You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

96 lines
2.8 KiB
Plaintext

7 months ago
.-
help for ^reoprob^ (STB-59: sg158; STB-61: sg158.1)
.-
Random-effects ordered probit
-----------------------------
^reoprob^ depvar varlist [^if^ exp] [^in^ range] ^,^
[ ^i(^varname^)^ ^q^uadrat^(^#^)^ ^l^evel^(^#^)^ maximize_options ]
This command shares the features of all estimation commands; see help @est@.
To reset problem-size limits, see help @matsize@.
Description
-----------
^reoprob^ estimates a random-effects ordered probit model for panel datasets
using maximum likelihood estimation. The likelihood for each unit is
approximated by Gauss-Hermite quadrature.
Options
-------
^i(^varname^)^ specifies the variable corresponding to an independent unit
(e.g., a subject id). ^i(^varname^)^ is not optional.
^quadrat(^#^)^ specifies the number of points to use for Gaussian-Hermite
quadrature. It is optional, and the default is 12. Increasing this value
improves accuracy, but also increases computation time. Computation time
is roughly proportional to its value.
^level(^#^)^ specifies the confidence level, in percent, for confidence
intervals. The default is ^level(95)^ or as set by ^set level^.
maximize_options controls the maximization process and the display of
information; see [R] maximize. ^nolog^ suppresses the display of the
likelihood iterations. Use the ^trace^ option to view parameter
convergence. The ^ltol(^#^)^ and ^tol(^#^)^ option can be used to loosen
the convergence criterion (respectively 1e-7 and 1e-6 by default) during
specification searches. ^iter(^#^)^ specifies the maximum number of
iterations.
Examples
--------
. ^reoprob y x, i(id)^
. ^reoprob y x^
. ^reoprob y x, i(id) quad(24) nolog^
. ^reoprob y x, i(id) trace^
. ^reoprob^
Method
------
^reoprob^ uses the d1 method (analytic first derviatives) of Stata's ^ml^
commands. See Butler and Moffitt (1982) for details about using Gauss-Hermite
quadrature to approximate such integrals. Also see Green (2000) for
information on how to estimate a basic ordered probit model.
Author
------
Guillaume R. Frechette
Ohio State University
Department of Economics
410 Arps Hall
1945 North High Street
Columbus, OH 43210-1172
Tel: (614) 688-4140
Fax: (614) 292-4192
e-mail: frechette.6@@osu.edu
http://www.econ.ohio-state.edu/frechette/
Reference
---------
Butler, J.S. and R. Moffitt. 1982. A computationally efficient
quadrature procedure for the one-factor multinomial probit model.
Econometrica 50: 761-764.
Green, W. H. 2000. Econometric Analysis. Prentice Hall, New Jersey.
pp. 875-878.
Also see
--------
Manual: ^[R] xt, [R] xtprobit, [R] maximize, [R] oprobit^
On-line: help for @xt@, @xtreg@