Help using Base SAS procedures

combining HPMIXED and MIXED for individual cross-classified growth models

Accepted Solution Solved
Reply
Contributor
Posts: 24
Accepted Solution

combining HPMIXED and MIXED for individual cross-classified growth models

I have a large, longitudinal data set -- seven years of data for approximately 115,000 students  (approximately 500,000 observations), attending approximately 600 schools.  I am doing cross-classified individual growth modeling (cross-classified because students change schools).  Since the data set is so large, I am estimating models with small (2 percent) subsamples of the data set.  However, with the 2 percent subsamples, the data are sparse; and so PROC MIXED cannot estimate the covariance parameters. Therefore, I am using a combination of HPMIXED and MIXED.   This way I can estimate the covariance parameters in HPMIXED, and then pass them along to MIXED. Then I can compute sequential F-tests and make adjustments for multiple comparisons in testing differences between LSMEANS.

The grouping variable of interest is ProFnc: 1=proficient, 0=non-proficient.  When I put the grouping variable in the model with no interactions, the fixed effects produced by HPMIXED and MIXED are the same. However, HPMIXED estimates a fixed effect for ProFnc=1, where as MIXED estimates an effect for ProFnc=0.

Then, when I add to the model interactions with the grouping variable, the fixed effects seem to behave strangely.  I don't know if I should ignore the fixed effects that HPMIXED produces, and just go with the fixed effects that MIXED produces.  And if that is the case, can I trust the covariance parameters coming out of HPMIXED?  Can I trust the fixed effects that MIXED is producing?  If there is a problem, is there a change I can make in the code to fix this?

Below I have pasted the code and output for the two models I described above.  Again, I first have the model with the grouping variable but no interactions; and second, I have the model with the grouping variable and its interactions.  (Note: I realize these particular interactions are not significant, but I am trying to understand what SAS is doing here and which numbers I can trust.)

Thank you in advance for any help with this.


/* MODEL 1 - the grouping variable (ProFnc) and NO interactions */

/* HPMIXED */

PROC HPMIXED DATA=sub2pct_long noclprint;

CLASS stdpseudoid schcode ProFnc;

MODEL zELA = Timec|Timec|Timec|Timec

Female

PrEdClGrd

PrEdSmClHS

FRL

ProFnc

zCeldt /solution ;

RANDOM intercept Timec  /subject=stdpseudoid type=un;

RANDOM intercept /subject=schcode type=un;

ODS OUTPUT covparms=hpmcov2pct;

RUN;

/* MIXED */

PROC MIXED DATA=sub2pct_long noclprint covtest lognote method=reml;

CLASS stdpseudoid schcode ProFnc;

MODEL zELA = Timec|Timec|Timec|Timec

Female

PrEdClGrd

PrEdSmClHS

FRL

zCeldt

ProFnc /solution htype=1;

RANDOM intercept Timec /subject=stdpseudoid type=un;

RANDOM intercept /subject=schcode type=un;

PARMS/PDATA=hpmcov2pct hold=1,2,3,4,5 noiter;

RUN;

  

THE HPMIXED PROCEDURE

Data Set

WORK.SUB2PCT_LONG

Response Variable

zELA

Estimation Method

Restricted Maximum Likelihood (REML)

Degrees of Freedom Method

Residual

Number of Observations Read

10175

Number of Observations Used

8898

  

Dimensions

G-side Cov. Parameters

4

R-side Cov. Parameters

1

Columns in X

12

Columns in Z

4969

Subjects (Blocks in V)

1

 

Optimization Information

Optimization Technique

Dual Quasi-Newton

Parameters in Optimization

4

Lower Boundaries

3

Upper Boundaries

0

Residual Variance

Profiled

   

Iteration History

Iterations

Evaluations

Objective Function

Change

Max Gradient

0

4

18310.276802

. 3333

425.1763

1

4

18306.028084

4.2487182056.80605

2

3

18305.679162

0.3489220374.52385

3

3

18305.05507

0.6240921039.65128

4

4

18305.032432

0.0226379838.72127

5

4

18304.982517

0.049914564.723682

6

3

18304.981792

0.000725310.027503

7

3

18304.981792

0.000000020.000091

 

Convergence criterion (GCONV=1E-8) satisfied.

