Function Reference: runstest

statistics: h = runstest (x)
statistics: h = runstest (x, v)
statistics: h = runstest (x, "ud")
statistics: h = runstest (…, Name, Value)
statistics: [h, pval, stats] = runstest (…)

Run test for randomness in the vector x.

h = runstest (x) calculates the number of runs of consecutive values above or below the mean of x and tests the null hypothesis that the values in the data vector x come in random order. h is 1 if the test rejects the null hypothesis at the 5% significance level, or 0 otherwise.

h = runstest (x, v) tests the null hypothesis based on the number of runs of consecutive values above or below the specified reference value v. Values exactly equal to v are omitted.

h = runstest (x, "ud") calculates the number of runs up or down and tests the null hypothesis that the values in the data vector x follow a trend. Too few runs indicate a trend, while too many runs indicate an oscillation. Values exactly equal to the preceding value are omitted.

h = runstest (…, Name, Value) specifies additional options to the above tests by one or more Name-Value pair arguments.

NameValue
"alpha"the significance level. Default is 0.05.
"method"a string specifying the method used to compute the p-value of the test. It can be either "exact" to use an exact algorithm, or "approximate" to use a normal approximation. The default is "exact" for runs above/below, and for runs up/down when the length of x is less than or equal to 50. When testing for runs up/down and the length of x is greater than 50, then the default is "approximate", and the "exact" method is not available.
"tail"a string specifying the alternative hypothesis
"both"two-tailed (default)
"left"left-tailed
"right"right-tailed

See also: signrank, signtest

Source Code: runstest