help lbpower
-------------------------------------------------------------------------------

Title


    lbpower --    Calculate approximate power (or sample size) for
                   longitudinal studies with binary response and two equally
                   sized treatment groups


Syntax

        lbpower , nrep(#) dur(#) corrjk(#) dif(#) alpha(#) [ power(numlist)
           nsize(#) unilateral ]


Description

    lbpower Approximates power (or sample size) for longitudinal studies with
    a binary response and two treatment groups with equal size. It should be
    used if the log odds can be assumed linear, that is when response
    probabilities are in the range of 0.2 to 0.8.  This formulation also
    assumes a constant correlation between repeated measurements. Note that
    this is just an approximation and should be applied with care.


Options

    nrep(#) Number of repeated mesurements.

    dur(#) Duration of the study.

    corrjk(#) Correlation between repeated measurements.

    dif(#) Difference in the change of response probabilites between groups
        (from begining to the end of the study).

    alpha(#) Significance level.

    power(numlist) Power, sample size is calculated.

    nsize(#) Sample size, calculate power.

    unilateral(#) Specify if the test is one sided

    Either power or nsize must be specified


Example

    Suppose that subjects are randomly assigned to receive any of two
    different suplements on a daily basis. There is no placebo for ethical
    reasons but in other contexts may be the case. The duration of the study
    is two years and five measurements will be taken. The researchers would
    like to detect treatment group differences in the prevalence of anemia of
    at least 6% per year, that is, 12% in the course of the whole study. The
    baseline prevalence in this population is about 45% so there is no
    problem with the linearity assumption for the log odds. Correlation
    between measurements is assumed to be 0.6


    Calculate sample size for power values between 0.7 and 0.9 :

    lbpower, nrep(5) dur(2) corrjk(0.6) dif(0.12) alpha(0.05)
        power(0.7(.05)0.9)

    Calculate power for a sample size of 140 per group:

    lbpower, nrep(5) dur(2) corrjk(0.6) dif(0.12) alpha(0.05) nsize(140)

    Calculate sample size if a power of 80% and a difference of 15% in the
    change of prevalences (from the beginning to the end of the study) are
    considered:

    lbpower, nrep(5) dur(2) corrjk(0.6) dif(0.15) alpha(0.05) power(0.8)


Saved results

    If power is provided, the sample size per group is saved as scalar in
    r(N1). In case a list of power values is given, each sample size value is
    stored in r(N1), r(N2), ...

    If sample size is specified, power is saved as scalar in r(power)


Author

    Amado David Quezada Sánchez
    Center for Research in Nutrition and Health
    National Institute of Public Health - Mexico (INSP)
    Email amado.quezada@insp.mx

Reference

    Fitzmaurice/Laird/Ware (2004) Applied Longitudinal Analysis, 411-413.