Binomial Test Options (One-Sample Nonparametric Tests)
The binomial test is intended for flag fields (categorical fields with only two categories), but is applied to all fields by using rules for defining "success".
Hypothesized proportion. This specifies the expected proportion of records defined as "successes", or p. Specify a value greater than 0 and less than 1. The default is 0.5.
Confidence Interval. The following methods for computing confidence intervals for binary data are available:
- Clopper-Pearson (exact). An exact interval based on the cumulative binomial distribution.
- Jeffreys. A Bayesian interval based on the posterior distribution of p using the Jeffreys prior.
- Likelihood ratio. An interval based on the likelihood function for p.
Define Success for Categorical Fields. This specifies how "success", the data value(s) tested against the hypothesized proportion, is defined for categorical fields.
- Use first category found in data performs the binomial test using the first value found in the sample to define "success". This option is only applicable to nominal or ordinal fields with only two values; all other categorical fields specified on the Fields tab where this option is used will not be tested. This is the default.
- Specify success values performs the binomial test using the specified list of values to define "success". Specify a list of string or numeric values. The values in the list do not need to be present in the sample.
Define Success for Continuous Fields. This specifies how "success", the data value(s) tested against the test value, is defined for continuous fields. Success is defined as values equal to or less than a cut point.
- Sample midpoint sets the cut point at the average of the minimum and maximum values.
- Custom cutpoint allows you to specify a value for the cut point.