| To: | s-news@lists.biostat.wustl.edu |
|---|---|
| Subject: | validation of cox coeff estimation by patients scores |
| From: | carol white <wht_crl@yahoo.com> |
| Date: | Wed, 14 Mar 2007 14:03:32 -0700 (PDT) |
| Domainkey-signature: | a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=NiNxzYFb8FgAZbeSefx3c5+I2XNlfie2IRkr/qZiqpNgBk78DTNpR0Di3Qw9pXBGdGZeIFPnkh/ogGenVW+VO3HuaQbALZmLYtgUxCySkGROHg2s+xOZLzHPg+8U8E2xLq6+ubMttIqBT5NKzppWDqAsOJ7zQ3orslTeN7JeT8E=; |
|
Hi all, if the patient risk score is defined as the sum of the product of gene _expression_ and coefficients of cox estimation, then negative score means low risk score and positive score a high score, respectively. then if the low score kaplan meier plot is shorter than high score plot, could it be assumed that the cox coeff were not estimated correctly and patients were mis-stratified? the same question if decreasing steps (for died patients) are observed in low risk plot and/or the high risk plot remains flat or stable instead of decreasing. Look forward to your feedback
It's here! Your new message! Get new email alerts with the free Yahoo! Toolbar. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: group by, Wensui Liu |
|---|---|
| Next by Date: | Re: SVMs in S-Plus, Kim Elmore |
| Previous by Thread: | group by, Neung-Hwan Oh |
| Next by Thread: | xyplot with square boxes, David Parkhurst |
| Indexes: | [Date] [Thread] [Top] [All Lists] |