 

Covariance Parameter Estimates

Cov Parm

Subject

Estimate

UN(1,1)

StdPseudoId

0.6356

UN(2,1)

StdPseudoId

-0.00929

UN(2,2)

StdPseudoId

0.01124

UN(1,1)

SchCode

0.009595

Residual

0.2287

  

Fit Statistics

-2 Res Log Likelihood

18305

AIC (smaller is better)

18315

AICC (smaller is better)

18315

BIC (smaller is better)

18305

CAIC (smaller is better)

18310

HQIC (smaller is better)

18305

   

Solution for Fixed Effects

Effect

ProFnc

Estimate

Standard Error

DF

t Value

Pr > |t|

Intercept

-0.1662

0.04025

8887

-4.13

<.0001

Timec

-0.02220

0.03404

8887

-0.65

0.5144

Timec*Timec

-0.00221

0.02929

8887

-0.08

0.9398

Timec*Timec*Timec

0.002277

0.008339

8887

0.270.7848

Time*Time*Time*Timec

-0.00020

0.000738

8887

-0.26

OC0.7913

Female

0.05291

0.03625

8887

1.460.1444

PrEdClGrd

0.1948

0.09722

8887

2.000.0452

PrEdSmClHS

0.1982

0.04100

8887

4.83<.0001

FRL

-0.04520

0.03694

8887

-1.22

0.2212

ProFnc

0

0

.

.

.

.

ProFnc

1

0.2171

0.0367388875.91<.0001

zCeldt

0.2361

0.01803888713.10<.0001

 


THE MIXED PROCEDURE

Data Set

WORK.SUB2PCT_LONG

Dependent Variable

zELA

Covariance Structures

Unstructured, Variance Components

Subject Effects

StdPseudoId, SchCode

Estimation Method

REML

Residual Variance Method

Parameter

Fixed Effects SE Method

Model-Based

Degrees of Freedom Method

Containment

  

 

Covariance Parameters

5

Columns in X

20

Columns in Z

4969

Subjects

1

Max Obs Per Subject

10175

 

Number of Observations

Number of Observations Read

10175

Number of Observations Used

8898

Number of Observations Not Used

1277

 

Parameter Search

CovP1

CovP2

CovP3

CovP4

CovP5

Res Log Like

-2 Res Log Like

0.6356

-0.00929

0.01124

0.0095950.2287-9152.490918304.9818

 

Covariance Parameter Estimates

Cov Parm

Subject

Estimate

Standard Error

Z Value

Pr Z

UN(1,1)

StdPseudoId

0.6356

0

.

.

UN(2,1)

StdPseudoId

-0.00929

0

.

.

UN(2,2)

StdPseudoId

0.01124

0

.

.

UN(1,1)

SchCode

0.009595

0

.

.

Residual

0.2287

0

.

.

Fit Statistics

-2 Res Log Likelihood

18305.0

AIC (smaller is better)

18305.0

AICC (smaller is better)

18305.0

BIC (smaller is better)

18305.0

 

Solution for Fixed Effects

Effect

ProFnc

Estimate

Standard Error

DF

t Value

Pr > |t|

Intercept

0.05087

0.04413

425

1.150.2497

Timec

-0.02220

0.03404

2040

-0.65

0.5144

Timec*Timec

-0.00221

0.02929

4190

-0.08

0.9398

Timec*Timec*Timec

0.002277

0.008339

4190

0.270.7848

Time*Time*Time*Timec

-0.00020

0.000738

4190

-0.26

0.7913

Female

0.05291

0.03625

4190

1.460.1444

PrEdClGrd

0.1948

0.09722

4190

2.000.0452

PrEdSmClHS

0.1982

0.04100

4190

4.83

<.0001

FRL

-0.04520

0.03694

4190

-1.22

0.2212

ProFnc

0

-0.2171

0.03673

4190

-5.91

<.0001

ProFnc

1

0

.

.

.

