irt_me help file

Title

    irt_me --  Calculates marginal effects for the latent variable (Theta) after IRT

               models

General syntax

    irt_me [varlist] , [options]

Overview

    irt_me calculates marginal effects for the latent variable (theta) after an IRT

    model. The latent variable is the independent variable; the variables specifed in the

    varlist are the observed items which are the dependent variables in an IRT model. If

    no varlist is specified, irt_me calculates marginal effects for theta across all of

    the observed items.

    irt_me supports all models that can be estimated using the Stata irt command and also

    models for continuous and count items (regress, poisson, and nbreg). A mix of

    different item types is also allowed (e.g., a mix of binary and ordinal items).

        +---------------------------------+

    ----+ Required Option for gsem models +----------------------------------------------

    latent(string)

                  is required if gsem was used to fit the model of interest. This is the

                  name of the latent variable you wish to obtain marginal effects for. The

                  latent( ) option should not be used if the model was fit with the irt

                  command as irt automatically names the latent variable Theta.

        +---------+

    ----+ Options +----------------------------------------------------------------------

    model(string)

                  specifies the name of saved model estimates to use.  See estimates store

                  for saving model estimates. By default, irt_me will use the IRT/GSEM

                  estimates in memory. If the relevant model estimates are not in memory,

                  you must specify their name.

    decimals(#)   changes the number of decimal places reported for the statistics. The

                  default is 3. Any integer between 1 - 8 is allowed.

    start(#)      specifies the starting value for the prediction used in the calculation

                  of the marginal effect. The default is -0.5 for a default marginal effect

                  estimate of a centered +1 unit change.

    end(#)        specifies the ending value for the prediction used in the calculation of

                  the marginal effect. The default is 0.5 for a default marginal effect

                  estimate of a centered +1 unit change.

    range         calculates marginal effects across the trimmed range of the predicted

                  values of the latent variable theta. Predictions are made at the 1st

                  percentile of theta (start) and at the 99th percentile of theta (end)

    title(string)

                  changes the title of the table of results.  A default title is

                  automatically included.

    help          prints footnotes below the table describing what the columns in the table

                  represent.

Examples

    webuse masc1

    irt 2pl q1 q2 q3 q4 q5

    irt_me, help

    gsem (Theta -> q1 q2 q3 q4 q5, logit), var(Theta@1)

    irt_me, latent(Theta)

Authorship

    irt_me is written by Trenton D Mize (Department of Sociology & Advanced

    Methodologies, Purdue University).  Questions can be sent to tmize@purdue.edu