Re: [R] the problem about sample size
Hi I am not at all an expert in this matter, so you shall copy you message to r-help list too. However I would try na.action=na.exclude as it shall preserve the length of variables. Regards Petr Hi, Sorry I didn't know the original post in this thread was not included. I'm using R version 2.14.0 (2011-10-31). This is the program: fitLME4 - lme(iadl ~ obstime, random = ~ obstime | id, data = iadl.long.df, na.action=na.omit) fitSURV - coxph(Surv(Time, death) ~ agew1, data = last_aa.df, x = TRUE) fit.JM4 - jointModel(fitLME1, fitSURV, timeVar = obstime, method = piecewise-PH-GH) This is the error message: Error in jointModel(fitLME1, fitSURV, timeVar = obstime, method = piecewise-PH-GH) : sample sizes in the longitudinal and event processes differ; maybe you forgot the cluster() argument. I have missing data in the lme data and that's why I used na.omit. But results of the lme and coxph show the same number of participants. From lme: Number of Observations: 4818 Number of Groups: 2087 From coxph: n= 2087, number of events= 1721 If the number of groups in lme = n in coxph, why am I getting the error message that sample sizes differ? Many thanks for your help. Helena From: Petr PIKAL [petr.pi...@precheza.cz] Sent: Thursday, March 01, 2012 6:17 PM To: Helena Chui Cc: r-help@r-project.org; r-help-boun...@r-project.org Subject: Re: [R] the problem about sample size Hi Hi, there, I run into the same sample size error in JM. Have you found the solution for the error? What error? Petr Many thanks, Helena -- View this message in context: http://r.789695.n4.nabble.com/the-problem- about-sample-size-tp1592855p4434009.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list 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. __ R-help@r-project.org mailing list 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.
Re: [R] the problem about sample size
Hi, Sorry I didn't know the original post in this thread was not included. I'm using R version 2.14.0 (2011-10-31). This is the program: fitLME4 - lme(iadl ~ obstime, random = ~ obstime | id, data = iadl.long.df, na.action=na.omit) fitSURV - coxph(Surv(Time, death) ~ agew1, data = last_aa.df, x = TRUE) fit.JM4 - jointModel(fitLME1, fitSURV, timeVar = obstime, method = piecewise-PH-GH) This is the error message: Error in jointModel(fitLME1, fitSURV, timeVar = obstime, method = piecewise-PH-GH) : sample sizes in the longitudinal and event processes differ; maybe you forgot the cluster() argument. I have missing data in the lme data and that's why I used na.omit. But results of the lme and coxph show the same number of participants. From lme: Number of Observations: 4818 Number of Groups: 2087 From coxph: n= 2087, number of events= 1721 If the number of groups in lme = n in coxph, why am I getting the error message that sample sizes differ? Many thanks for your help. Helena From: Petr PIKAL [petr.pi...@precheza.cz] Sent: Thursday, March 01, 2012 6:17 PM To: Helena Chui Cc: r-help@r-project.org; r-help-boun...@r-project.org Subject: Re: [R] the problem about sample size Hi Hi, there, I run into the same sample size error in JM. Have you found the solution for the error? What error? Petr Many thanks, Helena -- View this message in context: http://r.789695.n4.nabble.com/the-problem- about-sample-size-tp1592855p4434009.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list 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. __ R-help@r-project.org mailing list 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.
Re: [R] the problem about sample size
Hi, there, I run into the same sample size error in JM. Have you found the solution for the error? Many thanks, Helena -- View this message in context: http://r.789695.n4.nabble.com/the-problem-about-sample-size-tp1592855p4434009.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list 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.
Re: [R] the problem about sample size
Hi Hi, there, I run into the same sample size error in JM. Have you found the solution for the error? What error? Petr Many thanks, Helena -- View this message in context: http://r.789695.n4.nabble.com/the-problem- about-sample-size-tp1592855p4434009.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list 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. __ R-help@r-project.org mailing list 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.
[R] the problem about sample size
Hi all: I am a user of JM package. Here's the problem of sample size. The warning is: Error in jointModel(fitLME, fitSURV_death, timeVar = time, method = piecewise-PH-GH) : sample sizes in the longitudinal and event processes differ. According to the suggestion of missing data,I use the same data set(data_JM) without any missing value. fitLME - lme(CD4 ~ time + time:Group_DR, random = ~time | id,data = data_JM); fitSURV_death - coxph(Surv(time_fail, death) ~ (Group_DR), data = data_JM, x = TRUE); summary(fitLME); Linear mixed-effects model fit by REML Data: data_JM AIC BIClogLik 9102.502 9134.538 -4544.251 ... ... Number of Observations: 721 summary(fitSURV_death) Call: coxph(formula = Surv(time_fail_min, death) ~ (Group_DR), data = data_JM, x = TRUE) n= 721 coef exp(coef) se(coef) z Pr(|z|) Group_DR -0.16854 0.84490 0.04213 -4 6.33e-05 *** --- Signif. codes: 0 ¡®***¡¯ 0.001 ¡®**¡¯ 0.01 ¡®*¡¯ 0.05 ¡®.¡¯ 0.1 ¡® ¡¯ 1 The sample size of lme and coxph is the same as marked blue above,and I'm sure that data_JM contains no missing value. So, what's reason about the warning Error in jointModel(fitLME, fitSURV_death, timeVar = time, method = piecewise-PH-GH) : sample sizes in the longitudinal and event processes differ. Thanks a lot . My best. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list 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.