-------------------------------------------------------------------------------
help for wtd
-------------------------------------------------------------------------------

Analysis of Waiting Time Distribution

    wtd

Description

    The term wtd refers to Waiting Time Distribution data and the commands
    for analyzing them, all of which begins with the letters wtd. For a
    description of the Waiting Time Distribution concept, please refer to
    Støvring and Vach (2005).  Estimation of prevalence and incidence based
    on occurrence of health-related events.  Stat Med 2005; 24:3139-54.

    In short, the concept of the Waiting Time Distribution allows estimation
    of incidence and prevalence of for example drug use, based exclusively on
    occurrence of health-related events, in this case individual drug
    redemptions from pharmacies. Another example is incidence and prevalence
    of hypertension treatment based on occurrence of hypertension related
    consultations with physicians.

    Consider for example redemption of oral antidiabetics. This class of
    drugs is known to be a good indicator for treatment of type II diabetes.
    The approach of the Waiting Time Distribution can then be used to
    estimate the prevalence and incidence of treated type II diabetes in a
    given population. The procedure can allow for information on migration
    and survival if such data are available along with data on individual
    redemptions of oral antidiabetics. The Waiting Time Distribution has a
    characteristic shape which arise from only considering the first event
    for each individual in a given time window.

    The first step to analyzing Waiting Time Distribution data is to wtdset
    it. Then you can use any of the other wtd commands. This is analogous to
    the st commands for survival time data, see help st. The wtd commands are

        wtdset     Declare data to be Waiting Time Distribution data.

        wtd        Short descriptive table of the wtd data currently in
                        memory, cf. help wtdset.

        wtdml      Perform Maximum-likelihood estimation.

        wtddiag    Diagnostic plots of observed waiting time distribution

        wtdq       Q-Q-plot of fitted versus empirical Waiting Time
                        Distribution.


Remarks

    For a detailed description of the Waiting Time Distribution concept,
    please refer to

        Støvring and Vach (2005). Estimation of prevalence and incidence
        based on occurrence of health-related events.  Stat Med 2005;
        24:3139-54.

Author

    H. Støvring, Research Unit of General Practice, University of Southern
    Denmark.  Please email hstovring@health.sdu.dk if you have comments,
    questions or observe any problems.


Also see


On-line:  help for wtdset; st, ml