Power of Test and Sample Size |
|
|
Modules in the group Power and Sample Size compute power of a test, required sample size an minimal difference of parameters that can be detected by the test. The tests support normal and binomial distribution. Inputs are significance level (or type I error) α, type of the test (one-sided or two-sided and theoretical (expected, specified) distribution parameter value. This parameter is the mean value for normal distribution, or probability for binomial distribution. Further, it is necessary to specify two of the following three numbers: Sample size, expected sample statistic and the power of the test 1 – β (β is the type II error). This module does not use any data from the data editor.
Tests supported:
- Normal distribution - t-test 1 sample
- Normal distribution - t-test 2 samples
- Binomial distribution - Chi2-test 1 sample
- Binomial distribution - Chi2-test 2 samples
Testing - Pdf manual
Examples:
Sample Output:
Power and sample size |
|
Normal dist., 1 sample |
|
Computation of sample size |
|
|
|
Task name : |
Power & Sample size |
|
|
Significance level |
0.05 |
Mean value M |
10 |
Expected mean X |
11 |
Type of test |
Two-sided |
Null hypothesis H0 |
X = M |
Alternative hypothesis HA |
X <> M |
Standard deviation |
2 |
Sample size |
31.39551878 |
Rounded sample size |
32 |
Power of test |
0.8 |
Power and sample size |
|
|
Normal dist., 2 samples |
|
|
Computation of sample size |
|
|
|
|
|
Task name : |
Sheet38 |
|
|
|
|
Significance level |
0.05 |
|
Expected mean X1 |
5 |
|
Expected mean X2 |
6 |
|
Type of test |
Two-sided |
|
Null hypothesis H0 |
X1 = X2 |
|
Alternative hypothesis HA |
X1 <> X2 |
|
Standard deviation 1 |
1 |
|
Standard deviation 2 |
2 |
|
Ratio of sizes N2/N1 |
1 |
|
Sample sizes N1, N2 |
39.24439873 |
39.24439873 |
Rounded sample sizes |
40 |
40 |
|