I am trying to predict a time series where every data point is a percentage value between 0 and 1. Most data points are either 1 and few below 0.5. In such a case what could be suitable data transformation or an algorithm that can be used for prediction purposes. The plot below shows the data that I have.

enter image description here


1 Answer 1


This might help : Beta Regression for time series analysis of bounded data, with application to Canada Google® flu trends

From the abstract : Bounded time series consisting of rates or proportions are often encountered in applications. This manuscript proposes a practical approach to analyze bounded time series.

And it comes with the GCMR package.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.