17.3.7.1 The One-Sample Proportion Test Dialog Box

1 Supporting Information
2 Results Log Output
3 Input Data Form
4 Input Data
5 Proportion Test
6 Test Methods
7 Power Analysis
8 Output Results

Supporting Information

To open the One-Sample Proportion Test Dialog:

With a worksheet active, click Statistics: Hypothesis Testing: One-Sample Proportion Test...

See Also:

Results Log Output

Results Log Output	Select to output results to the Results Log.

Input Data Form

Summarized

Perform the test using summary statistics that you enter into the dialog box manually.

Raw

Perform the test using a dataset composed of "success" or "failure" values. The dataset must contain no more than two distinct values.

Input Data

(Summarized)

Number of Success

The observed number of successes.

Sample Size

The total number of observations.

Input Data

(Raw)

Sample

Define a sample data range.

Success

The dataset value that denotes success.

Proportion Test

Test Proportion	The hypothetical proportion to be tested.
Null Hypothesis	The null hypothesis to be tested (Sample Proportion = Test Proportion).
Alternative Hypothesis	Options: Proportion <> Test Proportion A two-tailed proportion test that seeks to answer whether the sampled proportion = Test Proportion. Proportion > Test Proportion An upper-tailed proportion test that seeks to answer whether the sampled proportion is larger than the Test Proportion. Proportion < Test Proportion A lower-tailed proportion test that seeks to answer whether the sampled proportion is less than the hypothetical proportion .
Significance Level	The significance level of the test.
Confidence Interval(s)	Compute confidence interval for the true (population) proportion.
Confidence Level(s) in %	Specifies the confidence levels for which the confidence intervals will be computed. This option is only available when Confidence Interval(s) is selected.

Test Methods

Origin uses two methods for computing p values and confidence intervals for one-sample proportion tests (for documentation of Normal Approximation and Binomial test, see the algorithms page):

Normal Approximation	The Normal Approximation is always calculated. Generally gives a satisfactory result when successes is ≥ 10 and when sample size - successes is ≥ 10. The quality of the approximation tends to improve as sample size increases.
Binomial Test	Use Binomial Test.

Power Analysis

Actual Power	Compute the power of the test (the probability of rejecting the null hypothesis when it is false).
Significance Level	Only available when Hypothetical Power and/or Actual Power are checked. This is the significance level (alpha value) for power computation.
Hypothetical Power	Compute the power of the test at various sample sizes.
Hypothetical Sample Size(s)	Only available when Hypothetical Power is checked. Specify hypothetical sample size(s) for power computation.