15 avril 2005

stats

i went to the stats dept, finally! talked with melissa for 2 hours and got all the info i needed to finish AND SEND the tq article!!! also tried to work with the pilot study and verify the reliability of my quesitonnaire... but it doesn't work well, i don't know what i'm doing wrong. tried crombach alpha and other stuff... and no, it won't work, it'll give me an alpha of 0.80 with the first construct but then i get stuff like 0.34 or 0.55.... and my constructs don't even seem to fit the "computer's" constructs. that'd not good! the conclusion of all this is the following: i have no idea what i'm doing!

i wonder if i could maybe have a real pilot at byu with a reworked questionnaire (but then how would i get the thing translated?? or should i use only high proficiency level students??).

i wrote to A. to ask her if she could recommend anyone from the psychology dept who'd be an expert in likert scales, but i doubt she'll answer. i'm going to call right now. i am discouraged, and the fact that my advisor doesn't know about all this doesn't help.

and i wrote an email to wanda fox. hopefully she'll help me!