|
Post by Jian Yang on Jun 11, 2015 1:25:25 GMT
|
|
|
Post by tatiana on Jun 23, 2015 21:15:37 GMT
Dear Jian, Thank you very much for your tips and tool. I have two questions. 1. What do you think about a reference sample with 2,000 unrelated individuals? Is it too small? At least, from the simulated plot in the article it looks quite stable. 2. I am afraid that I do not understand the procedure behind cojo-slct. When the stepwise regression is running, is any correction for p-values? Since sometimes the stepwise regression could lead problems. Thank you. Tatiana.
|
|
|
Post by Zhihong Zhu on Jun 27, 2015 7:09:07 GMT
Hi Tatiana,
1. I think sample size of 2k is enough. Actually the reference sample is used to estimate the LD.
2. I'm sorry, I'm not sure the problems that stepwise selection would bring.
Cheers, Zhihong Zhu
|
|