Inferences Involving Two Populations – Part I
Based on a current General Social Survey (GSS), an index is created from the few questions asking about the degree of confidence in government. Six age groups are compared. Suppose the values of the index result in the following ANOVA table:
Source | Sum of Squares | d.f. | MS | F | F critical |
Model | 39 | 5 | 7.8 | 4.55 | 2.60 |
Error | 48 | 28 | 1.714 | | |
Total | 87 | 33 | | | |
Carry out the F test for equality of means using the classical approach, taking α=.05
Report the results: Since the F value produce from the ANOVA table is greater than the F critical value then we have to reject the null hypothesis because F falls in the rejection area.
Open SPSS file “binge drinking.sav” (Datasets SPSS > Other files).
Look at the relationship between the binge in college (collbing) and hours of study (hrsstudy). Test the hypothesis that there may be a significant difference in hours of study among groups of collbing at α=.05.
Which test will you use? Why? The independent T test was used because we only had two groups to test.
State the null and alternative hypotheses:
H0: There is no relationship between hours of study among groups of college binge drinking.
Ha: There was a significance relationship between the binge drinking in hours of study.
Insert appropriate tables, formatted according to the APA style.
Mean comparison: students binge in college
| N | Mean | Std. Deviation |
Never binge | 776 | 3.2861 | 1.83109 |
Binge 1+ x | 545 | 2.8881 | 1.78545 |
t-test results comparing binge groups on number of hours they studyLevene’s test for equality of variances | Levene's Test for Equality of Variances |
| F | Sig. | t | df |
| | | | |
| Equal variances assumed | 1.926 | .165 | 3.929 | 1319 |
| Equal variances not...