15.12.2012 Views

scipy tutorial - Baustatik-Info-Server

scipy tutorial - Baustatik-Info-Server

scipy tutorial - Baustatik-Info-Server

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Parameters<br />

data : sequence<br />

Input data<br />

skew(a, axis=0, bias=True)<br />

Computes the skewness of a data set.<br />

SciPy Reference Guide, Release 0.8.dev<br />

axis<br />

[{0, int} optional] Axis along which to compute. If None, the computation is<br />

performed on a flat version of the array.<br />

For normally distributed data, the skewness should be about 0. A skewness value > 0 means that there is more<br />

weight in the left tail of the distribution. The function skewtest() can be used to determine if the skewness value<br />

is close enough to 0, statistically speaking.<br />

Parameters<br />

a : array<br />

axis : int or None<br />

bias : bool<br />

If False, then the calculations are corrected for statistical bias.<br />

Returns<br />

The skewness of values along an axis, returning 0 where all values are :<br />

References<br />

equal. :<br />

[CRCProbStat2000] Section 2.2.24.1<br />

[CRCProbStat2000]<br />

skewtest(a, axis=0)<br />

Tests whether the skew is different from the normal distribution.<br />

This function tests the null hypothesis that the skewness of the population that the sample was drawn from is the<br />

same as that of a corresponding normal distribution.<br />

Notes<br />

Parameters<br />

a : array<br />

axis : int or None<br />

Returns<br />

p-value : float<br />

a 2-sided p-value for the hypothesis test<br />

The sample size should be at least 8.<br />

spearmanr(x, y, use_ties=True)<br />

Calculates a Spearman rank-order correlation coefficient and the p-value<br />

to test for non-correlation.<br />

The Spearman correlation is a nonparametric measure of the linear relationship between two datasets.<br />

Unlike the Pearson correlation, the Spearman correlation does not assume that both datasets are normally<br />

3.18. Statistical functions (<strong>scipy</strong>.stats) 685

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!