Stata 15 help for sem reporting options

[SEM] sem reporting options -- Options affecting reporting of results

Syntax

sem paths ..., ... reporting_options

sem, reporting_options

reporting_options Description ------------------------------------------------------------------------- level(#) set confidence level; default is level(95) standardized display standardized coefficients and values coeflegend display coefficient legend nocnsreport do not display constraints nodescribe do not display variable classification table noheader do not display header above parameter table nofootnote do not display footnotes below parameter table notable do not display parameter tables nofvlabel display group values rather than value labels fvwrap(#) allow # lines when wrapping long value labels fvwrapon(style) apply style for wrapping long value labels; style may be word or width

byparm display results in a single table with rows arranged by parameter showginvariant report all estimated parameters -------------------------------------------------------------------------

Description

These options control how sem displays estimation results.

Options

level(#); see [R] estimation options.

standardized displays standardized values, that is, "beta" values for coefficients, correlations for covariances, and 1s for variances. Standardized values are obtained using model-fitted variances (Bollen 1989, 124-125). We recommend caution in the interpretation of standardized values, especially with multiple groups.

coeflegend displays the legend that reveals how to specify estimated coefficients in _b[] notation, which you are sometimes required to use when specifying postestimation commands.

nocnsreport suppresses the display of the constraints. Fixed-to-zero constraints that are automatically set by sem are not shown in the report to keep the output manageable.

nodescribe suppresses display of the variable classification table.

noheader suppresses the header above the parameter table, the display that reports the final log-likelihood value, number of observations, etc.

nofootnote suppresses the footnotes displayed below the parameter table.

notable suppresses the parameter table.

nofvlabel displays group values rather than value labels.

fvwrap(#) specifies how many lines to allow when long value labels must be wrapped. Labels requiring more than # lines are truncated. This option overrides the fvwrap setting; see [R] set showbaselevels.

fvwrapon(style) specifies whether value labels that wrap will break at word boundaries or break based on available space.

fvwrapon(word), the default, specifies that value labels break at word boundaries.

fvwrapon(width) specifies that value labels break based on available space.

This option overrides the fvwrapon setting; see [R] set showbaselevels.

byparm specifies that estimation results with multiple groups be reported in a single table with rows arranged by parameter. The default is to report results in separate tables for each group.

showginvariant specifies that each estimated parameter be reported in the parameter table. The default is to report each invariant parameter only once. This option is only effective with the byparm option.

Remarks

Any of the above options may be specified when you fit the model or when you redisplay results, which you do by specifying nothing but options after the sem command:

. sem (...) (...), ... (original output displayed)

. sem (output redisplayed)

. sem, standardized (standardized output displayed)

. sem, coeflegend (coefficient-name table displayed)

. sem (output redisplayed)

See [SEM] example 8 and [SEM] example 16.

Examples

Setup . webuse sem_2fmmby . sem (Peer -> peerrel1 peerrel2 peerrel3 peerrel4) (Par -> parrel1 parrel2 parrel3 parrel4), group(grade)

Display standardized coefficients . sem, standardized

Display coefficient legend . sem, coeflegend

Only display the parameter table . sem, nofootnote noheader nocnsreport

Report all estimated parameters . sem, showginvariant

Reference

Bollen, K. A. 1989. Structural Equations with Latent Variables. New York: Wiley.


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index