Hi Julia, You seem to be looking for a test for trend in proportions in the first question. Have a look at this page:
http://sphweb.bumc.bu.edu/otlt/MPH-Modules/BS/R/R6_CategoricalDataAnalysis/R6_CategoricalDataAnalysis6.html The second question may require GLMs using experimental condition as a predictor and proportion of each type of error as the response. Are the groups balanced? Jim On Sun, Jul 10, 2016 at 10:34 PM, Julia Edeleva <psychexpert1...@gmail.com> wrote: > Dear R-community, > > Thanks for replying to my previous post. I would need some more help, > thoug. > > I am performing statistical analysis on chidlren's accuracy rates as a > dependent variable and two predictor variables with two levels each (syntax > - subject vs object; internal NP position - pre vs post). > > As an outcome of my study, children committed 3 types of errors. I want to > compare whether children committed significantly more errors of one type as > compared to the other two types, i.e. test the scale *error 1 > error 2 > > error 3 (">" is "more than").* Which statistical test is most appropriate? > > Furthermore, I want to know whether one particular type of error is more > common in one experimental condition than in the other, i.e. test > whether *error > 1 in condition 1 is more common than error 1 in condition 2*. > > Thnx a lot > > Julia Edeleva > > *Compare different types of errors in chidren's performance. Statistical > Test? - ResearchGate*. Available from: > https://www.researchgate.net/post/Compare_different_types_of_errors_in_chidrens_performance_Statistical_Test > [accessed Jul 10, 2016]. > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. ______________________________________________ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