.

zCeldt

0.2361

0.01803419013.10<.0001

 

Type I Tests of Fixed Effects

Effect

Num DF

Den DF

F Value

Pr > F

Timec

1

2040

0.66

0.4156

Timec*Timec

1

4190

10.33

0.0013

Timec*Timec*Timec

1

4190

0.03

0.8713

Time*Time*Time*Timec

1

4190

0.01

0.9256

Female

1

4190

5.38

0.0204

PrEdClGrd

1

4190

3.38

0.0659

PrEdSmClHS

1

4190

31.73

<.0001

FRL

1

4190

0.56

0.4555

ProFnc

1

4190

33.85

<.0001

zCeldt

1

4190

171.49

<.0001


/* MODEL 2 - the grouping variable (ProFnc), AND its interactions */

/* HPMIXED */

PROC HPMIXED DATA=sub2pct_long noclprint;

CLASS stdpseudoid schcode ProFnc;

MODEL zELA =      Timec|Timec|Timec|Timec

Female

PrEdClGrd

PrEdSmClHS

FRL

zCeldt

ProFnc

ProFnc*Female

ProFnc*PrEdClGrd

ProFnc*PrEdSmClHS

ProFnc*zCeldt /solution ;

RANDOM intercept Timec /subject=stdpseudoid type=un;

RANDOM intercept /subject=schcode type=un;

ODS OUTPUT covparms=hpmcov2pct;

RUN;

/* MIXED */

PROC MIXED DATA=sub2pct_long noclprint covtest lognote method=reml;

CLASS stdpseudoid schcode ProFnc;

MODEL zELA =      Timec|Timec|Timec|Timec

Female

PrEdClGrd

PrEdSmClHS

FRL

ProFnc

zCeldt

ProFnc*Female

ProFnc*PrEdClGrd

ProFnc*PrEdSmClHS

ProFnc*zCeldt /solution htype=1;

RANDOM intercept Timec               /subject=stdpseudoid type=un;

RANDOM intercept /subject=schcode type=un;

PARMS/PDATA=hpmcov2pct hold=1,2,3,4,5 noiter;

RUN;

  

THE HPMIXED PROCEDURE

Data Set

WORK.SUB2PCT_LONG

Response Variable

zELA

Estimation Method

Restricted Maximum Likelihood (REML)

Degrees of Freedom Method

Residual

  

Number of Observations Read

10175

Number of Observations Used

8898

Dimensions

G-side Cov. Parameters

4

R-side Cov. Parameters

1

Columns in X

20

Columns in Z

4969

Subjects (Blocks in V)

1

Optimization Information

Optimization Technique

Dual Quasi-Newton

Parameters in Optimization

4

Lower Boundaries

3

Upper Boundaries

0

Residual Variance

Profiled

      

Iteration History

Iteration

Evaluations

Objective Function

Change

Max Gradient

0

4

18320.233278

.

430.4562

1

4

18315.885135

4.3481432657.74109

2

3

18315.533274

0.3518610175.8847

3

3

18314.895565

0.6377089040.89073

4

4

18314.872387

0.0231783439.85029

5

4

18314.819313

0.053073953.502647

6

3

18314.818918

0.000394100.020809

7

3

18314.818918

0.000000010.000075

 

Convergence criterion (GCONV=1E-8) satisfied.

Covariance Parameter Estimates

CovParm

Subject

Estimate

UN(1,1)

StdPseudoId

0.6363

UN(2,1)

StdPseudoId

-0.00940

UN(2,2)

StdPseudoId

0.01123

UN(1,1)

SchCode

0.009609

Residual

0.2287

 

Fit Statistics

-2 Res Log Likelihood

18315

AIC (smaller is better)

18325

AICC (smaller is better)

18325

BIC (smaller is better)

18315

CAIC (smaller is better)

18320

HQIC (smaller is better)

18315

Solution for Fixed Effects

Effects

ProFnc

Estimate

Standard Error

DF

t Value

Pr > |t|

Intercept

-0.1545

0.04406

8883

-3.51

0.0005

Timec

-0.02224

0.03404

8883

-0.65

0.5136

Timec*Timec

-0.00219

0.02929

8883

-0.07

0.9404

Timec*Timec*Timec

0.002277

0.008339

8883

0.270.7848

Time*Time*Time*Timec

-0.00020

0.000738

8883

-0.27

0.7909

Female

0

.

.

.

.

PrEdClGrd

0

.

.

