Hi !
I have a data (n=50, 14 patiens and 36 controls) with a score of a cognitive test but this test is no validated in chilean population. For this, my question is: what is more adequate, from psychometric and statistical approach. Have i to analize my data with t score o raw score?
Thanks to all
you have to see if your score has or not a normal distribution (teste with Shapiro-wilk) - if yes, use the t-test. if no, use the non-parametric equivalent
To add to this, you can also look at the skewedness and kurtosis using SPSS. Generally speaking, you dont want your standard deviation of skewedness/kurtosis to be bigger than 1.96x it's standard error.
Maybe you could also find some further ideas here:
Bondi et al. 2003: Neuropsychological deficits associated with Alzheimer's disease in the very-old: Discrepancies in raw vs. standardized scores (10.1017/S1355617703950119)
Hunter & Hamilton 2002: The advantages of using standardized scores in causal analysis (10.1111/j.1468-2958.2002.tb00823.x)
@lorenz b dehen ohh indeed, these papers are that i need ! I really thanks you
- Badges
- Science topic
- Similar topics
- Psychology
- Psychometrics