Re: What Statistical Analysis to use?

Posted by wordcount on Jun 10, 2012; 5:04pm
URL: http://spssx-discussion.165.s1.nabble.com/What-Statistical-Analysis-to-use-tp5713606p5713618.html

Sir Art Kendell!

I've no words to express in appreciation of your considerate reply, but count me novice when it comes to advanced statistics as suggested by you. Of course, Sir, the scales, both SES (Rosenberg, 1965) and CSWS (Crocker, Luhtanen, Cooper, & Bouvrette, 2003), are reliable and valid. The SES simply requires to add up scores for all 10 items and it's indeed a summative scale. The CSWS however requires to add first all the scores on each subscale and then divide by 5, which means the score range is 1-7.

I couldn't understand inerval scale. I also don't find this option under Measure in Variable View window (SPSS 17.0). Perhaps I should consider all variables as Scale only. Does it make any difference? Should I necessarily decide first whether the scale is nominal or ordinal? I understand Nominal, but what should I call the scores obtained on a Lickert type measure, Ordinal or Interval?

You have suggested Regression, but in my view ANOVA is the most suitable statistical analysis in this case. Only that I don't know how to run t-test for the first hypothesis because I don't want to see only the mean difference between pretest and posttest scores on SES. I also want to include Academic Performance, or scores obtained on tests given by the teacher, to see its effect on any change, significantly positive or significantly negative or insignificant, in SES scores. The question is how to do it. I can run t-test easily for two variables but how to include an independent variable as the third one in the analysis if t-test is only to use in this case?

In case of the 7 other hypotheses, you suggest that I should consider pretest SES scores,  centered CSWS scores, centered achievement test scores, new variables (obtained by multiplying centered CSW scores by centered achievement test scores as independent variables and the posttest SES scores as dependent variables? Should I use One-way or Two-way ANOVA if ANOVA is the right analysis in this case of finding interactive effect? Let me explain what I mean by interactive effect. Suppose five wrestlers win separate matches against opponents and two friends argue whether they won the matches because of their skills only or their weight, stamina, or height also played a role. To settle the dispute, an interactive effect of skills and weight, stamina and height each on the chances of winning the match was tested by analysis. In this case also, I want to see if academic performance alone causes a change in state self-esteem or, if combined with a particular contingency of self-worth this will affect more significantly on self-esteem of a student. Please guide me how to run analyses on SPSS for testing my 8 hypotheses, since this is the only software I'm familiar with.

I'm an undergraduate student, and this research is merely a part of courswork, and not an essential requirement for MA degree.

Thanks again for your considerate reply, Sir!

Respectfully,

Rashid