Scribd
Upload
362 views

Paired - Sample T Test (Part 3)

1. The document discusses how to conduct a paired-sample t-test, also known as a repeated measures t-test, which is used to compare the means of two sets of data obtained from the same group of samples before and after a treatment. 2. It provides steps for running a paired t-test in SPSS, including selecting the pretest and posttest variables to compare and interpreting the output tables which show differences in mean scores, the correlation between tests, and whether the difference is statistically significant. 3. An example is given of a study that administered a pretest and posttest to an experimental group that received a treatment and a control group that did not, and how to report that

Uploaded by

kinhai_see
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
362 views

Paired - Sample T Test (Part 3)

1. The document discusses how to conduct a paired-sample t-test, also known as a repeated measures t-test, which is used to compare the means of two sets of data obtained from the same group of samples before and after a treatment. 2. It provides steps for running a paired t-test in SPSS, including selecting the pretest and posttest variables to compare and interpreting the output tables which show differences in mean scores, the correlation between tests, and whether the difference is statistically significant. 3. An example is given of a study that administered a pretest and posttest to an experimental group that received a treatment and a control group that did not, and how to report that

Uploaded by

kinhai_see
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 4

1

Paired-Sample T Test (Repeated Measures) (DR SEE KIN HAI) (Part 3)


1. It is used to compare the means of 2 sets of data obtained from the same group of samples 2. This is the pretest-posttest research design after the sample has been given a treatment or intervention. 3. You will determine if there is any significant difference in the mean score. 4. Assumptions as in Part 1. Practice You wanted to investigate the effectiveness of certain treatment on students achievement. A quasiexperimental research design was chosen for this research exercise. By using the intact classes you have divided the students into 2 groups (i.e. the control and the experimental groups) each having 20 students. You had administered a pretest to all the students in both groups. The students from the experimental group were exposed to some treatment or intervention while the students from the control group were taught using traditional teaching and learning method. After few weeks (a longer period for the intervention will be more effective) both groups sat for the posttest. The results are shown below.

How to run the paired-sample t test 1. Key in all the data as in the [Data View] 2. Select [Analyze] on the menu bar then [Compare Means] then [Paired-Sample t test..] to open the dialogue box. 3. Select [Pretest] and [Posttest] and move to [Paired Variables] box, then [OK]

Interpreting the output

This table shows the mean, no of cases, SD and Std Error for the 2 tests. The mean for posttest = 65.80 > pretest of 60.80

This table shows how the 2 tests scores are correlated. The high correlation between them = 0.966 is significant at p = 0.000. For Correlated / related t test should have a substantial correlation between the 2 test scores. Be careful, this table is not the test of significance for the difference between the two variables.

This is the mean of the difference between the pretest and posttest scores = - 5.000. T-value = mean difference / std error = -5.00 / 0.768 = - 6.512 with DF = 19 and 2-tailed sig = 0.00 and is significantly different for the mean difference. For a 1-tailed level divide the p value by 2 to see if it is < 0.05. However, unless the difference has been predicted in advance of data collection on strong theoretical or empirical reasons, only 2-tailed t-test is appropriate.

Reporting the output The mean scores for Pretest = 60.8 and Posttest = 65.8 differ significantly with significant level p = 0.000. You report: There is a significant difference in the mean scores between the pretest and posttest at p < 0.05 level. The students performed significantly better in their posttest scores. This implies that the treatment may be effective in enhancing students academic performance. COURSEWORK A pretest was administered to a group of 22 students prior to a treatment/intervention and the same posttest was administered few weeks after the treatment/intervention. You are interested to determine whether there has been an improvement in the mean score as a result of this treatment/intervention.

You might also like