Es ist ein freies Upgrade für HLM6.0 und höher auf HLM 6.06 verfügbar. Sie können es hier herunterladen.

HLM 6 ist nun Vista-zertifiziert.

Sozialwissenschaftliche oder Psychologische Daten haben häufig eine verschachtelte (nested) Struktur. Werden z.B. wiederholt Beobachtungen an einer bestimmten Gruppe von Individuen gesammelt. so sind die Bedingungen nicht für alle Personen. Die korrekte Bezeichung eines derartigen Beobachtungsmodells wäre "geschachtelt innerhalb der Person". Jede Person könnte wiedrum verschachtelt innerhalb einer Organiation (z.B. Schule oder Arbeibeitsplatz) sein. Diese Organisation könnte weiterhin in einer geographischen Einheit (z.B. Kommune, Land, Staat) verschachtelt sein. Hierarische lineare Modelle repräsentieren jedes Niveau der Datenstruktur durch ein formal eigenständiges Untermodell. Jedes Untermodell repräsentiert die strukturellen Beziehungen auf genau einem Niveau - einschliesslich der Residualvarainz auf diesem Niveau.

New features in Version 6 include:

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:

• All new graphical displays of data: group-specific scatter plots, line plots, and cubic splines that can be color coded by values of predictor variables; box-plots displayed for overall data and data grouped within higher-level units.
• Greater expanded graphics for fitted models: graphing of group-specific equations, box-plots of level-1 residuals for each group, plots of residuals by predicted values for each group, posterior credibility intervals for random coefficients. For three-level models, level-1 trajectories are displayed in separate graphs or grouped by level-3 units. Graphs can be color coded by values of predictor variables.
• Model equations displayed in hierarchical or mixed-model format with or without subscripts - easy to save for publication. Distribution assumptions and link functions are presented in detail.
• Cross-classified random effects models for linear models and non-linear link functions with convenient Windows interface.
• High-order Laplace approximation with EM algorithm for stable convergence and accurate estimation in two-level hierarchical generalized linear models (HGLM).
• Multinomial and ordinal models for three-level data.
• New flexible and accurate sample design weighting for two- and three-level HLMs and HGLMs.
• Easier automated input from a wide variety of software packages, including the current versions of SAS, SPSS, and STATA.
• Residual files can be saved directly as SPSS (*.sav) or STATA (*.dta) files.
• Analyses are based on MDM files, replacing the older less flexible SSM format.

What's new in Version 6.06?

• General:
  • Programs would occasionally declare matrices non-positive definite when they were actually positive definite.
  • Will now read files from SPSS and Stata, up to SPSS version 16 and Stata version 10.
• HLM2:
  • Weighted HGLM (non-linear) model terminated prematurely in some cases.
  • Various multiple imputation problems (Note that the problem where the averaged output is nonsensical when one or more of the sub-analyses failed will not be fixed until version 7).
  • A problem in the hcm2 chi-squares for the random effects has been identified and fixed.
• HLM3:
  • Weighted HGLM (non-linear) model terminated prematurely in some cases.
  • Improvement to design weights.
  • ASCII/SAS residual file format problem.
  • Various multiple imputation problems (Note that the problem where the averaged output is nonsensical when one or more of the sub-analyses failed will not be fixed until version 7).
• WHLM:
  • Mixed-model window wouldn't scroll.
  • Improvements to the Exploratory Analysis interface.

• HLM Homepage.