================================================================== The gateway between this list and the sci.stat.edu newsgroup will be disabled on June 9. This list will be discontinued on June 21. Subscribe to the new list EDSTAT-L at Penn State using the web interface at http://lists.psu.edu/archives/edstat-l.html. ================================================================== .
> Standardization per se will not do anything about the problem of > sentence length. I thinks what you want is a rate measure rather > than a duration measure. Perhaps something like words per second > (or seconds per word). To do properly, this will involve going > back to the raw data and for each trial, computing > #words/duration (or the inverse if you prefer a seconds per word > measure). Unfortunately, ratios of means do not equal means of > ratios when the denominators change (the denominators being > either duration or #words, dedending on which measure you > adopt). You might get a rough idea of what the results would > look like, however, by dividing your mean durations for each > complexity level by the mean length of the respective sentence > type (or again the inverse). If your raw data was collected by > computer, then you hopefully have a file that indicates duration > and which sentence the person was processing (or even better its > length). Thanks to all who took time to give me good advice (Jim, Thom, Dennis, Lise, Ray, and Richard). As a starting point, I tried to avoid calculating syllables/second because it is difficult to judge when people ad or delete syllables from a word. However, it may be the best way out. There were several suggested alternatives to the z-score approach (log scores, covariant, and syllables/second). I take the listing of alternatives to mean that the z-score approach is not preferable; maybe particularly because it neutralizes within-group main effects (It was so nice to get rid of those main effects, though). If anybody thinks that there is NO problem with neutralizing certain main effects by using z-scores, let them speak up now or forever hold there peace! Thanks again for your help! Anders
