propind: Compute power for Tests of Two Independent Proportions Takes...

Description Usage Arguments Value Examples

View source: R/propind.R

Description

Compute power for Tests of Two Independent Proportions Takes phi, degrees of freedom, and a range of sample sizes. Alpha is .05 by default, alternative values may be entered by user This test uses what is sometimes called the chi-square test for comparing proportions

Usage

1
propind(p1, p2, nlow, nhigh, nratio = 0.5, alpha = 0.05, tails = 2, by = 1)

Arguments

p1

expected proportion Group 1

p2

expected proportion Group 2

nlow

starting sample size

nhigh

ending sample size

nratio

ratio of sample size of first group to second (default is .5 for equally sized groups)

alpha

Type I error (default is .05)

tails

number of tails for test (default is 2)

by

Incremental increase in sample (e.g. nlow = 10, nhigh = 24, by = 2, produces estimates of 10, 12, and 14)

Value

Power for Tests of Two Independent Proportions

Examples

1
propind(p1=.62, p2=.55,nlow=200,nhigh=2500, by=100,nratio=.2)

Example output

    n1   n2  Power
1   40  160 0.1239
2   60  240 0.1648
3   80  320 0.2054
4  100  400 0.2457
5  120  480 0.2855
6  140  560 0.3245
7  160  640 0.3627
8  180  720 0.3999
9  200  800 0.4359
10 220  880 0.4707
11 240  960 0.5041
12 260 1040 0.5362
13 280 1120 0.5668
14 300 1200 0.5960
15 320 1280 0.6237
16 340 1360 0.6500
17 360 1440 0.6748
18 380 1520 0.6982
19 400 1600 0.7203
20 420 1680 0.7410
21 440 1760 0.7605
22 460 1840 0.7787
23 480 1920 0.7958
24 500 2000 0.8117

pwr2ppl documentation built on April 4, 2021, 9:06 a.m.