Hi,
I am enjoying reading all the posts on the Likert Scale. I was wondering if anyone could help me with my final research paper for my master's degree.
I gave a pre and post test to a class of students regarding their attitudes toward technology. My sample for the pre test was 20, for the post it was 12 because some kids blew it off. The pre test was taken at the beginning of a one-to-one laptop implementation study. The post was taken when the laptop study was over.
Example question: I am confident I can use technology hardware responsibly in the classroom. Choices: strongly agree, agree, not sure, disagree, strongly disagree.
Here are my questions:
1. Does the decrease in sample size matter statistically? If so, how do I account for it?
2. I have tabulated the answers using percentages and written up the results, but I am worried I should have given the scale values such as strongly agree (5), agree (4). Did I do it wrong?
3. If several students go from agree to strongly agree on a question, does that show growth or gain? I am not sure how to phrase it or if I should. Should I remark on all of the gains and decreases?
4. Should I do more analysis? I have looked at paired t-tests, Wilcoxon rank sum, and Mann-Whitney U. I am having a hard time understanding any of them. Although, there are plenty of calculators out there I can have do the work for me.
If anyone had any suggestions on a simple way for me to write this up properly, I would really appreciate it. Thank you in advance.
Well you're sample is very small. In my opinion you have to exclude the missing values cases listwise. Yes the decrease in sample will matter. You lose some power to reject Ho as n decreases. You can give a percentage score or an averaged item score or a total item score. This does not matter. The results will be the same. I can't really answer your other questions. I'd use a matched ttest or a random block (repeated measures) anova to test Ho depending on # of groups you have.
Posting Permissions
|
|
Reply With Quote