Bioequivalence and Bioavailability Forum • lme() does not work with all fixed effects

lme() does not work with all fixed effects [🇷 for BE/BA]

posted by yjlee168 – Kaohsiung, Taiwan, 2015-04-22 01:41 (3656 d 14:33 ago) – Posting: # 14730
Views: 25,176

Dear Helmut,

❝ ... The Q&A specifically mentions SAS’ Proc GLM, not Proc Mixed.

glm() works in R.

❝ In lme() it should be possible to specify all effects fixed. Actually the random effect(s) are optional. If is doesn’t work, lm() should do.

lme() does not work without random effect. Am I doing anything wrong?

> require(nlme)

Loading required package: nlme

> cnames<-c("subj","drug","seq", "prd","Cmax", "AUC0t", "AUC0INF","lnCmax","lnAUC0t","lnAUC0INF")

> TotalData<-read.csv(file="SingleRep_stat_demo.csv",header=TRUE,row.names=NULL,col.names=cnames, sep=",",dec=".")

> mod.lme<-lme(log(Cmax) ~ subj + seq +  prd + drug, data=TotalData, method="REML")

Error in getGroups.data.frame(dataMix, groups) : 

  invalid formula for groups

If I compared lme(), lm(), and glm(), I got

> mod.lme<-lme(log(Cmax) ~ seq +  prd + drug, random=~drug -1|subj, data=TotalData, method="REML")  ###lme in bear

> mod.lm<-lm(log(Cmax) ~ subj + seq +  prd + drug, data=TotalData)    ## lm()

> mod.glm<-glm(log(Cmax) ~ subj + seq +  prd + drug, data=TotalData)  ## glm()

> AIC(mod.lme, mod.lm)

        df       AIC

mod.lme  6 -49.88309

mod.lm   6 -70.88094

Warning message:

In AIC.default(mod.lme, mod.lm) :

  models are not all fitted to the same number of observations

> AIC(mod.lme, mod.glm)

        df       AIC

mod.lme  6 -49.88309

mod.lm   6 -70.88094

Warning message:

In AIC.default(mod.lme, mod.lm) :

  models are not all fitted to the same number of observations

Summary of mod.lme

Linear mixed-effects model fit by REML

 Data: TotalData 

        AIC       BIC   logLik

  -49.88309 -38.17563 30.94155



Random effects:

 Formula: ~drug - 1 | subj

              drug  Residual

StdDev: 0.04344759 0.1041244



Fixed effects: log(Cmax) ~ seq + prd + drug 

                Value  Std.Error DF  t-value p-value

(Intercept)  7.314670 0.08349877 40 87.60213  0.0000

seq         -0.025701 0.04252039 12 -0.60445  0.5568

prd          0.016233 0.01244525 40  1.30438  0.1996

drug         0.046554 0.03015388 40  1.54387  0.1305

 Correlation: 

     (Intr) seq    prd   

seq  -0.764              

prd  -0.373  0.000       

drug -0.461  0.000  0.000



Standardized Within-Group Residuals:

       Min         Q1        Med         Q3        Max 

-2.8081617 -0.6114645  0.1380420  0.5476292  1.8620918 



Number of Observations: 56

Number of Groups: 14

Summary of mod.lm

Call:

lm(formula = log(Cmax) ~ subj + seq + prd + drug, data = TotalData)



Residuals:

     Min       1Q   Median       3Q      Max 

-0.29483 -0.07058  0.01211  0.07004  0.23080 



Coefficients:

             Estimate Std. Error t value Pr(>|t|)    

(Intercept)  7.353905   0.087149  84.383   <2e-16 ***

subj        -0.007061   0.004041  -1.747   0.0866 .  

seq         -0.016555   0.032583  -0.508   0.6136    

prd          0.016233   0.014459   1.123   0.2668    

drug         0.046554   0.032332   1.440   0.1560    

---

Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1



Residual standard error: 0.121 on 51 degrees of freedom

Multiple R-squared:  0.1126,    Adjusted R-squared:  0.04302 

F-statistic: 1.618 on 4 and 51 DF,  p-value: 0.184

Summary of glm

Call:

glm(formula = log(Cmax) ~ subj + seq + prd + drug, data = TotalData)



Deviance Residuals: 

     Min        1Q    Median        3Q       Max  

-0.29483  -0.07058   0.01211   0.07004   0.23080  



Coefficients:

             Estimate Std. Error t value Pr(>|t|)    

(Intercept)  7.353905   0.087149  84.383   <2e-16 ***

subj        -0.007061   0.004041  -1.747   0.0866 .  

seq         -0.016555   0.032583  -0.508   0.6136    

prd          0.016233   0.014459   1.123   0.2668    

drug         0.046554   0.032332   1.440   0.1560    

---

Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1



(Dispersion parameter for gaussian family taken to be 0.01463458)



    Null deviance: 0.84108  on 55  degrees of freedom

Residual deviance: 0.74636  on 51  degrees of freedom

AIC: -70.881



Number of Fisher Scoring iterations: 2



> AIC(mod.lm, mod.glm)

        df       AIC

mod.lm   6 -70.88094

mod.glm  6 -70.88094

—
All the best,
-- Yung-jin Lee
bear v2.9.2:- created by Hsin-ya Lee & Yung-jin Lee
Kaohsiung, Taiwan https://www.pkpd168.com/bear
Download link (updated) -> here

Complete thread:

Bear vs. Phoenix & SAS Helmut 2015-04-20 17:34
- R vs. Phoenix & SAS? yjlee168 2015-04-20 19:36
  - R vs. Phoenix & SAS? Helmut 2015-04-21 01:02
    - lme() does not work with all fixed effectsyjlee168 2015-04-21 23:41
      - lme() does not work with all fixed effects Astea 2016-11-04 00:13
        
        lmer: Method B (PE catched for imbalanced dataset!!!) and Method C mittyri 2016-11-05 17:38
        
        lmer: Method B (PE catched for imbalanced dataset!!!) and Method C Astea 2016-11-05 19:27
        
        lmer: Method B is ready for scaling mittyri 2016-11-05 20:01
        
        lmer: Method B is ready for scaling Astea 2016-11-06 11:50
        
        lmer: Method B is ready for scaling mittyri 2016-11-07 06:07
- info for lsmeans yjlee168 2015-04-20 21:34
  - info for lsmeans Helmut 2015-04-21 01:15
    - once more about R and replicate designes Astea 2016-11-02 23:43
      - once more about R and replicate designes VStus 2016-11-06 11:34
        
        Getting variance components from the lmer output StatR 2017-02-03 13:53
        
        Getting variance components from the lmer output VStus 2017-02-03 15:47
        
        Getting variance components from the lmer output StatR 2017-02-03 17:12
        
        Getting variance components d_labes 2017-02-07 11:16
        
        Getting variance components StatR 2017-02-07 11:36
        Getting variance components StatR 2017-02-08 08:41
        
        Getting variance components d_labes 2017-02-08 10:13
        
        Getting variance components StatR 2017-02-08 10:19
        
        Data structure Helmut 2017-02-08 10:33
        
        Data structure StatR 2017-02-08 10:49