{smcl}
{* *! version 2.0.1 16dec2015}{...}
{cmd:help msdthaz}
{hline}
{title:Title}
{p2colset 5 16 16 2}{...}
{p2col:{hi:msdthaz} {hline 2}}Multiply-specified discrete-time event history analysis{p_end}
{p2colreset}{...}
{title:Syntax}
{p 8 18 2}
{cmd:msdthaz}
{it:using filename}
[{cmd:,} {it:options}]
{synoptset 28 tabbed}{...}
{synopthdr}
{synoptline}
{syntab:Model}
{synopt :{opt tp:ar(#)}}select alternative parameterizations of time{p_end}
{synopt :{opth l:ink(msdthaz##linkname:linkname)}}link function; default is logit hazard{p_end}
{syntab:SE/Robust}
{synopt :{opth clus:ter(varname)}}adjust standard errors for intragroup
correlation{p_end}
{syntab:Reporting}
{synopt :{opt base:line}}include baseline estimates{p_end}
{synopt :{opt m:odel}}output model estimate{p_end}
{synopt :{opt level(#)}}set confidence level; default is {cmd:level(95)}{p_end}
{syntab:Graph options}
{synopt :{opt gr:aph(#)}}conditional hazard, survival, or cumulative incidence curves{p_end}
{syntab:Miscellaneous}
{synopt :{opt copyleft}}display license information{p_end}
{synoptline}
{p2colreset}{...}
{marker linkname}{...}
{synoptset 23}{...}
{synopthdr :linkname}
{synoptline}
{synopt :{opt logit}}logit hazard{p_end}
{synopt :{opt probit}}probit hazard{p_end}
{synopt :{opt cloglog}}complimentary log log hazard{p_end}
{synoptline}
{p2colreset}{...}
{p 4 6 2}
{opt fweights}, {opt iweights}, and {opt pweights} are allowed; see {help weight}.
{title:Description}
{pstd}
{cmd:msdthaz} uses {help dthaz:dthaz} to perform discrete time analyses with
multiply-specified models, returning the matrix e(MSHazard) that contains
conditional hazard and survival probabilities for all specifications of a given
model. The model is estimated once, and probabilities for different specifications
of that model are calculated thereafter. A strength of {cmd:msdthaz} is that
multiple conditional hazard or survival curves may be overlaid on the same graph.
{pstd}
The required {it:using filename} statement directs the program to an arbitrarily
named ASCII text file containing the predictor variable names and specification
values desired by the user. The first line of this file must contain the
predictor variable names, separated by spaces. Each line thereafter contains
exactly one set of comma or space separated specified values for these
variables. In this way the effects of predictors upon conditional hazard and
survival probabilities may be evaluated. The discrete time model to be
estimated is specified in the options as per {help dthaz:dthaz}. Because {cmd:msdthaz} obtains
its specified values from the file, the {cmd:specify()} option cannot be used with
{cmd:msdthaz}.
{pstd}
{cmd:msdthaz} accepts the same arguments as {help dthaz:dthaz}, excepting {help grtwoway:grtwoway}
options which the program will not accept.
{title:Options}
{dlgtab:Model}
{phang}{cmd:{ul on}tp{ul off}ar(}{it:#}{cmd:)} selects alternative
parameterizations of time. Such time parameterizations allow a parsimonious
smoothing of the effects of time, and are as follows:
{p 5 8}-1 Fully discrete time parameterization. This setting is the default, and
reflects unique effects of time for each period.
{p 6 8}0 Constant time parameterization. This model constrains the effect of time to
be constant across all periods. The model includes a prespecified constant
term, is used in the following models, and permits model nesting.
{p 6 8}N Polynomial time parameterization. This model constrains the effect of
time as a polynomial function of order N. If the representation of time is
over-specified (i.e. has more predictors than the number of periods in the dataset,
or than the number the analysis has been truncated to) then the user will be warned
and the parameterization will be reset to its maximum. Lower order models nest
within higher order ones. N > 0.
{p 5 8}-2 Root time parameterization. This model constrains the effect of time as a
square-root function of period (plus constant plus linear terms)
{phang}{cmd:{ul on}l{ul off}ink(}{it:linkname}{cmd:)} switches between different models of the
hazard function: logit, probit or complimentary log log hazards. The default is the
logit hazard model. See {help dthaz:dthaz} for more details.
{dlgtab:SE/Robust}
{phang}{cmd:{ul on}clus{ul off}ter(}{it:varname}{cmd:)} adjusts the standard errors
of the estimates for person-level (between person) variance in repeated measures
designs by specifying the {it:id} variable used to construct the person-period
dataset.
{dlgtab:Reporting}
{phang}{cmd:{ul on}base{ul off}line} includes baseline (i.e. unconditional)
hazard and survival probabilities and graphs in the output.
{phang}{cmd:{ul on}m{ul off}odel} displays the estimated model in the output.
{phang}
{opt level(#)}; see {helpb estimation options##level():[R] estimation options}.
{dlgtab:Graph options}
{phang}{cmd:{ul on}gr{ul off}aph(}{it:#}{cmd:)} graphs conditional hazard
probabilities (1), survival probabilities (2), both (3) or (4) cumulative
incidence probabilities (i.e. 1 - survival) against discrete time periods.
Graphing options available to {help graph_twoway:graph_twoway} are available. The default
setting is no graph. Different colors are automatically assigned to each line.
{dlgtab:Miscellaneous}
{phang}{cmd:copyleft} {cmd:msdthaz} is free software, licensed under the GPL. The {cmd:copyleft} option displays
the copying permission statement for {cmd:msdthaz}. The full license can be obtained
by typing:
{p 12 8 2}
{inp: . net describe dthaz, from (http://www.alexisdinno.com/stata)}
{p 4 8 2}
and clicking on the {net "describe dthaz, from (http://www.alexisdinno.com/stata)":click here to get} link for the ancillary file.
{title:Examples}
The following example illustrates the specification plaint text file format,
with the first line containing variable names separated by spaces, and
subsequent four lines containing bespoke values for each variable:
{col 5}female age
{col 5}0 20
{col 5}1 20
{col 5}0 30
{col 5}1 30
{hline}
{p 4 8}{inp:. msdthaz using ":Path:myfile"}{p_end}
{hline}
{p 4 8}{inp:. msdthaz using ":Path:myfile" truncate(6)}{p_end}
{hline}
{p 4 8}{inp:. msdthaz using ":Path:myfile" link(cloglog) model tp(3)}{p_end}
{hline}
{title:Author}
Alexis Dinno
Portland State University
alexis dot dinno at pdx dot edu
{title:Saved results}
{pstd}
{cmd:msdthaz} returns {cmd:e(MSHazard)} with period and each of the hazard and
survival probabilities for each specified prediction (including baseline if that
option is set).
{title:Also See}
{psee}
{space 2}Help: {help dthaz:dthaz}, {help prsnperd:prsnperd}