.-
help for ^confsvy^
.-
Assessing confounding effects in survey studies
----------------------------------------------------------------
^confsvy^ yvar xvar, [^con^(covlist) ^cat^(covlist) ^nog^raph
^b^ackward ^det^ail ^l^evel(#) ^co^ef graph_options]
^confsvy^ calculates the change in effect estimates such as odds ratio,
after adjusting for a potential confounder using either "forward
selection" or "backward deletion" strategies.
^confsvy^ also calculates and graphs adjusted effect measures and
their confidence intervals. The order of variables being selected is
based on the "importance" (magnitude) of "change in estimate".
Variables required
-------------------
^yvar^ -- dependent variable, binary variable for logistic or poisson
regression; survival time variable for Cox proportional hazards
model.
^xvar^ -- exposure of interest
Options
--------
^con^ -- list of potential continuous confounding variables.
^cat^ -- list of potential categorical confouding variables.
^nog^graph -- suppresses graphs. By default, a graph is given.
^b^ackward -- specifies selection strategy as "back deletion method",
otherwise, "forward selection" method is default.
^co^ef -- graphs regression coefficients instead of effect estimates
for graphs.
^det^ail -- gives details at each step. Default only gives a summary.
^l^evel(#) -- specifies the confidence level, in percent, for
calculation of confidence intervals (default=95%)
^graph_options^ -- some options with ^graph^ are allowed; see help
@graph@.
Examples
---------
. ^confsvy dead ab_uria, con(sbp weight) cat(sex agegroup)^
Calculates and graphs crude and adjusted odds ratios using
^svylogit^ with a forward selection approach.
. ^confsvy dead ab_uria, con(weight sbp) cat(sex agegroup) detail^
Calculates and graphs crude and adjusted odds ratios using
^svylogit^. Details in each step are given.
Author
-------
Zhiqiang Wang
Menzies School of Health Research, Darwin, Australia
wang@@menzies.su.edu.au