HLM Support

SSI, Inc. offers a technical support service via e-mail. This service is only available to registered end users of the SSI software products. Click here to view SSI’s policy and procedures for obtaining technical support.

This service applies to problems in using the software and does not include statistical consultation. If you need help with modeling concepts and interpretation, please consult our list of related material or post a question to the Multilevel Listserv. If you require statistical consultation service, Vector Psychometric Group‘s Consulting Division would be pleased to be of assistance. Contact the VPG Sales Desk at sales@vpgcentral.com for more information.

Please note that the program may not be able to read special characters such as ė, ö, ý, ş, etc. not used in English. Users should take care to avoid the use of these in either path or file names when using HLM.

Recently revised documentation/procedures

These documents describe changes to the program features not documented in the current manual.

HLM 8.1: Handling of missing data in all modules

HLM 8.1: Description of currently implemented weighting scheme


Anything Else option for data import

Batch creation of multiple MDMs

Specifying an AR model at level-1 for unequally spaced measurements

Running multiple analyses using a batch file

Calculating cross-level interactions

Calculating posterior variances

Comparing model fit

Confidence intervals for fixed effects

Constraints and hypothesis testing

Deviance statistic in HGLM

Degrees of freedom: HCM2

Degrees of freedom: HCM3

Degrees of freedom: HLM2

Degrees of freedom: HLM3

Degrees of freedom: HLM4

Degrees of freedom: HLMHCM

Effect size and standardized coefficients

HGLM models: extreme values of p

HGLM models: level-1 variance


Evaluating random slopes for an HMLM model

Creating indicator variables for HMLM modules

Hypothesis testing for variance-covariance components

Level-1 variance in the case of HGLM models

Level-1 variance: homogeneous or heterogeneous

Log likelihood and negative deviances


Multiple imputation analyses

Ordinal model: subtraction vs addition

Over dispersion

Proper vs improper imputation

Proportion variance explained in 2-level model

Proportion variance explained in a 3-level model


Reliability of random coefficients

Robust standard errors

Standardized coefficients

Testing significance of sigma-squared

Use of additional output file tauvc.dat

Use of additional output file gamvc.dat

Transposing data for use in HMLM/HMLM2

Use of proportion variance explained statistics

Weighting in HCM3

Error messages

Actual number of occasions exceeds…

Data not sorted

Effect has been fixed… 

Fisher scoring algorithm is unable…   

Group X has inadequate data

Group X not in level Y file   

HGLM specific error messages

HLM is unable to estimate covariance components  

Improper imputation

Invalid dictionary subtype

Laplace iterations stops prematurely

Errors occurred when making MDM

MDM file not of recognized type

Values of MDIST and CHIPCT are missing

No robust standard errors are reported 

OLS coefficients were only computed for ….   

Only robust standard errors are reported

Only X out of Y units used..    

P-values incorrect or not reported

Random effects needs to be restricted

Robust standard errors cannot be computed for this model

System errors    

Descriptive statistics are incorrect

The model should be respecified…   

There are no degrees of freedom left      

There is a problem in the fixed part of the model    

Unable to open the file for writing   

Very large numbers in output 

VTheta1 not invertible 

X of Y units failed the conditioning check