Re: [R] Wilcoxon Test and Mean Ratios

2012-09-21 Thread Henric (Nilsson) Winell
On 2012-09-20 21:07, Thomas Lumley wrote: On Fri, Sep 21, 2012 at 6:43 AM, avinash barnwal wrote: Hi, http://en.wikipedia.org/wiki/Wilcoxon_signed-rank_test We can clearly see that null hypothesis is median different or not. One way of proving non difference is P(X>Y) = P(X Avinash. No. F

Re: [R] Wilcoxon Test and Mean Ratios

2012-09-20 Thread Thomas Lumley
On Fri, Sep 21, 2012 at 6:43 AM, avinash barnwal wrote: > Hi, > > http://en.wikipedia.org/wiki/Wilcoxon_signed-rank_test > > We can clearly see that null hypothesis is median different or not. > One way of proving non difference is P(X>Y) = P(X ordered. Avinash. No. Firstly, the Wikipedia link

Re: [R] Wilcoxon Test and Mean Ratios

2012-09-20 Thread avinash barnwal
Hi, http://en.wikipedia.org/wiki/Wilcoxon_signed-rank_test We can clearly see that null hypothesis is median different or not. One way of proving non difference is P(X>Y) = P(X wrote: > > On Sep 20, 2012, at 02:43 , Thomas Lumley wrote: > >> On Thu, Sep 20, 2012 at 5:46 AM, Mohamed Radhouane Anib

Re: [R] Wilcoxon Test and Mean Ratios

2012-09-20 Thread peter dalgaard
On Sep 20, 2012, at 02:43 , Thomas Lumley wrote: > On Thu, Sep 20, 2012 at 5:46 AM, Mohamed Radhouane Aniba > wrote: >> Hello All, >> >> I am writing to ask your opinion on how to interpret this case. I have two >> vectors "a" and "b" that I am trying to compare. >> >> The wilcoxon test is gi

Re: [R] Wilcoxon Test and Mean Ratios

2012-09-20 Thread avinash barnwal
Hi, In Wilcoxon test , we look for medians rather than the means. Ratio of medians should be more coherent with P value. On Thu, Sep 20, 2012 at 6:30 PM, Ben Bolker wrote: > Mohamed Radhouane Aniba gmail.com> writes: > > > > > > > Thank you Thomas, > > > > So you think a t-test is more adequat

Re: [R] Wilcoxon Test and Mean Ratios

2012-09-20 Thread Ben Bolker
Mohamed Radhouane Aniba gmail.com> writes: > > > Thank you Thomas, > > So you think a t-test is more adequate to use in this case ? > > Rad No, because a t-test makes even stronger parametric assumptions. You were given more specific advice on stackoverflow http://stackoverflow.com/questi

Re: [R] Wilcoxon Test and Mean Ratios

2012-09-19 Thread Mohamed Radhouane Aniba
Thank you Thomas, So you think a t-test is more adequate to use in this case ? Rad On Sep 19, 2012, at 8:43 PM, Thomas Lumley wrote: > On Thu, Sep 20, 2012 at 5:46 AM, Mohamed Radhouane Aniba > wrote: >> Hello All, >> >> I am writing to ask your opinion on how to interpret this case. I hav

Re: [R] Wilcoxon Test and Mean Ratios

2012-09-19 Thread Thomas Lumley
On Thu, Sep 20, 2012 at 5:46 AM, Mohamed Radhouane Aniba wrote: > Hello All, > > I am writing to ask your opinion on how to interpret this case. I have two > vectors "a" and "b" that I am trying to compare. > > The wilcoxon test is giving me a pvalue of 5.139217e-303 of a over b with the > alter

[R] Wilcoxon Test and Mean Ratios

2012-09-19 Thread Mohamed Radhouane Aniba
Hello All, I am writing to ask your opinion on how to interpret this case. I have two vectors "a" and "b" that I am trying to compare. The wilcoxon test is giving me a pvalue of 5.139217e-303 of a over b with the alternative "greater". Now if I make a summary on each of them I have the followi