Mixed Effects Model for Percent Body Fat with Random Intercept

Hybrid Model with Exponential Serial Correlation

MIT Growth and Development Study

 

The Mixed Procedure

 

Model Information

Data Set

WORK.FAT

Dependent Variable

pbf

Covariance Structures

Unstructured, Spatial Exponential

Subject Effects

id, id

Estimation Method

REML

Residual Variance Method

Profile

Fixed Effects SE Method

Model-Based

Degrees of Freedom Method

Containment

 

Class Level Information

Class

Levels

Values

id

162

not printed

 

Dimensions

Covariance Parameters

4

Columns in X

3

Columns in Z Per Subject

1

Subjects

162

Max Obs Per Subject

10

Observations Used

1049

Observations Not Used

0

Total Observations

1049

 

Iteration History

Iteration

Evaluations

-2 Res Log Like

Criterion

0

1

7073.41750695

 

1

3

6013.20961208

0.00391220

2

1

6003.54699439

0.00113583

3

2

6001.03956295

0.00045032

4

1

5999.99584548

0.00005112

5

1

5999.88044924

0.00000242

6

1

5999.87535265

0.00000001

 

Convergence criteria met.

 

Estimated G Matrix

Row

Effect

id

Col1

1

Intercept

1

28.7625

 

 

Covariance Parameter Estimates

Cov Parm

Subject

Estimate

Standard Error

Z Value

Pr Z

UN(1,1)

id

28.7625

4.6549

6.18

<.0001

Variance

id

17.0015

2.3368

7.28

<.0001

SP(EXP)

id

2.3640

0.5897

4.01

<.0001

Residual

 

2.5999

0.8391

3.10

0.0010

 

Fit Statistics

-2 Res Log Likelihood

5999.9

AIC (smaller is better)

6007.9

AICC (smaller is better)

6007.9

BIC (smaller is better)

6020.2

 

 

Solution for Fixed Effects

Effect

Estimate

Standard Error

DF

t Value

Pr > |t|

Intercept

21.2577

0.5406

161

39.32

<.0001

time

0.2286

0.1440

885

1.59

0.1129

time_0

2.1646

0.2282

885

9.49

<.0001

 

Type 3 Tests of Fixed Effects

Effect

Num DF

Den DF

Chi-Square

F Value

Pr > ChiSq

Pr > F

time

1

885

2.52

2.52

0.1125

0.1129

time_0

1

885

89.99

89.99

<.0001

<.0001