Statistics Help @ Talk Stats Forum - Biostatistics
http://www.talkstats.com/
Epidemiology and biostatistics, public health research. GLM, logistic regression, survival analysis, clinical trials.enMon, 03 Aug 2015 01:56:28 GMTvBulletin60http://www.talkstats.com/images/misc/rss.pngStatistics Help @ Talk Stats Forum - Biostatistics
http://www.talkstats.com/
ROC analysis using survival data
http://www.talkstats.com/showthread.php/61879-ROC-analysis-using-survival-data?goto=newpost
Fri, 31 Jul 2015 14:44:22 GMTDear readers,
I would like to create two groups of patients depending on value of numerical parameter (like age), i.e. younger and older than 60...Dear readers,
I would like to create two groups of patients depending on value of numerical parameter (like age), i.e. younger and older than 60 years... and check how they compare in survival analysis (log-rank test).
I did arbitrary division and I noticed significant difference in survival between two groups. But I was suggested to use ROC analysis to find optimal cut off point.

Can someone please suggest how to perform ROC analysis with one numerical variable A and survival data (follow up time and censoring status)? I tried several times but I can't figure it out. (as far as I understand, one would need tested variable A and second "classification" yes-no variable). Thank you in advance
]]>BiostatisticsMarkica85http://www.talkstats.com/showthread.php/61879-ROC-analysis-using-survival-dataHow to correctly combine two binary variables into one dependent variable?
http://www.talkstats.com/showthread.php/61878-How-to-correctly-combine-two-binary-variables-into-one-dependent-variable?goto=newpost
Fri, 31 Jul 2015 14:19:25 GMTI want to create a combined death or stroke rate binary variable.
For each row (patient data), I have data for death and stroke (yes/no)...I want to create a combined death or stroke rate binary variable.
For each row (patient data), I have data for death and stroke (yes/no) separately.

How should I create the two variables into one dependent variable to use in multivariate logistic models?
I worry that simply using the OR function (e.g. >alldata$DeathStroke <- ifelse(alldata$Death=="Yes"| alldata$Stroke=="Yes", c("Yes"), c("No")) will involve unwanted interaction.. Or, would that be okay?

I'm using R.

Thank you in advance for your help!
]]>Biostatisticshonghhttp://www.talkstats.com/showthread.php/61878-How-to-correctly-combine-two-binary-variables-into-one-dependent-variable