help for ppplot

P-P plots

ppplot plottype varname [weight] [if exp] [in range] , by(byvar) [ missing reference(#) graph_options ]

ppplot plottype varlist [if exp] [in range] [, graph_options ]


ppplot produces a P-P (probability-probability) plot of the cumulative distribution functions of one or more groups or variables against that of a reference group or variable, for the same sets of observed values. By default the reference group is the last variable named, or, with a single variable, that defined by the highest value of byvar.

For more than one variable in varlist, only observations with all values of varlist present are shown.

The plot may be one of eight twoway types, namely, area, bar, connected, dot, dropline, line, scatter or spike. The plottype must be specified.

fweights and aweights may be specified.


by() specifies that groups are defined by the distinct values of a single variable byvar. by() is only allowed with a single varname.

missing, used only with by(), permits the use of non-missing values of varname corresponding to missing values for the variable named by by(). The default is to ignore such values.

reference(), used only with by(), specifies a reference group as a value of byvar. By default, the highest value of byvar in the data specified defines the reference group.

graph_options refers to options of graph appropriate to the plottype specified.


. ppplot connected mpg, by(foreign) . ppplot connected mpg, by(foreign) ref(0) . ppplot connected mpg, by(foreign) plot(function y = x, clp(dash)) . ppplot connected width length

To sample all possible plottypes:

. foreach t in area bar connected dot dropline line scatter spike { . ppplot `t' mpg, by(foreign) . }

Some tuning may be desirable, for example::

. ppplot bar mpg, by(foreign) bartype(spanning) base(0)


Nicholas J. Cox, University of Durham n.j.cox@durham.ac.uk

Also see

On-line: help for graph, cumul, distplot (if installed)

Manual: [G] graph, [R] cumul, [R] diagnostic plots