PQL estimation of Random Effects Logistic Regression Model for Odds of Amenorrhea
Clinical Trial of Contracepting Women

The GLIMMIX Procedure

Model Information
Data Set WORK.AMEN
Response Variable y
Response Distribution Binomial
Link Function Logit
Variance Function Default
Variance Matrix Blocked By id
Estimation Technique Residual PL
Degrees of Freedom Method Containment

Number of Observations Read 4604
Number of Observations Used 3616

Dimensions
G-side Cov. Parameters 1
Columns in X 5
Columns in Z per Subject 1
Subjects (Blocks in V) 1151
Max Obs per Subject 4

Optimization Information
Optimization Technique Dual Quasi-Newton
Parameters in Optimization 1
Lower Boundaries 1
Upper Boundaries 0
Fixed Effects Profiled
Starting From Data

Iteration History
Iteration Restarts Subiterations Objective
Function
Change Max
Gradient
0 0 4 16069.3811 2.00000000 0.000577
1 0 3 16415.929901 0.10700008 0.000898
2 0 3 16537.73115 0.02933027 0.000068
3 0 2 16568.062012 0.00676895 0.000063
4 0 2 16574.766399 0.00146607 8.915E-8
5 0 2 16576.199665 0.00031214 1.362E-8
6 0 1 16576.503889 0.00006621 2.017E-6
7 0 1 16576.568375 0.00001401 1.236E-7
8 0 1 16576.582022 0.00000297 7.582E-8
9 0 1 16576.584911 0.00000064 1.954E-6
10 0 1 16576.585539 0.00000085 0.000093
11 0 1 16576.586363 0.00000055 9.493E-7
12 0 1 16576.585824 0.00000077 0.000085
13 0 1 16576.585079 0.00000050 8.216E-7
14 0 1 16576.585565 0.00000069 0.000077
15 0 1 16576.586242 0.00000044 5.808E-7
16 0 1 16576.58581 0.00000069 0.000076
17 0 1 16576.585142 0.00000044 6.43E-7
18 0 1 16576.585568 0.00000068 0.000075
19 0 1 16576.586231 0.00000044 3.982E-7
20 0 1 16576.5858 0.00000063 0.00007
21 0 1 16576.585185 0.00000041 8.076E-8
22 0 1 16576.585581 0.00000061 0.000067
23 0 1 16576.586171 0.00000038 1.586E-6
24 0 1 16576.585803 0.00000064 0.000071
25 0 1 16576.585175 0.00000042 2.117E-7
26 0 1 16576.585581 0.00000060 0.000067
27 0 1 16576.58617 0.00000040 1.003E-6
28 0 0 16576.585783 0.00000000 9.857E-6

Convergence criterion (PCONV=1.11022E-8) satisfied.

Fit Statistics
-2 Res Log Pseudo-Likelihood 16576.59
Generalized Chi-Square 2457.54
Gener. Chi-Square / DF 0.68

Estimated G Matrix
Effect Row Col1
Intercept 1 1.8488

Covariance Parameter Estimates
Cov Parm Subject Estimate Standard Error
Intercept id 1.8488 0.1693

Solutions for Fixed Effects
Effect Estimate Standard Error DF t Value Pr > |t|
Intercept -2.5859 0.2298 1150 -11.25 <.0001
time 0.7735 0.2178 2461 3.55 0.0004
time2 -0.02666 0.04494 2461 -0.59 0.5530
time*trt 0.3666 0.1416 2461 2.59 0.0097
time2*trt -0.07247 0.03851 2461 -1.88 0.0600

Type III Tests of Fixed Effects
Effect Num DF Den DF F Value Pr > F
time 1 2461 12.61 0.0004
time2 1 2461 0.35 0.5530
time*trt 1 2461 6.70 0.0097
time2*trt 1 2461 3.54 0.0600

Contrasts
Label Num DF Den DF Chi-Square F Value Pr > ChiSq Pr > F
2 df Test of Trt X Time Interaction 2 2461 10.89 5.45 0.0043 0.0044