Very sorry that I ignore the question type.Yest,it's not an R question. Many thanks for your answer.
-- QQ: 1733768559 At 2015-02-05 18:26:01,"peter dalgaard" <pda...@gmail.com> wrote: > >On 05 Feb 2015, at 09:20 , meng <laomen...@163.com> wrote: > >> Hi all: >> If I want to test whether the mean of a set of normal distributed data is >> different from a value(e.g. 0), I can use one sample t test . But if the >> data is not normal distributed,what kind of method should be used? >> > >Not really an R question is it? > > (stats.stackexchange.com is -----> over there) > >Anyways, short answer: If you can assume symmetry under the null hypothesis, >there is a one-sample wilcox.test (signed rank test) and a couple of similar >tests. If the distribution is not symmetric, first decide if you really mean >the mean. If you actually mean median, there's the sign test. If you really do >mean the mean, I'd look at the t test supplemented with bootstrap simulations >to see whether departure from normality matters much. > >> Many thanks! >> >> >> My best. >> >> >> >> >> >> >> >> >> [[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. > >-- >Peter Dalgaard, Professor, >Center for Statistics, Copenhagen Business School >Solbjerg Plads 3, 2000 Frederiksberg, Denmark >Phone: (+45)38153501 >Email: pd....@cbs.dk Priv: pda...@gmail.com > > > > > > > > [[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.