|
|
|
 |
|
|
共分散構造分析ソフトウェア
Amos 4
(Windows95/98/NT4.0/2000版) |
|
Amos の際立った機能
* Graphical, fully interactive model specification. Amos accepts a path diagram as a model specification, and displays parameter estimates graphically on a path diagram. The path diagrams used for model specification, as well as those that display parameter estimates, are of presentation quality. They can be printed directly, or imported into other applications, such as word processors, desktop publishing programs, and general purpose graphics programs.
* Estimation by ML, GLS, ADF, ULS or SLS (scale-free least squares)
* Many types of fit statistics, including chi-square, Akaike, Bayes and Bozdogan information criteria, Browne and Cudeck BCC, ECVI, RMSEA and PCLOSE criteria, root mean square residual, Hoelter's critical n, Bentler-Bonett and Tucker-Lewis indices, etc.
* Effortless modeling of mean structures and multiple-group datasets. Flexible modeling across groups, possibly even with different models for different groups. Mean and intercept estimates are displayed in the path diagram.
* Fitting of multiple models in a single analysis. Amos examines every pair of models in which one model can be obtained by placing restrictions on the parameters of the other. The program reports several statistics appropriate for comparing models for different groups. Mean and intercept terms displayed in the path diagram.
* Efficient missing data modeling by full-information (case-wise) maximum likelihood.
* Fast bootstrap simulation yields bias estimates and empirical standard errors of model parameters and fit functions, for any empirical distribution of the data.
* Percentile and bias-corrected percentile formulas yield non-naive confidence intervals from the bootstrap simulation.
* Bollen-Stine chi-square correction for model testing by bootstrap when normality assumptions are violated.
* Normal-theory Monte-Carlo simulation to evaluate approximate confidence intervals of any model parameter estimate, including standardized coefficients.
* Test of univariate normality for each observed variable, as well as a test of multivariate normality.
* Multivariate outlier detection.
* Randomized permutation test shows whether equivalent or better fitting models can easily be found.
|
| Amos 4のTopページに戻る |
|
|
