Differences Between Group Means (Click icon for audio) Dr. Michael R. Hyman, NMSU Differences between Groups when Comparing Means • Interval or ratio scaled variables • t-test – When groups are small – When population standard deviation is unknown • z-test – When groups are large 2 3 Null Hypothesis about Mean Differences between Groups 1 2 OR 0 1 2 4 t-Test for Difference of Means 1 2 t S X1 X 2 X1 = mean for Group 1 X2 = mean for Group 2 SX1-X2 = the pooled or combined standard error of difference between means 5 Pooled Estimate of the Standard Error t-test for the Difference of Means S X1 X 2 n1 1S12 ( n2 1) S 22 ) 1 1 n1 n2 2 n1 n2 S12 = the variance of Group 1 S22 = the variance of Group 2 n1 = the sample size of Group 1 n2 = the sample size of Group 2 6 t-Test for Difference of Means Example 202.1 132.6 33 2 S X1 X 2 2 1 1 21 14 .797 7 16.5 12.2 4 .3 t .797 .797 5.395 8 9 Comparing Two Groups when Comparing Proportions • Percentage Comparisons • Sample Proportion - P • Population Proportion - 10 Differences between Two Groups when Comparing Proportions The hypothesis is: Ho: 1 2 may be restated as: Ho: 1 2 0 11 12 Z-Test for Differences of Proportions Z p1 p 2 1 2 S p1 p 2 p1 = sample portion of successes in Group 1 p2 = sample portion of successes in Group 2 (p1 - p1) = hypothesized population proportion 1 minus hypothesized population proportion 1 minus Sp1-p2 = pooled estimate of the standard errors of difference of proportions 13 Z-Test for Differences of Proportions: Standard Deviation S p1 p2 pp = p q = n1 = n2 = 1 1 pq n1 n2 pooled estimate of proportion of success in a sample of both groups (1- p p) or a pooled estimate of proportion of failures in a sample of both groups sample size for group 1 sample size for group 2 14 Z-Test for Differences of Proportions: Example S p1 p2 1 1 .375 .625 100 100 .068 15 Z-Test for Differences of Proportions n1 p1 n2 p2 p n1 n2 16 Z-Test for Differences of Proportions: Example 100 .35 100 .4 p 100 100 .375 17 Hypothesis Test of a Proportion is the population proportion p is the sample proportion is estimated with p 18 Hypothesis Test of a Proportion H0 : . 5 H1 : . 5 19 Sp 0.60.4 100 .0024 .24 100 .04899 20 .6 .5 p Zobs .04899 Sp .1 2.04 .04899 21 Hypothesis Test of a Proportion: Another Example n 1,200 p .20 Sp pq n Sp (.2)(.8) 1200 Sp .16 1200 Sp .000133 Sp . 0115 22 Hypothesis Test of a Proportion: Another Example Z p Sp .20 .15 .0115 .05 Z .0115 Z 4.348 The Z value exceeds 1.96, so the null hypothesis should be rejected at the .05 level. Indeed it is significantt beyond the .001 Z 23 24 25