0

I'm using df['col1'].cov(df['col2']) to calculate the covariance between two columns in dataframe df. How can I get smth like p-value for this covariance value? Maybe there is smth similar to stats.pearsonr, which produces correlation coefficient and p-value?

DYZ
  • 55,249
  • 10
  • 64
  • 93
Ekaterina
  • 189
  • 1
  • 10
  • Related (not dup): [pandas columns correlation with statistical significance](https://stackoverflow.com/questions/25571882/pandas-columns-correlation-with-statistical-significance) – jpp Aug 28 '18 at 16:49
  • 2
    @jpp Not a duplicate at all. Scipy.stats has a function to calculate the p-value for correlation (mentioned in the answer), but it does not have a similar function for covariance. In fact [even R does not seem to have such function](https://stats.stackexchange.com/questions/48366/standard-errors-for-covariance-estimate-in-r). – DYZ Aug 28 '18 at 16:51

0 Answers0