Dear R List, I am trying to use mixed models to analyze an intervention and want to make sure I am doing it correctly. The intervention is for lowing cholesterol and there are two groups: one with an intervention and one without. The subjects were evaluated a differing amount of time, so there were between 2 and 7 visits, equally spaced. Sample output is below. TC is total cholesterol, group.minus.1 is the intervention indicator and Study.Number is the subject id. If I'm reading this correctly, the t-value on group.minus.1 is 0.63 and so the intervention did not have a significant effect. Is that the correct way of interpreting this? Troy Linear mixed model fit by REML Formula: TC ~ group.minus.1 + Visit + (Visit | Study.Number) + (1 | Study.Number) Data: rawdf AIC BIC logLik deviance REMLdev 4676 4710 -2330 4670 4660 Random effects: Groups Name Variance Std.Dev. Corr Study.Number (Intercept) 857.440 29.2821 Visit 21.471 4.6337 -0.755 Study.Number (Intercept) 508.757 22.5556 Residual 333.710 18.2677 Number of obs: 494, groups: Study.Number, 140 Fixed effects: Estimate Std. Error t value (Intercept) 162.3291 4.4392 36.57 group.minus.1 3.4466 5.4699 0.63 Visit -1.4515 0.5997 -2.42 Correlation of Fixed Effects: (Intr) grp..1 group.mns.1 -0.593 Visit -0.493 -0.043 [[alternative HTML version deleted]]
Daniel Malter
2011-Aug-18 18:49 UTC
[R] Using mixed models to analyze Longitudinal intervention
It looks like it. However, you provide very little information. Do you have measurements before and after the intervention and did the intervention occur at the same point in time for all treated? If so, you could do a simple difference in differences estimation. HTH, Daniel Troy S wrote:> > Dear R List, > > I am trying to use mixed models to analyze an intervention and want to > make > sure I am doing it correctly. The intervention is for lowing cholesterol > and there are two groups: one with an intervention and one without. The > subjects were evaluated a differing amount of time, so there were between > 2 > and 7 visits, equally spaced. > > Sample output is below. TC is total cholesterol, group.minus.1 is the > intervention indicator and Study.Number is the subject id. If I'm reading > this correctly, the t-value on group.minus.1 is 0.63 and so the > intervention > did not have a significant effect. Is that the correct way of > interpreting > this? > > Troy > > Linear mixed model fit by REML > > Formula: TC ~ group.minus.1 + Visit + (Visit | Study.Number) + (1 | > Study.Number) > > Data: rawdf > > AIC BIC logLik deviance REMLdev > > 4676 4710 -2330 4670 4660 > > Random effects: > > Groups Name Variance Std.Dev. Corr > > Study.Number (Intercept) 857.440 29.2821 > > Visit 21.471 4.6337 -0.755 > > Study.Number (Intercept) 508.757 22.5556 > > Residual 333.710 18.2677 > > Number of obs: 494, groups: Study.Number, 140 > > Fixed effects: > > Estimate Std. Error t value > > (Intercept) 162.3291 4.4392 36.57 > > group.minus.1 3.4466 5.4699 0.63 > > Visit -1.4515 0.5997 -2.42 > > Correlation of Fixed Effects: > > (Intr) grp..1 > > group.mns.1 -0.593 > > Visit -0.493 -0.043 > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help at 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. >-- View this message in context: http://r.789695.n4.nabble.com/Using-mixed-models-to-analyze-Longitudinal-intervention-tp3753199p3753333.html Sent from the R help mailing list archive at Nabble.com.