------------------------------------------------------------------------------- help forqfrplot-------------------------------------------------------------------------------

Quantile plots of fitted and residuals

qfrplot[plottype] [,super[normal|gaussian]combine(graph_options)fplot(qplot_options)rplot(qplot_options)graph_options]

Description

qfrplotplots quantile plots of fitted values, minus their mean, and residuals from the previous estimation command. Fitted values are whateverpredictproduces by default and residuals are whateverpredict,resproduces. Comparing the distributions gives an overview of their variability and some idea of their fine structure. By default plots are side-by-side.The plot type may be one of eight twoway types, namely,

area,bar,connected,dot,dropline,line,scatterorspike.scatteris the default.The plot is restricted to the estimation sample.

qplot(SJ 4(1) 2004) must be installed.

RemarksA quantile plot shows ordered values versus the so-called plotting positions, or if the

normalorgaussianoption is specified, the corresponding quantiles of a standard normal (Gaussian) distribution. For n values ordered minimum first, the plotting positions are (i - a) / (n - 2a + 1) for i = 1, ..., n, where a is by default 0.5.W.S. Cleveland in

Visualizing data(Hobart Press, Summit, NJ, 1993) gives many side-by-side quantile plots of fit and residuals, which he calls "residual-fit spread plots". See example on p.41. However, he also uses this term for side-by-side time series plots of fit and residuals. See example on p.157. The command name and description here emphasise the use of a quantile plot.

Options

superspecifies that plots are to be superimposed, not side-by-side. Ifsuperis specified, usecombine()to control other characteristics of the combined plot.

normalspecifies that standard normal quantiles should be shown instead of plotting positions.gaussianis an exact synonym except that by default the textGaussianwill appear within the axis title, rather thannormal.

fplot()specifies options of qplot controlling the quantile plot of fitted values.fplot()is irrelevant ifsuperis also specified.

rplot()specifies options of qplot controlling the quantile plot of residuals.rplot()is irrelevant ifsuperis also specified.

combine()specifies options of qplot controlling the quantile plot of fitted and residuals, wheneversuperis also specified; and options of graph combine otherwise.

graph_optionsare other graph options affecting the combined graph.

Examples

. use auto. regress mpg weight. qfrplot

. glm mpg weight, link(power -1). qfrplot, norm fplot(yla(,ang(h)))

AuthorNicholas J. Cox, University of Durham, U.K. n.j.cox@durham.ac.uk

Also see