandingkan pengujian sampel besar untuk perbedaan antara dua proporsi populasi dan pengujian untuk kesamaan dua populasi

3. 3 Outline Materi Pengujian Sampel Besar untuk Perbedaan antara Dua Proporsi Populasi Sebaran-F dan Uji untuk Kesamaan Dua Ragam Populasi

4. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-4 Hypothesized difference is zero I: Difference between two population proportions is 0 p 1 = p 2 » H 0 : p 1 -p 2 = 0 » H 1 : p 1 -p 2  0 II: Difference between two population proportions is less than 0 p 1  p 2 » H 0 : p 1 -p 2  0 » H 1 : p 1 -p 2 > 0 Hypothesized difference is other than zero: III: Difference between two population proportions is less than D p 1  p 2 +D » H 0 :p-p 2  D » H 1 : p 1 -p 2 > D 8-5 A Large-Sample Test for the Difference between Two Population Proportions

5. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-5 A large-sample test statistic for the difference between two population proportions, when the hypothesized difference is zero: where is the sample proportion in sample 1 and is the sample proportion in sample 2. The symbol stands for the combined sample proportion in both samples, considered as a single sample. That is: A large-sample test statistic for the difference between two population proportions, when the hypothesized difference is zero: where is the sample proportion in sample 1 and is the sample proportion in sample 2. The symbol stands for the combined sample proportion in both samples, considered as a single sample. That is: When the population proportions are hypothesized to be equal, then a pooled estimator of the proportion ( ) may be used in calculating the test statistic. Comparisons of Two Population Proportions When the Hypothesized Difference Is Zero: Test Statistic

6. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-6 Carry out a two-tailed test of the equality of banks’ share of the car loan market in 1980 and 1995. Comparisons of Two Population Proportions When the Hypothesized Difference Is Zero: Example 8-8

7. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-7 0.4 0.3 0.2 0.1 0.0 z f ( z ) Standard Normal Distribution Nonrejection Region Rejection Region -z 0.05 =-1.645 z 0.05 =1.645 Test Statistic=1.415 Rejection Region 0 Since the value of the test statistic is within the nonrejection region, even at a 10% level of significance, we may conclude that there is no statistically significant difference between banks’ shares of car loans in 1980 and 1995. Example 8-8: Carrying Out the Test

8. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-8 Example 8-8: Using the Template P-value = 0.157, so do not reject H 0 at the 5% significance level.

9. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-9 Carry out a one-tailed test to determine whether the population proportion of traveler’s check buyers who buy at least $2500 in checks when sweepstakes prizes are offered as at least 10% higher than the proportion of such buyers when no sweepstakes are on. Comparisons of Two Population Proportions When the Hypothesized Difference Is Not Zero: Example 8-9

10. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-10 0.4 0.3 0.2 0.1 0.0 z f ( z ) Standard Normal Distribution Nonrejection Region Rejection Region z 0.001 =3.09 Test Statistic=3.118 0 Since the value of the test statistic is above the critical point, even for a level of significance as small as 0.001, the null hypothesis may be rejected, and we may conclude that the proportion of customers buying at least $2500 of travelers checks is at least 10% higher when sweepstakes are on. Example 8-9: Carrying Out the Test

11. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-11 Example 8-9: Using the Template P-value = 0.0009, so reject H 0 at the 5% significance level.

12. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-12 A (1-  ) 100% large-sample confidence interval for the difference between two population proportions: A 95% confidence interval using the data in example 8-9: A 95% confidence interval using the data in example 8-9: Confidence Intervals for the Difference between Two Population Proportions

13. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-13 Confidence Intervals for the Difference between Two Population Proportions – Using the Template – Using the Data from Example 8-9

14. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-14 The F distribution is the distribution of the ratio of two chi-square random variables that are independent of each other, each of which is divided by its own degrees of freedom. An F random variable with k 1 and k 2 degrees of freedom: 8-6 The F Distribution and a Test for Equality of Two Population Variances

15. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-15 The F random variable cannot be negative, so it is bound by zero on the left. The F distribution is skewed to the right. The F distribution is identified the number of degrees of freedom in the numerator, k 1, and the number of degrees of freedom in the denominator, k 2. The F random variable cannot be negative, so it is bound by zero on the left. The F distribution is skewed to the right. The F distribution is identified the number of degrees of freedom in the numerator, k 1, and the number of degrees of freedom in the denominator, k 2. The F Distribution

16. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-16 Critical Points of the F Distribution Cutting Off a Right-Tail Area of 0.05 k 1 1 2 3 4 5 6 7 8 9 k 2 1161.4199.5215.7224.6230.2234.0236.8238.9240.5 218.5119.0019.1619.2519.3019.3319.3519.3719.38 310.139.559.289.129.018.948.898.858.81 47.716.946.596.396.266.166.096.046.00 56.615.795.415.195.054.954.884.824.77 65.995.144.764.534.394.284.214.154.10 75.594.744.354.123.973.873.793.733.68 85.324.464.073.843.693.583.503.443.39 95.124.263.863.633.483.373.293.233.18 104.964.103.713.483.333.223.143.073.02 114.843.983.593.363.203.09 3.01 2.952.90 124.753.893.493.263.113.002.912.852.80 134.673.813.413.183.032.922.832.772.71 144.603.743.343.112.962.852.762.702.65 154.543.683.293.062.902.792.712.642.59 3.01 543210 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0.0 F 0.05 =3.01 f ( F ) F Distribution with 7 and 11 Degrees of Freedom F The left-hand critical point to go along with F (k1,k2) is given by: Where F (k1,k2) is the right-hand critical point for an F random variable with the reverse number of degrees of freedom. Using the Table of the F Distribution

17. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-17 The right-hand critical point read directly from the table of the F distribution is: F (6,9) =3.37 The corresponding left-hand critical point is given by: The right-hand critical point read directly from the table of the F distribution is: F (6,9) =3.37 The corresponding left-hand critical point is given by: Critical Points of the F Distribution: F(6, 9),  = 0.10

18. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-18 I: Two-Tailed Test  1 =  2 H 0 :  1 =  2 H 1 :     2 II: One-Tailed Test  1  2 H 0 :  1  2 H 1 :  1  2 I: Two-Tailed Test  1 =  2 H 0 :  1 =  2 H 1 :     2 II: One-Tailed Test  1  2 H 0 :  1  2 H 1 :  1  2 Test Statistic for the Equality of Two Population Variances

19. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-19 The economist wants to test whether or not the event (interceptions and prosecution of insider traders) has decreased the variance of prices of stocks. Example 8-10

20. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-20 Distribution with 24 and 23 Degrees of Freedom 543210 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0.0 F 0.01 =2.7 f ( F ) F Test Statistic=3.1 Since the value of the test statistic is above the critical point, even for a level of significance as small as 0.01, the null hypothesis may be rejected, and we may conclude that the variance of stock prices is reduced after the interception and prosecution of inside traders. Example 8-10: Solution

21. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-21 Example 8-10: Solution Using the Template Observe that the p- value for the test is 0.0042 which is less than 0.01. Thus the null hypothesis must be rejected at this level of significance of 0.01.

22. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-22 Example 8-11: Testing the Equality of Variances for Example 8-5

23. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-23 Since the value of the test statistic is between the critical points, even for a 20% level of significance, we can not reject the null hypothesis. We conclude the two population variances are equal. F Distribution with 13 and 8 Degrees of Freedom 543210 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0.0 F f ( F ) F 0.10 =3.28F 0.90 =(1/2.20)=0.4545 0.10 0.80 Test Statistic=1.19 Example 8-11: Solution

24. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-24 Template to test for the Difference between Two Population Variances: Example 8-11 Observe that the p- value for the test is 0.8304 which is larger than 0.05. Thus the null hypothesis cannot be rejected at this level of significance of 0.05. That is, one can assume equal variance.

25. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-25 The F Distribution Template to

26. COMPLETE 5 t h e d i t i o n BUSINESS STATISTICS Aczel/Sounderpandian McGraw-Hill/Irwin © The McGraw-Hill Companies, Inc., 2002 8-26 The Template for Testing Equality of Variances

27. 27 Penutup Pembandingan Dua Populasi merupakan bagian dari pengujian Hipotesis dimana populasinya lebih dari satu,hal ini juga merupakan salah satu bentuk inferensial statistik yang berupa pengambilan kesimpulan/ pengambilan keputusan tentang menolak atau tidak menolak (menerima) suatu pernyataan/hipotesis