regression_ttest
statistics: h = regression_ttest (y, x)
statistics: [h, pval] = regression_ttest (y, x)
statistics: [h, pval, ci] = regression_ttest (y, x)
statistics: [h, pval, ci, stats] = regression_ttest (y, x)
statistics: […] = regression_ttest (y, x, Name, Value)
Perform a linear regression t-test.
h = regression_ttest (y, x) tests the null
hypothesis that the slope beta1 of a simple linear regression equals
0. The result is h = 0 if the null hypothesis cannot be rejected at
the 5% significance level, or h = 1 if the null hypothesis can be
rejected at the 5% level. y and x must be vectors of equal
length with finite real numbers.
The p-value of the test is returned in pval. A 100(1-alpha)%
confidence interval for beta1 is returned in ci. stats is
a structure containing the value of the test statistic (tstat),
the degrees of freedom (df), the slope coefficient (beta1),
and the intercept (beta0). Under the null, the test statistic
stats.tstat follows a T-distribution with
stats.df degrees of freedom.
[…] = regression_ttest (…, name, value)
specifies one or more of the following name/value pairs:
| Name | Value |
|---|---|
'alpha' | the significance level. Default is 0.05. |
'tail' | a string specifying the alternative hypothesis |
Source Code: regression_ttest
'both' | beta1 is not 0 (two-tailed, default) |
'left' | beta1 is less than 0 (left-tailed) |
'right' | beta1 is greater than 0 (right-tailed) |
Source Code: regression_ttest
See also: regression_ftest, regress, regress_gp
Source Code: regression_ttest