T-Test for Dependent Samples: Measuring Teaching Intervention, Lecture notes of Statistics

Download T-Test for Dependent Samples: Measuring Teaching Intervention and more Lecture notes Statistics in PDF only on Docsity!

T-TEST FOR

DEPENDENT SAMPLES

DID WE MAKE A DIFFERENCE?

 State the null hypothesis and the

research hypothesis:  The null hypothesis states that there is no difference between the means of the pretest and posttest scores

 The research hypothesis states that there will be a difference in the pretest and posttest scores

 Run the t -Test

 Using Excel, click on the data tab in your worksheet, then click on data analysis tab, then click on t-Test: Paired Two Sample for Means and click OK.  Fill in variable 1 range by highlighting the “before” column, fill in variable 2 range by highlighting the “after” column, insert zero in hypothesized mean difference, set Alpha at .05, click on new worksheet under output options (this will create a new worksheet tab and will display the results on that sheet). C:\Users\mwilder\Documents\Classes\80600\SU13\T-Test for Dependent Sample EXAMPLE for 80600.xlsx

 Analyze the Results

 Looking at the results, begin by comparing the means of the before and after scores (did the mean increase?), then note the t Stat result and compare it to the t Critical two-tail value (is the absolute value of the t Stat larger than the t Critical value?), if so confirm that the p value is less than .05 (if so, then you know that the change in scores is NOT due to chance but that the intervention made a statistically significant

difference). YEAH—your intervention worked!