Bioequivalence and Bioavailability Forum • lsmeans for mixed model in R

lsmeans for mixed model in R [🇷 for BE/BA]

posted by yjlee168 – Kaohsiung, Taiwan, 2015-04-20 01:36 (4075 d 22:42 ago) – Posting: # 14709
Views: 32,730

Dear Helmut and Elmaestro,

I also tried some other methods. I used two R packages lsmeans and lmerTest to do analysis of mixed model first.
if I used lmerTest (also required package pbkrtest),

modlnCmax<-lmer(log(Cmax) ~ seq +  prd + drug + (1|subj), data=TotalData, REML=TRUE)

lsm_lnCmax<-lsmeans(modlnCmax,test.effs="drug") ### for lmerTest, or

lsm_lnCmax<-lsmeans(modlnCmax,"drug")           ### for lsmeans

I got the results as

Least Squares Means table:

        seq prd drug Estimate Standard Error   DF t-value Lower CI Upper CI p-value    

drug  1  NA  NA  1.0   7.3633         0.0273 19.4     270     7.31     7.42  <2e-16 ***

drug  2  NA  NA  2.0   7.4098         0.0273 19.4     272     7.35     7.47  <2e-16 ***

If I used lsmeans package, I got

 drug   lsmean         SE    df lower.CL upper.CL

 1    7.363255 0.02726719 19.38 7.306260 7.420250

 2    7.409809 0.02726719 19.38 7.352813 7.466804



Results are averaged over the levels of: seq, prd 

Confidence level used: 0.95

Original results from bear are

  summary  Test   Ref Ratio

1  LSMEAN 7.411 7.365 1.006

2    S.D. 0.106 0.120 0.020

3  C.V(%) 1.424 1.633 1.992

Both lsmeans and lmerTest only work with lmer(), not lme(). What do you think about these results? I'm :confused:

.

Ref. link: detlew's The SAS way in Rrrr land

❝ ...

❝ R T

❝ Method A (EMA, subjects fixed) 7.328141 7.391880

❝ Method B (EMA, subjects random) 7.328141 7.391880

❝ Method C (FDA = mixed efects) 7.328141 7.391880

❝ Marginal means (Gnumeric) 7.328141 7.391880

❝ So why do we get…

❝ bear 7.356274 7.420013

❝ … which are ~3.8% higher for both treatments? No, I’m not satisfied if only the PE agrees – I expect to get a nasty surprise once we start to deal with unbalanced data.

—
All the best,
-- Yung-jin Lee
bear v2.9.6:- created by Hsin-ya Lee & Yung-jin Lee
Kaohsiung, Taiwan https://www.pkpd168.com/bear
Download link (updated) -> here

Thread locked

Complete thread:

Reproducing Bear results in Phoenix mittyri 2015-04-14 08:35 [🇷 for BE/BA]
- Bug in bear? Helmut 2015-04-14 14:07
  - Bug in bear? mittyri 2015-04-14 20:43
    - Bug in bear? Helmut 2015-04-15 02:17
  - use the same dataset? yjlee168 2015-04-20 10:13
- Bugs in bear with replicated demo data set? yjlee168 2015-04-15 09:38
- Bugs fixed in bear? yjlee168 2015-04-17 01:21
  - Bugs fixed in bear? Helmut 2015-04-17 14:25
    - Bugs fixed in bear? yjlee168 2015-04-17 18:50
      - Bugs fixed in bear? ElMaestro 2015-04-17 23:14
        
        lme() in bear yjlee168 2015-04-18 11:12
        
        lme() in bear ElMaestro 2015-04-18 11:28
        
        lme() in bear yjlee168 2015-04-18 12:02
        
        lme() in bear ElMaestro 2015-04-18 13:42
        
        Mean means Helmut 2015-04-18 14:08
        
        Mean means ElMaestro 2015-04-18 16:01
        
        Mean means Helmut 2015-04-19 00:59
        
        Mean means ElMaestro 2015-04-19 09:14
        
        LL and AIC Helmut 2015-04-19 11:08
        
        Confused ElMaestro 2015-04-19 11:42
        
        lsmeans for mixed model in Ryjlee168 2015-04-19 23:36
        
        lsmeans() & lme() Helmut 2015-04-20 01:28
        
        lsmeans() & lme() yjlee168 2015-04-20 10:23
        lsmeans() & lme() ElMaestro 2015-04-20 10:35
        
        keep it simple! Helmut 2015-04-20 14:34
        
        keep it simple! ElMaestro 2015-04-20 15:39
        
        ML vs. REML Helmut 2015-04-20 16:35
        
        lme() with NA in R yjlee168 2015-04-19 23:44
      - Dataset Helmut 2015-04-18 13:30
        
        Dataset and lme() in bear yjlee168 2015-04-18 23:14