.

.

PrEdSmClHS

0

.

.

.

.

FRL

-0.04623

0.03708

8883

-1.25

0.2125

ProFnc

0

0

.

.

.

.

ProFnc

1

0.1951

0.05881

8883

3.320.0009

zCeldt

0

.

.

.

.

Female*ProFnc

0

0.06340

0.04752

8883

1.330.1822

Female*ProFnc

1

0.03835

0.05611

8883

0.680.4943

PrEdClGrd*ProFnc

0

0.1479

0.1253

8883

1.180.2377

PrEdClGrd*ProFnc

1

0.2608

0.1544

8883

1.690.0911

PrEdSmClHS*ProFnc

0

0.1508

0.05290

8883

2.850.0044

PrEdSmClHS*ProFnc

1

0.2672

0.06477

88834.13<.0001

zCeldt*ProFnc

0

0.2515

0.02414

888310.42<.0001

zCeldt*ProFnc

1

0.2173

0.02710

8883

8.02

<.0001

 


  

THE MIXED PROCEDURE

Data Set

WORK.SUB2PCT_LONG

Dependent Variable

zELA

Covariance Structures

Unstructured, Variance Components

Subject Effects

StdPseudoId, SchCode

Estimation Method

REML

Residual Variance Method

Parameter

Fixed Effects SE Method

Model-Based

Degrees of Freedom Method

Containment

  

Dimensions

Covariance Parameters

5

Columns in X

20

Columns in Z

4969

Subjects

1

Max Obs Per Subject

10175

  

Number of Observations Read

10175

Number of Observations Used

8898

Number of Observations Not Used

1277

       

Parameter Search

CovP1

CovP2

CovP3

CovP4

CovP5

Res Log Like

-2 Res Log Like

0.6363

-0.00940

0.01123

0.009609

0.2287-9146.853118293.7063

       

Covariance Parameter Estimates

Cov Parm

Subject

Estimate

Standard Error

Z Value

Pr Z

UN(1,1)

StdPseudoId

0.6363

0

.

.

UN(2,1)

StdPseudoId

-0.00940

0

.

.

UN(2,2)

StdPseudoId

0.01123

0

.

.

UN(1,1)

SchCode

0.009609

0

.

.

Residual

0.2287

0

.

.

  

Fit Statistics

-2 Res Log Likelihood

18293.7

AIC (smaller is better)

18293.7

AICC (smaller is better)

18293.7

BIC (smaller is better)

18293.7

        

Solution for Fixed Effects

Effect

ProFnc

Estimate

Standard Error

DF

t Value

Pr > |t|

Intercept

0.03238

15327

425

0.00

1.0000

Timec

-0.02224

0.03404

2040

-0.65

0.5136

Timec*Timec

-0.00219

0.02929

4190

-0.07

0.9404

Timec*Timec*Timec

0.002277

0.008339

4190

0.270.7848

Time*Time*Time*Timec

-0.00020

0.000738

4190

-0.27

0.7909

Female

0.03835

0.05611

4190

0.680.4943

PrEdClGrd

0.2608

0.1544

4190

1.690.0911

PrEdSmClHS

0.2672

0.06477

41904.13<.0001

FRL

-0.04623

0.03708

4190

-1.25

0.2125

ProFnc

0

-0.1869

15327

4190

-0.00

1.0000

ProFnc

1

0.008199

15327

4190

0.00

1.0000

zCeldt

0.2173

0.02710

4190

8.02

<.0001

Female*ProFnc

0

0.02505

0.07352

4190

0.340.7333

Female*ProFnc

1

0

.

.

.

.

PrEdClGrd*ProFnc

0

-0.1129

0.1988

4190

-0.57

0.5701

PrEdClGrd*ProFnc

1

0

.

.

.

.

PrEdSmClHS*ProFnc

0

-0.1165

0.08351

4190

-1.39

0.1631

PrEdSmClHS*ProFnc

1

0

.

.

.

.

zCeldt*ProFnc

0

0.03423

0.03626

4190

0.940.3453

zCeldt*ProFnc

1

0

.

.

.

.

