Bioequivalence and Bioavailability Forum

AIC, BIC and that all ... [General Sta­tis­tics]

posted by d_labes  – Berlin, Germany, 2010-07-15 14:01 (5815 d 13:06 ago) – Posting: # 5635
Views: 16,922

Dear Helmut,

❝ let's continue!

           -2 REML log(LikH)   AIC       BIC
SAS (FDA)      272.910       282.9     291.8
PHX/WNL        251.724       273.724   304.923
lme()          271.654       291.654   320.096

❝ ❝ Seems WNL computes different.

Seems SAS computes different.
According to the SAS help on Proc MIXED:

AIC = -2*LL + 2*d
BIC = -2*LL + d*log(n)

Here LL denotes the maximum value of the (possibly restricted) log likelihood, d the dimension of the model, and n the number of observations. In SAS 6 of SAS/STAT software, n equals the number of valid observations for maximum likelihood estimation and n-p for restricted maximum likelihood estimation, where p equals the rank of X. In later versions, n equals the number of effective subjects as displayed in the "Dimensions" table, unless this value equals 1, in which case n equals the number of levels of the first random effect you specify in a RANDOM statement. If the number of effective subjects equals 1 and you have no RANDOM statements, n then reverts to the SAS 6 values. For restricted likelihood estimation, d equals q, the effective number of estimated covariance parameters. In SAS 6, when a parameter estimate lies on a boundary constraint, then it is still included in the calculation of d, but in later versions it is not. The most common example of this behavior is when a variance component is estimated to equal zero. For maximum likelihood estimation, d equals q+p.

A very concise and clear description of the calculations in SAS 9.2 . That recognize who will or can.

Of course the R's lme() values are different from SAS's. The R folks undertake each effort to do things not the <$ineffable$> way .

Complete thread:

• SABE Reference Variability and CI Computation preyes323 2010-07-12 17:12 [General Sta­tis­tics] 
  • Dataset Helmut 2010-07-12 17:26
    • Dataset preyes323 2010-07-12 18:20
      • Data format Helmut 2010-07-12 18:38
        • Data format preyes323 2010-07-13 01:16
          • SAS and/or Phoenix/WinNonlin-experts around? Helmut 2010-07-13 02:29
            • Phoenix/WinNonlin-experts around? d_labes 2010-07-13 12:15
              • Phoenix/WinNonlin-experts around? Helmut 2010-07-13 13:42
                • Mixed interest d_labes 2010-07-13 15:11
                  • Mixed interest Helmut 2010-07-13 19:19
                    • lme() answer and beyond ... d_labes 2010-07-14 10:41
                      • lme() answer and beyond ... Helmut 2010-07-14 13:47
                        • AIC, BIC and that all ...d_labes 2010-07-15 12:01
          • To Err is Human d_labes 2010-07-13 11:51
            • To Err is Human, but... Helmut 2010-07-13 13:45
              • ... to Arr is Pirate d_labes 2010-07-13 15:47
                • Brilliant page!!! ElMaestro 2010-07-14 21:03
            • To Err is Human preyes323 2010-07-14 14:45
              • Heads up! Helmut 2010-07-14 15:17
              • To Err is Teacher d_labes 2010-07-15 11:05
            • To Err is Human preyes323 2010-07-16 02:28
              • To Err is Human d_labes 2010-07-16 10:42
                • To Err is Human preyes323 2010-07-17 11:14
                  • Regulatory constants d_labes 2010-07-19 10:00
          • Data format ElMaestro 2011-02-06 11:54
            • SAS System Viewer Helmut 2011-02-06 13:02