Scientific Software International (SSI) publishes statistical data analysis software: LISREL (structural equation model/SEM, survey generalized linear model/SGLIM), HLM (hierarchical linear modeling, multilevel model) and Item Response Theory/IRT (BILOG-MG, MULTILOG, PARSCALE)Scientific Software International (SSI) publishes statistical data analysis software: LISREL (structural equation model/SEM, survey generalized linear model/SGLIM), HLM (hierarchical linear modeling, multilevel model) and Item Response Theory/IRT (BILOG-MG, MULTILOG, PARSCALE)Scientific Software International (SSI) publishes statistical data analysis software: LISREL (structural equation model/SEM, survey generalized linear model/SGLIM), HLM (hierarchical linear modeling, multilevel model) and Item Response Theory/IRT (BILOG-MG, MULTILOG, PARSCALE)

  New in HLM 6

HLM 6 greatly broadens the range of hierarchical models that can be estimated. It also offers greater convenience of use than previous versions. Here is a quick overview of key new features and options:

  Overview of modeling options in HLM modules

Interface option

HLM2

HLM3

HMLM

HMLM2

HCM2

Basic Settings: Distribution of outcome

Normal outcome

Y

Y

-

-

-

Bernoulli outcome

Y

Y

-

-

-

Poisson outcome (constant exposure)

Y

Y

-

-

-

Poisson outcome (variable exposure)

Y

Y

-

-

-

Binomial outcome

Y

Y

-

-

-

Multinomial outcome

Y

Y

-

-

-

Ordinal outcome

Y

Y

-

-

-

Over-dispersion

Y

Y

-

-

-

Basic Settings: Residual files, title and file names

Level-1 residual file

Y

Y

-

-

Y

Level-2 residual file

Y

Y

-

-

-

Level-3 residual file

-

Y

-

-

-

Row-residual file

-

-

-

-

Y

Column-residual file

-

-

-

-

Y

Title

Y

Y

Y

Y

Y

Output filename

Y

Y

Y

Y

Y

Graph filename

Y

Y

Y

Y

Y

Basic Settings: Treatment of level-1 variance

Unrestricted

-

-

Y

Y

-

Skip unrestricted

-

-

Y

Y

-

Homogeneous

-

-

Y

Y

-

Heterogeneous

-

-

Y

Y

-

Log-linear

-

-

Y

Y

-

Predictor of level-1 var

-

-

Y

Y

-

1-st order autoregressive

-

-

Y

Y

-

Iteration Settings

Number of  iterations

Y

Y

Y

Y

Y

Frequency of accelerator

Y

Y

Y

Y

Y

% change to stop iterating

Y

Y

Y

Y

Y

How to handle bad tau

Y

Y

Y

Y

Y

How to handle bad delta

-

-

-

-

Y

What to do when convergence not reached

Y

Y

Y

Y

Y

Mode of acceleration

-

Y

-

-

-

Estimation Settings

REML

Y

-

-

-

-

FML

Y

Y

Y

Y

Y

PQL

Y

Y

-

-

-

 (HGLM)

(HGLM)

LaPlace iteration control

Y

Y

-

-

-

(HGLM)

(HGLM)

EM Laplace iteration control

Y

-

-

-

-

(HGLM)

Constraint of fixed effects

Y

Y

-

-

-

Heterogeneous sigma^2

Y

-

-

-

-

Plausible values

Y

Y

-

-

-

Multiple imputation

Y

Y

-

-

-

Latent variable regression

Y

Y

Y

-

-

Weighting

Y

Y

-

-

-

Level-1 deletion variables

Y

Y

-

-

-

Fix sigma^2 to specified value

Y

Y