Basically, I have two timestamped datasets.I DID spend lot of time searching for an answer without anything convincing.

The first dataset is of continuous variables. It is under this format:

Timestamp            P1     P2    P3     P4
14:47 15/09/2016     340     364   329    0.2
15:18 15/09/2016     366      365   301   0.5

The other is a history of signifcant events and their timestamps:

Timestamp                    Event
14:47:24 15/09/2016         E1,E3
14:48:15 15/09/2016         E2
15:37:02 15/09/2016         E5

What I want to do is to identify implicit relations between events appearance and changes in the variables values.For this purpose, I thought of using the correlation ration but I am not sure it is suited for this kind of problems .

Do you know other measures that are suitable for this problem?


Create a single dataset out of this, by joining both the datasets on the time. Now build a multi-class logistic/machine learning model to understand the impact of the variables p1-p4(independent variables) on the event type(target)

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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