Re: [R] linear regression and t-distribution

2011-02-22 Thread Peter Ehlers
On 2011-02-21 02:42, Rosario Garcia Gil wrote: Hello I have a data set with outlier and it is not normally distributed. I would instead like to use a more robust distribution like t-distribution. My question is if the coefficients of the regression are different from zero, but assuming a t-di

Re: [R] linear regression and t-distribution

2011-02-22 Thread Kjetil Halvorsen
did you try RSiteSearch("t-regression") ? That seems to give some usefull hits. On Mon, Feb 21, 2011 at 7:42 AM, Rosario Garcia Gil wrote: > Hello > > I have a data set with outlier and it is not normally distributed. I would > instead like to use a more robust distribution like t-distribution

[R] linear regression and t-distribution

2011-02-21 Thread Rosario Garcia Gil
Hello I have a data set with outlier and it is not normally distributed. I would instead like to use a more robust distribution like t-distribution. My question is if the coefficients of the regression are different from zero, but assuming a t-distribution. Could someone hint me what package t