Hlm - Real Tutoringrealtutoring.com/phd/HLM/HlmIntroMy.pdf · 2008-10-12 · The value of the likelihood function at iteration 5 = -2.328429E+004 The value of the likelihood function

��

Hlm

��

��

��

��

��

��

��

��

��

��

��

�

��

��

�

��

��

��

��MDMT��

�

��

��

�

�

��

� ��

��

��Targil1.mdmt Targil1.mdm HLM.MDM.STS Creatmdm.mdmt

�

�

��

��

��

��

��

�Program: HLM 6 Hierarchical Linear and Nonlinear Modeling �Authors: Stephen Raudenbush, Tony Bryk, & Richard Congdon �Publisher: Scientific Software International, Inc. (c) 2000 ��[email protected]

�� www.ssicentral.com ��

�Module: HLM2S.EXE (6.04.2754.2� �Date: 11 December 2007, Tuesday �Time: 13:42:34

�� SPECIFICATIONS FOR THIS HLM2 RUN ��Problem Title: no title ��The data source for this run = G:\hlmtargil2008\targil1.mdm ��The command file for this run = whlmtemp.hlm ��Output file name = G:\HLM2008\hlm2.txt ��The maximum number of level-1 units = 7185 ��The maximum number of level-2 units = 160 ��The maximum number of iterations = 100 ��Method of estimation: restricted maximum likelihood �Weighting Specification

�� Weight ��Variable ��Weighting? Name Normalized� �Level 1 no�� Level 2 no�� Precision no�� The outcome variable is MATHACH�� The model specified for the fixed effects was�

�� Level-1 Level-2 ��Coefficients Predictors

�� INTRCPT1, B0 INTRCPT2, G00��

��

�The model specified for the covariance components was� ��

��Sigma squared (constant across level-2 units� ��Tau dimensions ��INTRCPT1 �Summary of the model specified (in equation format�

�� Level-1 Model Y = B0 + R Level-2 Model B0 = G00 + U0 Iterations stopped due to small change in likelihood function ��ITERATION 4�� Sigma_squared = 39.14831 �Tau �INTRCPT1,B0 8.61431� Tau (as correlations� �INTRCPT1,B0 1.000

�� Random level-1 coefficient Reliability estimate

�� INTRCPT1, B0 0.901

�� The value of the likelihood function at iteration 4 = -2.355840E+004 The outcome variable is MATHACH �Final estimation of fixed effects�

�� Standard Approx� ��Fixed Effect Coefficient Error T-ratio d.f. P-value

�� For INTRCPT1, B0 ��INTRCPT2, G00 12.636972 0.244412 51.704 159 0.000

�� The outcome variable is MATHACH

��

�Final estimation of fixed effects ��with robust standard errors�


�� For INTRCPT1, B0 ��INTRCPT2, G00 12.636972 0.243628 51.870 159 0.000

�� Final estimation of variance components�

�� Random Effect Standard Variance df Chi-square P-value ��Deviation Component

�� INTRCPT1, U0 2.93501 8.61431 159 1660.23259 0.000 ��level-1, R 6.25686 39.14831

�� Statistics for current covariance components model

�� Deviance = 47116.793477 � Number of estimated parameters = 2

��

�� OLS!��"#intercept�$��

��

�

�

��

�

�

��

��

�Program: HLM 6 Hierarchical Linear and Nonlinear Modeling �Authors: Stephen Raudenbush, Tony Bryk, & Richard Congdon �Publisher: Scientific Software International, Inc. (c) 2000 �� [email protected]

��www.ssicentral.com ��

�Module: HLM2S.EXE (6.04.2754.2� �Date: 11 December 2007, Tuesday �Time: 16:23:23

�� SPECIFICATIONS FOR THIS HLM2 RUN ��Problem Title: no title ��The data source for this run = G:\hlmtargil2008\targil1.mdm ��The command file for this run = whlmtemp.hlm ��Output file name = G:\HLM2008\hlm2.avg ��The maximum number of level-1 units = 7185 ��The maximum number of level-2 units = 160 ��The maximum number of iterations = 100 ��Method of estimation: restricted maximum likelihood �Weighting Specification

�� Weight ��Variable ��Weighting? Name Normalized� �Level 1 no�� Level 2 no�� Precision no ��

��

��The outcome variable is MATHACH�� The model specified for the fixed effects was�

