sm.tsa.acovf fails when both unbiased and fft are True #1187

Closed
kyleabeauchamp opened this Issue Nov 16, 2013 · 0 comments

Projects

None yet

1 participant

@kyleabeauchamp
Contributor

We probably need to add a note and an exception for when users specify both fft and unbiased. Alternatively, we could just make this parameter combo work.


import numpy as np
import statsmodels.api as sm

q = np.random.normal(size=100)
F = sm.tsa.acovf(q, demean=False, unbiased=True, fft=True)

--> 310         acov = np.fft.ifft(Frf*np.conjugate(Frf))[:nobs]/d
    311         return acov.real
    312     else:

ValueError: operands could not be broadcast together with shapes (100) (199) 

@kyleabeauchamp kyleabeauchamp added a commit to kyleabeauchamp/statsmodels that referenced this issue Nov 16, 2013
@kyleabeauchamp kyleabeauchamp Fix for issue #1187 858dc76
@josef-pkt josef-pkt closed this in cc04669 Dec 18, 2013
@PierreBdR PierreBdR pushed a commit to PierreBdR/statsmodels that referenced this issue Sep 2, 2014
@kyleabeauchamp @josef-pkt kyleabeauchamp + josef-pkt Fix for issue #1187 753d3f8
@PierreBdR PierreBdR pushed a commit to PierreBdR/statsmodels that referenced this issue Sep 2, 2014
@josef-pkt josef-pkt Merge branch 'fix_acovf_fft_1188' closes #1187 closes #1188 5cf7f95
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment