Jill Binker wrote: > At 11:13 AM +0200 9/26/02, Jan Malte Wiener wrote: > >>hi, >>I have data that i do not exactly know how to statistically analyze: >> >>subjects are repeatedly asked to make a decision (e.g. left-right -> >>coded as 0 or 1). i have 20 subjects, each subject made 8 decisions. >> >>i now want to analyse whether my experimental manipulation induced a >>systematic bias in subjects answers. if that wasn't true i expected a >>chance level of 0.5 (50% left, 50% right). > > > This seems highly suspect to me. What reason is there to think people would > decide between left and right 50/50? It isn't a case of flipping a > perfectly balanced coin. We have hard-wired biases here, so to speak. I > think you need a control group to identify the proportion in an > un-treated/-manipulated situation.
thanks for your answer, i gave a bad example-> actually the decision subjects have to make is as follows: you have two possible routes to get from a to b, one route crosses two bridges, the other route crosses one bridge. the route with one bridge could be either the route to your left or to your right (counterbalanced). since all 8 decisions subjects have to make have different starting- and goal-places, i assume they can (in the first place) be treated as independent measures. so what i really would like to do is to get a single value for each subjects preferrence, and then compare the mean of single subjects preferrences to a chance level (50%). i used the 1-sample wilcoxon signed rank test to do so, but i do not exactly know how to avoid the problem of having ties ? greetinx jan -- Jan Malte Wiener Max-Planck-Institute for Biological Cybernetics Spemannstr. 38, 72076 Tuebingen, Germany Tel.: +49 7071 601 631 Email: [EMAIL PROTECTED] . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