�� Level-1 Level-2 ��Coefficients Predictors

�� INTRCPT1, B0 INTRCPT2, G00�� MEANSES, G01��

�� SES slope, B1 INTRCPT2, G10�� The residual parameter variance for this level-1 coefficient has been set

��to zero� �� This level-1 predictor has been centered around its group mean�

�� This level-2 predictor has been centered around its grand mean� �The model specified for the covariance components was�

�� Sigma squared (constant across level-2 units� ��Tau dimensions ��INTRCPT1 �Summary of the model specified (in equation format�

�� Level-1 Model Y = B0 + B1*(SES) + R Level-2 Model B0 = G00 + G01*(MEANSES) + U0 B1 = G10� Level-1 OLS regressions

�� Level-2 Unit INTRCPT1��

��

��

��

The average OLS level-1 coefficient for INTRCPT1 = 12.62075 �Least Squares Estimates

�� sigma_squared = 39.63669 �The outcome variable is MATHACH �Least-squares estimates of fixed effects

�� Standard ��Fixed Effect Coefficient Error T-ratio d.f. P-value

�� For INTRCPT1, B0 ��INTRCPT2, G00 12.711688 0.074282 171.126 7182 0.000 ��MEANSES, G01 5.716800 0.179611 31.829 7182 0.000 �For SES slope, B1 ��INTRCPT2, G10 2.191172 0.112444 19.487 7182 0.000

��

��

The outcome variable is MATHACH �Least-squares estimates of fixed effects ��with robust standard errors�

�� Standard ��Fixed Effect Coefficient Error T-ratio d.f. P-value


�� The least-squares likelihood value = -23416.839136 �Deviance = 46833.67827 �Number of estimated parameters = 1 �STARTING VALUES

�� sigma(0)_squared = 36.99907 �Tau(0� �INTRCPT1,B0 2.87266� �The outcome variable is MATHACH �Estimation of fixed effects �Based on starting values of covariance components�



�� The value of the likelihood function at iteration 1 = -2.328438E+004

��

The value of the likelihood function at iteration 2 = -2.328431E+004 The value of the likelihood function at iteration 3 = -2.328429E+004 The value of the likelihood function at iteration 4 = -2.328429E+004 The value of the likelihood function at iteration 5 = -2.328429E+004

�� The value of the likelihood function at iteration 5 = -2.328429E+004 Iterations stopped due to small change in likelihood function ��ITERATION 6�� Sigma_squared = 37.01907 �Tau �INTRCPT1,B0 2.69235� Tau (as correlations� �INTRCPT1,B0 1.000

�� Random level-1 coefficient Reliability estimate

�� INTRCPT1, B0 0.754

�� The value of the likelihood function at iteration 6 = -2.328429E+004 �The outcome variable is MATHACH �Final estimation of fixed effects�



��

��

�The outcome variable is MATHACH �Final estimation of fixed effects ��with robust standard errors�



�� Final estimation of variance components�

�� Random Effect Standard Variance df Chi-square P-value ��Deviation Component

�� INTRCPT1, U0 1.64084 2.69235 158 670.16369 0.000 ��level-1, R 6.08433 37.01907

�� Statistics for current covariance components model

�� Deviance = 46568.577332 �Number of estimated parameters = 2

��

GET FILE='G:\hlmtargil2008\hsb1.sav'. REGRESSION /MISSING LISTWISE /STATISTICS COEFF OUTS R ANOVA /CRITERIA=PIN(.05) POUT(.10) /NOORIGIN /DEPENDENT mathach /METHOD=ENTER ses .

��

Coefficientsa

12.747 .076 168.424 .0003.184 .097 .361 32.783 .000

(Constant)SES

Model1

B Std. Error

UnstandardizedCoefficients

Beta

Standardized

Coefficients

t Sig.

Dependent Variable: MATHACHa.

Coefficients a

12.622 .153 82.347 .0005.909 .371 .785 15.910 .000

(Constant)MEANSE_1

Model1

B Std. Error


Beta

Standardized

Coefficients

t Sig.

Dependent Variable: MATHAC_1a.

Coefficients a

12.657 .153 82.568 .0005.909 .371 .785 15.910 .000

(Constant)SES_1

Model1

B Std. Error


Beta

Standardized

Coefficients

t Sig.

Dependent Variable: MATHAC_1a.

��

��

��

��

��

Documents

Hlm - Real Tutoringrealtutoring.com/phd/HLM/HlmIntroMy.pdf · 2008-10-12 · The value of the likelihood function at iteration 5 = -2.328429E+004 The value of the likelihood function