help fraclogit-------------------------------------------------------------------------------

Title

fraclogit-- Fractional logit model as implemented in Wedderburn (1974) and generalized by McCullagh (1983).

Syntaxfraclogitdepvarindepvars[if] [in] [weight], [options]

optionsDescription -------------------------------------------------------------------------eformodds ratio form resultsDescription

fraclogitcarries out a quasi-likelihood estimation of a fractional logit model as described Wedderburn (1974) and generalized by McCullah (1983). The dependent variable forfraclogitis assumed to a proportion in the (0,1) interval. This model was rediscovered two decades later by Papke and Wooldridge (1996).

Example (from Wedderburn 1974). use wedderburn, clear . fraclogit yield i.site i.variety . margins variety

Estimation Details

fraclogituses iteratively reweighted least squares in repeated calls toglm.

Saved Results

fraclogitsaves the following ine():Scalars

e(N)number of observationse(df)number of model parameterse(dev)deviancee(rmse)root mse (dispersion)Macros

e(depvar)name of dependent variable Matricese(b)1 XKvector of estimatese(V)KXKvariance-covariance matrixFunctions

e(sample)marks estimation sample

AuthorsDaniel A. Powers, University of Texas at Austin(dpowers@austin.utexas.edu).

ReferencesMcCullagh, P. (1983) "Quasi-Likelihood Functions,"

Annals of Statistics. Vol. 11, No. 1, pp. 59-67.Papke, L.E. and J.W. Wooldridge (1996) "Econometric Methods for Fractional Response Variables With an Application to 401 (K) Plan Participation Rates,"

Journal of Applied Econometrics. Vol 11, No. 6, pp. 619-632.Wedderburn, R.M.W. (1974) "Quasi-Likelihood Functions, Generalized Linear Models, and the Gauss-Newton Method,"

Biometrika, Vol. 61, No. 3, pp. 439-447.

Also see