power analysis for logistic regression

Ivana

New Member
#1
I am a dentist working on a PhD thesis and recently my coleagues and I submitted a paper that assesed the effect of baseline factors (tooth type, number of residual coronal walls and the type of final restoration) on the restoration failure. The sample consisted of 162 patients and I performed logistic regression that showed no significance of any of the independent variables.

A few days ago I received reviewers comments which are overall positive, however, they require a power analysis using the data obtained to be conducted in order to determine the sample size needed for finding the statistical significance.

Could you please advise me how to do this? :confused: I use SPSS 13; could it be done with it? If not, could you recommend me another software, hopefully a free one? I know that PASS offers an evaluation 1 month version, but it is limited to 100 rows of data...

I would truly appreciate an advice!! Thanks! :wave: