What do I use
Education
Achievement studies, teaching interventions, curriculum evaluation, assessment research.
Your question, and what answers it
Or ANOVA for more than two methods, with the effect size a head teacher can act on.
In ZStat: open your study, go to Analysis, and choose independent t.
Yes. Treating students as independent when they share a teacher inflates every t statistic in the analysis.
In ZStat: open your study, go to Analysis, and choose multilevel mixed.
With multicollinearity checked, because entry score and prior grade usually carry the same information.
In ZStat: open your study, go to Analysis, and choose ols regression.
Item difficulty and discrimination, and which items separate strong students from weak ones.
In ZStat: open your study, go to Analysis, and choose irt 2pl.
Before any comparison of mean attitude scores.
In ZStat: open your study, go to Analysis, and choose measurement invariance.
Paired, because the same students were measured twice.
In ZStat: open your study, go to Analysis, and choose paired t.
What goes wrong in education
- Analysing at the student level a treatment that was assigned to whole classes.
- Reporting a significant improvement without the effect size, when a two-mark gain on a hundred-mark paper is not an educational finding.