      

Type I Tests of Fixed Effects

Effect

Num DF

Den DF

F Value

Pr > F

Timec

1

2040

0.63

0.4270

Timec*Timec

1

4190

10.39

0.0013

Timec*Timec*Timec

1

4190

0.01

0.9113

Time*Time*Time*Timec

1

4190

0.01

0.9377

Female

1

4190

5.35

0.0208

PrEdClGrd

1

4190

3.39

0.0657

PrEdSmClHS

1

4190

31.90

<.0001

FRL

1

4190

0.52

0.4690

ProFnc

1

4190

33.97

<.0001

zCeldt

1

4190

171.07

<.0001

Female*ProFnc

1

4190

0.10

0.7482

PrEdClGrd*ProFnc

1

4190

0.14

0.7094

PrEdSmClHS*ProFnc

1

4190

1.74

0.1877

zCeldt*ProFnc

1

4190

0.89

0.3453

Accepted Solutions
Solution
‎03-05-2013 10:28 AM
Respected Advisor
Posts: 2,655

Re: combining HPMIXED and MIXED for individual cross-classified growth models

Ah, a much easier question. Because your errors are gaussian, I believe that the random effect estimates are good.  Proceeding from the fixed estimates, differences between levels were constant between the two methods, so variance estimates should not be affected.  I still advise against htype=1, due to likely unbalance, and the potential for order entry effects as a result.  (Although somewhere, Frank Harrell is rolling his eyes in disgust at this advice).

Steve Denham

View solution in original post


All Replies
Respected Advisor
Posts: 2,655

Re: combining HPMIXED and MIXED for individual cross-classified growth models

Without going into a lot of other interesting things, one way of putting the two procs "on the same" page would be the use of the ref= option in the class statement.  Perhaps something like:

CLASS stdpseudoid schcode ProFnc(ref='1');

for both procs.  This would put MIXED on the same reference as HPMIXED.  Once you do this, I think you will be satisfied with all of the other things you are doing in moving the covariance parameters over to MIXED.  It would be nice if the STORE statement was available for HPMIXED, as then all of the adjustments you are using MIXED for would be available directly for the HPMIXED output.  Good luck with this project, and let us know if this helps at all.

Steve Denham

Contributor
Posts: 24

Re: combining HPMIXED and MIXED for individual cross-classified growth models

Posted in reply to SteveDenham

Thanks very much, Steve.

I must be missing something. ProFnc is a numeric variable (0 or 1).  I tried making 0 the ref group, but received a syntax error. Please see below:

 

NOTE: The SAS System stopped processing this step because of errors.

PROC HPMIXED DATA=sub2pct_long noclprint;

CLASS stdpseudoid schcode ProFnc(ref=0);

                                                       -

                                                       22

                                                       76

ERROR 22-322: Syntax error, expecting one of the following: a name, ;, -, /, :, _ALL_,

               _CHARACTER_, _CHAR_, _NUMERIC_.

ERROR 76-322: Syntax error, statement will be ignored.

MODEL zELA = Timec|Timec|Timec|Timec

                         Female

                         PrEdClGrd

                         PrEdSmClHS

                         FRL

                         ProFnc

                         zCeldt          /solution htype=1;

RANDOM intercept Timec      /subject=stdpseudoid type=un;

RANDOM intercept                /subject=schcode type=un;

PARMS /PDATA=hpmcov2pct hold=1,2,3,4,5 noiter;

RUN;

Respected Advisor
Posts: 2,655

Re: combining HPMIXED and MIXED for individual cross-classified growth models

The ref= syntax requires the level to be quoted, whether it is character or numeric in nature.  Try


CLASS stdpseudoid schcode ProFnc(ref='0');

making sure to quote the zero.

Steve Denham

Contributor
Posts: 24

Re: combining HPMIXED and MIXED for individual cross-classified growth models

Posted in reply to SteveDenham

Still no luck. I got the same error...

PROC HPMIXED DATA=sub2pct_long noclprint;

CLASS stdpseudoid schcode ProFnc(ref='0');

                                                      -

                                                     22

                                                     76

ERROR 22-322: Syntax error, expecting one of the following: a name, ;, -, /, :, _ALL_,

_CHARACTER_, _CHAR_, _NUMERIC_.

ERROR 76-322: Syntax error, statement will be ignored.

MODEL zELA = Timec|Timec|Timec|Timec

                         Female

                         PrEdClGrd

                         PrEdSmClHS

                         FRL

                         ProFnc

                         zCeldt           /solution ;

RANDOM intercept Timec      /subject=stdpseudoid type=un;

RANDOM intercept                /subject=schcode type=un;

ODS OUTPUT covparms=hpmcov2pct;

RUN;

Respected Advisor
Posts: 2,655

Re: combining HPMIXED and MIXED for individual cross-classified growth models

Two possible workarounds:

In HPMIXED (this seems to have a real finicky taste for the ref= option):

class stdpseudoid schcode ProFnc(ref=LAST);

     and leave MIXED unchanged, or

In MIXED:

class stdpseudoid schcode ProFnc(ref='0');

  and leave HPMIXED unchanged, or at least without the ref= option.

I noticed something else--the fixed effects are not listed in exactly the same order in the two PROCS.  I am just curious as to whether that may be affecting things, as might the htype=1 hypothesis tests.  Given the likely unbalanced nature and the order dependence of Type 1 hypotheses, this may also be something to be concerned about.

Steve Denham

   .

Contributor
Posts: 24

Re: combining HPMIXED and MIXED for individual cross-classified growth models

Posted in reply to SteveDenham

Still no luck.

First, I tried the following:

PROC HPMIXED DATA=sub2pct_long noclprint;

CLASS stdpseudoid schcode ProFnc (ref=LAST);

MODEL zELA = Timec|Timec|Timec|Timec

                         Female

                         PrEdClGrd

                         PrEdSmClHS

                         FRL

                         ProFnc

                         zCeldt           /solution ;

RANDOM intercept Timec       /subject=stdpseudoid type=un;

RANDOM intercept                /subject=schcode type=un;

ODS OUTPUT covparms=hpmcov2pct;

RUN;

But received the same error message for HPMIXED:

 

CLASS stdpseudoid schcode ProFnc (ref=LAST);

                                                       -

                                                       22

                                                       76

ERROR 22-322: Syntax error, expecting one of the following: a name, ;, -, /, :, _ALL_,

_CHARACTER_, _CHAR_, _NUMERIC_.

ERROR 76-322: Syntax error, statement will be ignored.

Then, I tried the following:

PROC HPMIXED DATA=sub2pct_long noclprint;

CLASS stdpseudoid schcode ProFnc;

MODEL zELA = Timec|Timec|Timec|Timec

                         Female

                         PrEdClGrd

                         PrEdSmClHS

                         FRL

                         ProFnc

                         zCeldt           /solution ;

RANDOM intercept Timec       /subject=stdpseudoid type=un;

RANDOM intercept                /subject=schcode type=un;

ODS OUTPUT covparms=hpmcov2pct;

RUN;

PROC MIXED DATA=sub2pct_long noclprint covtest lognote method=reml;

CLASS stdpseudoid schcode ProFnc (ref='0');

MODEL zELA = Timec|Timec|Timec|Timec

                         Female

                         PrEdClGrd

                         PrEdSmClHS

                         FRL

                         ProFnc

                         zCeldt           /solution htype=1;

RANDOM intercept Timec        /subject=stdpseudoid type=un;

RANDOM intercept                  /subject=schcode type=un;

PARMS /PDATA=hpmcov2pct hold=1,2,3,4,5 noiter;

RUN;

But I received the same error message for MIXED:

CLASS stdpseudoid schcode ProFnc (ref='0');

                                                       -

                                                       22

                                                       76

ERROR 22-322: Syntax error, expecting one of the following: a name, ;, -, /, :, _ALL_,

_CHARACTER_, _CHAR_, _NUMERIC_.

ERROR 76-322: Syntax error, statement will be ignored.

