statsmodels.tools.eval_measures.iqr¶
-
statsmodels.tools.eval_measures.
iqr
(x1, x2, axis=0)[source]¶ interquartile range of error
rounded index, no interpolations
this could use newer numpy function instead
- Parameters
- x1, x2array_like
The performance measure depends on the difference between these two arrays.
- axis
int
axis along which the summary statistic is calculated
- Returns
Notes
If
x1
andx2
have different shapes, then they need to broadcast.This uses
numpy.asarray
to convert the input, in contrast to the other functions in this category.