# Does ARIMA assume evenly-spaced data in statsmodels?

I've read that ARIMA assumes that endogenous input array is evenly spaced. If that is the case, then what is the point of the dates parameter in statsmodels.tsa.ARIMA(), which seems like it is there to support irregularly spaced data? Also, what are the assumptions for the optional exogenous arrays, need these be spaced in the exact same way as the endogenous?

• To add to @AlaskaRon's answer, the dates parameter might not mean much; perhaps it is useful when plotting as it helps create relevant scale of $x$ axis. It does not mean the function supports irregularly spaced data (although I do not work with Python, so I cannot fully guarantee this is the case). – Richard Hardy Nov 24 '15 at 17:44
• dates are also used to allow users to select time periods for prediction or forecasting using dates instead of indices. – Josef Nov 26 '15 at 14:32
• The only application of irregular time series I know is in "nowcasting" in macroeconomics. They use statespace models for this, as far as I know. Although the new statespace models in statsmodels allow for missing values, I don't think irregular time periods would work out of the box. – Josef Nov 26 '15 at 14:35