-------------------------------------------------------------------------------
help for raschpower                       Jean-Benoit Hardouin, Myriam Blanchin
-------------------------------------------------------------------------------

Estimation of the power of the Wald test in order to compare the means of the l
> atent trait in two groups of individuals

        raschpower [, n0(#) n1(#) gamma(#) var(#) d(matrix) method(method)]


Description

    raschpower allows estimating the power of the Wald test comparing the
        means of two groups of patients in the context of the Rasch model or
        the partial-credit model. The estimation is based on the estimation
        of the variance of the difference of the means based on the
        Cramer-Rao bound.

Options

    n0 and n1 indicates the numbers of individuals in the two groups [100 by
        default].

    gamma indicates the group effect (difference between the two means) [0.5
        by default].

    var indicates the value of the variance of the latent trait [1 by
        default].

    d is a matrix containing the item parameters [one row per item, one
        column per positive modality - (-1.151, -0.987\-0.615, -0.325\-0.184,
        -0.043\0.246, 0.554\0.782, 1.724) by default].

    method(method) indicates the method for constructing data. (method) may
        be GH, MEAN, MEAN+GH or POPULATION+GH [default is method(GH) if
        number of patterns<500, method(MEAN+GH) if 500<=number of
        patterns<10000, method(MEAN) if 10000<=number of patterns<1000000,
        method(POPULATION+GH) otherwise].

        GH: The probability of all possible response patterns is estimated by
              Gauss-Hermite quadratures.

        MEAN: The mean of the latent trait for each group is used instead of
              Gauss-Hermite quadratures.

        MEAN+GH: In a first step, the MEAN method is used to determine the
              most probable patterns. In a second step, the probability of
              response patterns is estimated by Gauss-Hermite quadratures on
              the most probable patterns.

        POPULATION+GH: The most frequent response patterns are selected from
              a simulated population of 1,000,000 of individuals. The
              probability of the selected response patterns is estimated by
              Gauss-Hermite quadratures.

Example

        
    . raschpower

        
    . raschpower, n0(200) n1(200) gamma(0.4) var(1.3)

        
    . matrix diff=(-1.47\-0.97\-.23\-0.12\0.02\0.1)
        
    . raschpower, n0(127) n1(134) gamma(0.23) d(diff) var(2.58)

References

        
    Hardouin J.B., Amri S., Feddag M., Sébille V. (2012) Towards Power And
        Sample Size Calculations For The Comparison Of Two Groups Of Patients
        With Item Response Theory Models. Statistics in Medicine, 31(11):
        1277-1290.

        
Author

    Jean-Benoit Hardouin, PhD, assistant professor
    Myriam Blanchin, PhD, research assistant
    EA4275 "Biostatistics, Pharmacoepidemiology and Subjective Measures in
        Health Sciences"
    University of Nantes - Faculty of Pharmaceutical Sciences
    1, rue Gaston Veil - BP 53508
    44035 Nantes Cedex 1 - FRANCE
    Emails:  jean-benoit.hardouin@univ-nantes.fr
             myriam.blanchin@univ-nantes.fr