Bioequivalence and Bioavailability Forum • Variance components

Variance components – Proc mixed [Software]

posted by d_labes – Berlin, Germany, 2014-02-03 12:58 (4096 d 09:25 ago) – Posting: # 12320
Views: 28,071
(edited on 2014-02-03 13:11)

Dear ElMaestro,

❝ If or when you test with PROC MIXED, can you paste the entire co-variance matrix (not the Z or the G)? It will be the one with 14 columns if you use the dataset above; I'd expect a common sigma sq. on the diagonal and a single beween-sigma sq. elsewhere in each row.

As requested: the V matrices using the following code

Proc Mixed data=BEBAC12305;

  class subject period formulation sequence;

  model &lnMetric = formulation period sequence;

  random subject(sequence);

run;

ln(AUCt)

diagonal matrix (28 rows/cols) with 0.02720 on the diagonal



ln(Cmax)

Block diagonal matrix (28 rows/cols) with blocks

 0.02072   0.002918

 0.002918  0.02072

on the diagonal

Covariance Parameter Estimates:

ln(AUCt)

   V(subject(sequence))= 0 ! 

   V(residual)         = 0.02720   -> CV_intra= 16.6%



ln(Cmax)

   V(subject(sequence))= 0.002918  -> CV_inter=  5.4%

   V(residual)         = 0.01780   -> CV_intra= 13.4%

Variance parameters are by default in SAS restricted to ≥0 in the maximization of the likelihood.
Reasonable to me :-D

.
I get negative variance for subject(sequence) in case of ln(AUCt) only if I use the non-standard NOBOUND option in the Proc MIXED call:

ln(AUCt)

   V(subject(sequence))= -0.00609

   V(residual)         =  0.03329  -> CV_intra= 18.4%

Seems the same as PHX build 6.3.0.395 / 6.4.0.511 results. See Helmut's post above.

Edit:
Interesting! Here the 90% CI's for AUCt (PE=96.14%):


Proc GLM             85.02% ... 108.71%

Proc Mixed           86.03% ... 107.44%

Proc Mixed (nobound) 85.02% ... 108.71%

Our (at least my own :lookaround:

) belief "Proc GLM and Proc MIXED give the same results for a complete, balanced data set" has to be modified!

—
Regards,

Detlew

Complete thread:

How to calculate intersubject variability in PHX WinNonlin zan 2014-01-29 23:58 [Software]
- Negative variance component Helmut 2014-01-30 01:16
  - Negative variance component zan 2014-01-30 18:11
  - Negative variance component zan 2014-01-31 00:16
    - Negative variance component ElMaestro 2014-01-31 08:20
    - Negative variance component yjlee168 2014-01-31 10:26
      - Example data set Helmut 2014-02-01 16:03
        
        Example data set yjlee168 2014-02-01 17:40
        
        PHX build 6.3.0.395 / 6.4.0.511 Helmut 2014-02-02 02:04
        
        PHX build 6.3.0.395 / 6.4.0.511 yjlee168 2014-02-02 07:54
    - Negative variance component ElMaestro 2014-02-01 16:31
      - Negative variance component yjlee168 2014-02-01 17:47
        
        Just thinking loud ElMaestro 2014-02-01 19:02
        
        All models are wrong… Helmut 2014-02-02 02:31
        
        another book for linear model yjlee168 2014-02-02 08:07
      - References Helmut 2014-02-02 02:19
        
        References ElMaestro 2014-02-02 09:56
    - Negative variance component – Chow/Liu d_labes 2014-02-03 09:02
      - Negative variance component – Chow/Liu ElMaestro 2014-02-03 10:22
        
        Variance components – Proc mixedd_labes 2014-02-03 11:58
        
        Variance components – Proc mixed ElMaestro 2014-02-03 12:58
        
        Variance components – Proc mixed 90% CIs d_labes 2014-02-03 13:16
        Variance components – Proc mixed Helmut 2014-02-03 14:14
        
        FDA code for non-replicate crossover? d_labes 2014-02-03 15:54
        
        Proc GLM rulez Helmut 2014-02-03 16:16
        
        Variance components – Proc mixed yjlee168 2014-02-03 20:43
        
        NOBOUND Helmut 2014-02-03 22:08
      - lm() or lme() for 2x2x2 study design? yjlee168 2014-02-03 20:22
        
        lm() or lme() for 2x2x2 study design? ElMaestro 2014-02-03 22:11
        
        lm() or lme() for 2x2x2 study design? yjlee168 2014-02-04 13:09
        
        bear for 2x2x2 study with negative variance components yjlee168 2014-02-05 19:12