I have time series data for minutes interval. But due to some noise i have to remove some rows from data. Now, I have data with some missing time stamp.
What should i do for forecasting in this case?
$\begingroup$
$\endgroup$
3
-
$\begingroup$ You haven't said how you intend to forecast. The answer could be do nothing or replace the missing rows depending on the approach v $\endgroup$– fswingsMay 15 '21 at 14:04
-
$\begingroup$ Hello @fswings, i want to use arima model for forcasting, i already have data for all minutes, but due to some noise i have removed it, how can i replace them? $\endgroup$– Jay TilalaJun 4 '21 at 3:45
-
$\begingroup$ If you intend to use ARIMA, then don't remove any of the data and construct your model. If you want to remove any data which you know to be extremes the for your analysis you can use the average of adjacent records and it won't affect the analysis that much. $\endgroup$– fswingsJun 4 '21 at 17:53
Add a comment
|