|
Dependent variables
- Continuous
- Binary—logistic model
- Count—Poisson model
Types of models
- Multilevel models
- Hierarchical models
- Mixed models
- Two-, three-, and multiway random-effects models
- Crossed random effects
Types of effects
- Random effects (variance components)
- Random intercepts
- Random coefficients
- Fixed effects
Effect covariance structures
- Identity—shared variance parameter for specified effects with no covariances
- Independent—unique variance parameter for each specified effect with no covariances
- Exchangeable—shared variance parameter and single shared covariance parameter for specified effects
- Unstructured—unique variance parameter for each specified effect and unique covariance parameter for each pair of effects
- Compound—any combination of the above
Estimation
- Maximum likelihood (ML)
- Restricted maximum likelihood (REML)
Survey data*
- Sampling weights
- Robust variance estimation
- Clustered variance estimation
- Weights at each model level
- Weight rescaling
- Frequency weights
Marginal analysis
- Estimated marginal means
- Marginal and partial effects
- Average marginal and partial effects
- Least-squares means
- Predictive margins
- Adjusted predictions, means, and effects
- Contrasts of margins*
- Pairwise comparisons of margins*
- Profile plots*
- Graphs of margins and marginal effects*
Pairwise comparisons*
- Compare estimated means, intercepts, and slopes
- Compare marginal means, intercepts, and slopes
- Balanced and unbalanced data
- Nonlinear responses
- Multiple-comparison adjustments: Bonferroni, Šidák, Scheffé, Tukey HSD, Duncan, and Student-Newman-Keuls adjustments
- Group comparisons that are significant
- Graphs of pairwise comparisons
|
|
Residual-error structures for linear models
- Independent
- Exchangeable
- Autoregressive
- Moving-average
- Exponential*
- Banded*
- Toeplitz*
- Unstructured
Other features
- Factor notation for specifying effects
- Allow unbalanced designs and unbalanced panels
- EM method starting values
Predictions
- Predicted outcomes with and without effects
- Predicted effects
- Pearson, deviance, and Anscombe residuals for binary and count outcomes
- Continuous outcomes
- Best linear unbiased predictions (BLUPs) of any or all effects
- BLUPs of fitted values
- Standard errors of BLUPs
- Residuals and standardized residuals
Other postestimation analysis
- Linear and nonlinear combinations of coefficients with SEs and CIs
- Wald tests of linear and nonlinear constraints
- Likelihood-ratio tests
- Linear and nonlinear predictions
- Summarize the composition of nested groups
- Adjusted predictions
- Information criteria—AIC and BIC
- Hausman tests
Factor variables
- Automatically create indicators based on categorical variables
- Form interactions among discrete and continuous variables
- Include polynomial terms
- Perform contrasts of categories/levels
Contrasts*
- Analysis of main effects, simple effects, interaction effects, partial interaction effects, and nested effects
- Comparisons against reference groups, of adjacent levels, or against the grand mean
- Orthogonal polynomials
- Helmert contrasts
- Custom contrasts
- ANOVA-style tests
- Contrasts of nonlinear responses
- Multiple-comparison adjustments
- Balanced and unbalanced data
- Contrasts of means, intercepts, and slopes
- Graphs of contrasts
- Interaction plots
More information about mixed models in Stata.
|
