Good evening, I have a few data objects that are the result of an analysis producing regression models associated with methylation for TCGA GBM and LGG subjects. I am trying to figure out how I can use R to find out which probes among these data objects correlate with patient survival? With this information, I hope to establish if the gene MGMT is one of the genes whose methylation show an association with survival. Is there a general procedure that I might look to as a guide for this? I believe the result of such a query into probeset data would result in a heatmap visualizing the association with survival. Best, Spencer [[alternative HTML version deleted]]
Spencer: Sorry, but I'll be blunt. IMO, you are misusing this list (see the posting guide). You clearly don't know what you're doing statistically and need to consult with your advisors. This list cannot and is not meant to serve that purpose -- it is for for R programming issues. If your advisors can't or won't help you, you might try stats.stackexchange.com, which does deal with statistical issues. But I could not guarantee that they would act as a statistical consulting service for you, which seems to be what you seek. Cheers, Bert Gunter "The trouble with having an open mind is that people keep coming along and sticking things into it." -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip ) On Fri, Aug 2, 2019 at 8:05 PM Spencer Brackett <spbrackett20 at saintjosephhs.com> wrote:> > Good evening, > > I have a few data objects that are the result of an analysis producing > regression models associated with methylation for TCGA GBM and LGG > subjects. I am trying to figure out how I can use R to find out which > probes among these data objects correlate with patient survival? With this > information, I hope to establish if the gene MGMT is one of the genes whose > methylation show an association with survival. Is there a general procedure > that I might look to as a guide for this? I believe the result of such a > query into probeset data would result in a heatmap visualizing the > association with survival. > > Best, > > Spencer > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help at 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.
Rolf Turner
2019-Aug-03 05:34 UTC
[R] [FORGED] Re: Determining survival correlation among probes
On 3/08/19 3:51 PM, Bert Gunter wrote:> Spencer: > > Sorry, but I'll be blunt. IMO, you are misusing this list (see the > posting guide). You clearly don't know what you're doing statistically > and need to consult with your advisors. This list cannot and is not > meant to serve that purpose -- it is for for R programming issues. If > your advisors can't or won't help you, you might try > stats.stackexchange.com, which does deal with statistical issues. But > I could not guarantee that they would act as a statistical consulting > service for you, which seems to be what you seek.I very firmly agree with Bert's post. It seems to me that Spencer's postings demonstrate fundamental misunderstanding both of R and of statistical science. He gives the impression that he *thinks* he understands a great deal more than he actually does, with the result that the questions he asks are generally ill-conceived and ill-posed. He appears to be attempting advanced statistical analysis without having mastered the elementary basics. Spencer should focus on remedying his misconceptions and filling in the lacunae in his knowledge. cheers, Rolf Turner -- Honorary Research Fellow Department of Statistics University of Auckland Phone: +64-9-373-7599 ext. 88276