Linear Trend Model for FEV1 data (REML)

Vlagtwedde-Vlaardingen Study

 

The Mixed Procedure

 

Model Information

Data Set

WORK.SMOKE

Dependent Variable

fev1

Covariance Structure

Unstructured

Subject Effect

id

Estimation Method

REML

Residual Variance Method

None

Fixed Effects SE Method

Model-Based

Degrees of Freedom Method

Between-Within

 

Class Level Information

Class

Levels

Values

id

133

not printed

t

7

0 3 6 9 15 19 12

 

Dimensions

Covariance Parameters

28

Columns in X

4

Columns in Z

0

Subjects

133

Max Obs Per Subject

7

Observations Used

771

Observations Not Used

0

Total Observations

771

 

Iteration History

Iteration

Evaluations

-2 Res Log Like

Criterion

0

1

1318.53109594

 

1

3

392.63286551

0.16685136

2

2

358.02971731

0.08215662

3

1

302.79842296

0.03563484

4

1

277.67561877

0.01334807

5

1

268.34746404

0.00320948

6

1

266.22391711

0.00028269

7

1

266.05227350

0.00000287

8

1

266.05062185

0.00000000

 

Convergence criteria met.

 

Estimated R Matrix for id 12

Row

Col1

Col2

Col3

Col4

Col5

Col6

Col7

1

0.3551

0.2997

0.2856

0.2842

0.2851

0.2884

0.2714

2

0.2997

0.3397

0.2932

0.2763

0.2810

0.2939

0.2632

3

0.2856

0.2932

0.3212

0.2688

0.2822

0.2837

0.2590

4

0.2842

0.2763

0.2688

0.3239

0.2820

0.2877

0.2620

5

0.2851

0.2810

0.2822

0.2820

0.3130

0.3008

0.2630

6

0.2884

0.2939

0.2837

0.2877

0.3008

0.3328

0.2823

7

0.2714

0.2632

0.2590

0.2620

0.2630

0.2823

0.3005

 

 

Fit Statistics

-2 Res Log Likelihood

266.1

AIC (smaller is better)

322.1

AICC (smaller is better)

324.3

BIC (smaller is better)

403.0

 

 

Solution for Fixed Effects

Effect

Estimate

Standard Error

DF

t Value

Pr > |t|

Intercept

3.5073

0.1004

131

34.94

<.0001

smoker

-0.2617

0.1151

131

-2.27

0.0246

time

-0.03322

0.003066

131

-10.84

<.0001

smoker*time

-0.00500

0.003525

131

-1.42

0.1586