search

0todd0000 / spm1d

One-Dimensional Statistical Parametric Mapping in Python
GNU General Public License v3.0
61 stars 21 forks source link

Non-parametric and normality tests in SPM #129

Closed gabrielmoisan closed 4 years ago

gabrielmoisan commented 4 years ago

Hi Todd, Do you have a list of all the non-parametric and normality tests that can implemented in SPM? For example ANOVA1rm=permutation test (Nichols and Holmes 2002). I'd like to know for the following, but a complete list could help others:

Non-parametric equivalent: -dependent and independent t tests -One way Anova -Hotelling's paired -nonparam.hotellings2

Normality tests: -dependent and independent t tests -One way Anova -Anova1rm

Thanks again Todd, Gabriel

0todd0000 commented 4 years ago

Hi Gabriel,

Nonparametric and normality tests are supported for all tests in spm1d.stats.

So if you have run a test called spm1d.stats.testname, there are corresponding nonparametric and normality tests called:

All nonparametric tests use permutation.

The normality tests use either the D'Agostino-Pearson K2 test (normality.k2) or the Shapiro-Wilks statistic (normality.sw). Both k2 and sw procedures are corrected for arbitrary one-dimensional domains using random field theory.

Todd

gabrielmoisan commented 4 years ago

Thanks Todd!