Why should I use a 1-sample sign test?

To perform this test, select Stat > Nonparametrics > 1-Sample Sign.

Use the 1-sample sign test to estimate the population median and compare it to a target or reference value. Using this test, you can:
  • Determine whether the median of a group differs from a specified value.
  • Calculate a range of values that is likely to include the population median.

The 1-sample sign test is a nonparametric alternative of the 1-sample t-test because it does not require the data to come from a normally distributed population, as the t-test does. Furthermore, the 1-sample sign test does not make assumptions about population symmetry.

For example, a consultant for a large company analyzes its payroll to determine whether the company's median salary differs from the industry average of $45,000. Because the data are nonnormal and asymmetric, the consultant chooses the nonparametric 1-sample sign test.

For 1-Sample Sign, the hypotheses are:
Null hypothesis
H0: η = η0 The population median (η) equals the hypothesized median (η0).
Alternative hypothesis
Choose one:
H1: η ≠ η0 The population median (η) differs from the hypothesized median (η0).
H1: η > η0 The population median (η) is greater than the hypothesized median (η0).
H1: η < η0 The population median (η) is less than the hypothesized median (η0).
By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy