help prtest, help prtestti dialogs: one-sample two-sample
two-sample, by()
immediate dialogs: one-sample two-sample
-------------------------------------------------------------------------------
Title
[R] prtest -- One- and two-sample tests of proportions
Syntax
One-sample test of proportion
prtest varname == #p [if] [in] [, level(#)]
Two-sample test of proportion
prtest varname1 == varname2 [if] [in] [, level(#)]
Two-group test of proportion
prtest varname [if] [in] , by(groupvar) [level(#)]
Immediate form of one-sample test of proportion
prtesti #obs1 #p1 #p2 [, level(#) count]
Immediate form of two-sample test of proportion
prtesti #obs1 #p1 #obs2 #p2 [, level(#) count]
by is allowed with prtest; see [D] by.
Menu
one-sample
Statistics > Summaries, tables, and tests > Classical tests of
hypotheses > One-sample proportion test
two-sample
Statistics > Summaries, tables, and tests > Classical tests of
hypotheses > Two-sample proportion test
two-group
Statistics > Summaries, tables, and tests > Classical tests of
hypotheses > Two-group proportion test
immediate command: one-sample
Statistics > Summaries, tables, and tests > Classical tests of
hypotheses > One-sample proportion calculator
immediate command: two-sample
Statistics > Summaries, tables, and tests > Classical tests of
hypotheses > Two-sample proportion calculator
Description
prtest performs tests on the equality of proportions using large-sample
statistics.
In the first form, prtest tests that varname has a proportion of #p. In
the second form, prtest tests that varname1 and varname2 have the same
proportion. In the third form, prtest tests that varname has the same
proportion within the two groups defined by groupvar.
prtesti is the immediate form of prtest; see immed.
The bitest command is a better version of the first form of prtest in
that it gives exact p-values. Researchers should use bitest when
possible, especially for small samples; see [R] bitest.
Options
+------+
----+ Main +-------------------------------------------------------------
by(groupvar) specifies a numeric variable that contains the group
information for a given observation. This variable must have only
two values. Do not confuse the by() option with the by prefix; both
may be specified.
level(#) specifies the confidence level, as a percentage, for confidence
intervals. The default is level(95) or as set by set level.
count specifies that integer counts instead of proportions be used in the
immediate forms of prtest. In the first syntax, prtesti expects that
#obs1 and #p1 are counts -- #p1 < #obs1 -- and #p2 is a proportion.
In the second syntax, prtesti expects that all four numbers are
integer counts, that #obs1 > #p1, and that #obs2 > #p2.
Examples
---------------------------------------------------------------------------
Setup
. sysuse auto
One-sample test of proportion
. prtest foreign==.4
---------------------------------------------------------------------------
Setup
. webuse cure
Two-sample test of proportion
. prtest cure1==cure2
---------------------------------------------------------------------------
Setup
. webuse cure2
cure has same proportion for males and females
. prtest cure, by(sex)
Immediate form of one-sample test of proportion
. prtesti 50 .52 .70
First two numbers are counts
. prtesti 30 4 .7, count
Immediate form of two-sample test of proportion
. prtesti 30 .4 45 .67
All numbers are counts
. prtesti 30 4 45 17, count
---------------------------------------------------------------------------
Saved results
prtest and prtesti save the following in r():
Scalars
r(z) z statistic
r(P_#) proportion for variable #
r(N_#) number of observations for variable #
Also see
Manual: [R] prtest
Help: [R] bitest, [MV] hotelling, [R] proportion, [R] ttest