Respected Advisor
Posts: 2,655

Re: combining HPMIXED and MIXED for individual cross-classified growth models

This is very curious and unexpected behavior.  I have used the ref= option in the class statement of both procedures and have not run into this error, other than when the value was unquoted. FIRST and LAST always seem to work  Since the other class variables are used only as subjects in the random statements, perhaps the global version would work:

CLASS stdpseudoid schcode ProFnc /ref=FIRST;

Steve Denham

Contributor
Posts: 24

Re: combining HPMIXED and MIXED for individual cross-classified growth models

Posted in reply to SteveDenham

Thanks, Steve.  I tried the global version and received the same error message.  I think the reason is I have version 9.3 TS1M0, not TS1M2 (as specified below):

" NOTE : The REF= option for setting reference levels was added to the GLM, MIXED, GLIMMIX, and ORTHOREG beginning in SAS 9.3 TS1M2."

Can I trust the random effects from HP even where the fixed effects seem weird (i.e. even when it is estimating parameters for both categories of a dichotomous CLASS variable) ?  

Solution
‎03-05-2013 10:28 AM
Respected Advisor
Posts: 2,655

Re: combining HPMIXED and MIXED for individual cross-classified growth models

Ah, a much easier question. Because your errors are gaussian, I believe that the random effect estimates are good.  Proceeding from the fixed estimates, differences between levels were constant between the two methods, so variance estimates should not be affected.  I still advise against htype=1, due to likely unbalance, and the potential for order entry effects as a result.  (Although somewhere, Frank Harrell is rolling his eyes in disgust at this advice).

Steve Denham

Contributor
Posts: 24

Re: combining HPMIXED and MIXED for individual cross-classified growth models

Posted in reply to SteveDenham

Thanks very much for your help.  Much appreciated.

Contributor
Posts: 24

Re: combining HPMIXED and MIXED for individual cross-classified growth models

Posted in reply to SteveDenham

Hi Steve,

I have a follow-up question I was hoping you might be able to answer...

Is it possible to get MIXED to generate hypothesis tests for covariance parameters even when it's prevented from iterating on them when given values from HPMIXED? It seems to go back to solving for the random effects, which is what takes all the time and memory, and what I'm trying to avoid by using HPMIXED and MIXED.

thank you.

Respected Advisor
Posts: 2,655

Re: combining HPMIXED and MIXED for individual cross-classified growth models

What sort of tests do you have in mind--being cognizant of the distributional assumptions regarding estimates of variance, etc?  Once upon a time, MIXED automatically "tested" whether the individual variance estimates were different from zero as part of the default output, using an asymptotic normal assumption.  Those tests were, well, wrong.  Sometimes Wald tests just do not apply.

Anyway, PROC GLIMMIX enables some specific kinds of G side testing.  But I would avoid tests if at all possible and consider instead the estimation approach, looking at confidence bounds on the parameters.  Those should be available from HPMIXED.  When you fix/hold/noiter variance-covariances, I don't think there will be any way to calculate bounds or tests on the parameters.  The blup's, on the other hand, can be compared, using the ESTIMATE statement.

Steve Denham

Contributor
Posts: 24

Re: combining HPMIXED and MIXED for individual cross-classified growth models

Posted in reply to SteveDenham

Well I was thinking about testing whether individual variance estimates were different from zero, using covtest.  But if I were to look at the confidence bounds, I would do so with ' cl ' after the slash in the random statement?  And to prevent SAS from outputting confidence intervals for every student?

RANDOM intercept  Timec     /subject=stdpseudoid type=un cl;

RANDOM intercept            /subject=schcode type=un;

One last question if I could...  Do you have any thoughts on whether it's useful/appropriate to include school-level covariates in the model even if a very small percentage (definitely less than 5%, and maybe closer to 2%) of variance is between schools?  An argument in favor of including school-level covariates is that the composition of schools could still be affecting individual student performance, even if the average performance across schools doesn't vary that much.

Respected Advisor
Posts: 2,655

Re: combining HPMIXED and MIXED for individual cross-classified growth models

So the code with cl in it should only give three estimates (intercept, timec and their covariance) with confidence bounds.  Only if you specify solution, or do the blups, would I expect to get a confidence bound for each student.

I always try to include design covariates, and the school-level covariates strike me as design based in the following sense:  If you set up a designed experiment to look at these effects, you would include them.  In this case, not including them would probably increase the standard errors and reduce the precision of your estimates.

Steve Denham

🔒 This topic is solved and locked.

Need further help from the community? Please ask a new question.

Discussion stats
  • 15 replies
  • 458 views
  • 3 likes
  • 2 in conversation