Let's say we have a large dataset with several samples over time. I'm looking for an automated way to find correlations over a specific time period. For example, in cycles, we might observe that when one set increases, the other decreases. This is a rough observation made by "eye". I'm wondering if there is any method, program, or formula in Excel that can calculate correlation such as between June and July there is x% positive correlation, on November 22 the correlation is x% etc?
. I appreciate any hints you can provide.
- 1Some sample data would be quite helpfuljkpieterse– jkpieterse2024-08-08 11:41:15 +00:00Commented Aug 8, 2024 at 11:41
- Also an explanation as to why only the two circled areas are considered as having correlation, the same could be said of the entire June 22 to July 23 period and the spike around Oct 23cybernetic.nomad– cybernetic.nomad2024-08-08 12:55:39 +00:00Commented Aug 8, 2024 at 12:55
- @jkpieterse. This is just an example. I was really curious if we could do this kind of analysis from a draw (of course, when the dataset is available).KGee– KGee2024-08-08 18:03:12 +00:00Commented Aug 8, 2024 at 18:03
- @cybernetic.nomad You are correct. I picked two random points from the draw. I want to know if I can correlate information from a draw, either in Excel or other programs (assuming the datasets are available). If there's a better way than just checking by eye, which is scientifically inaccurate, I'd like to know."KGee– KGee2024-08-08 18:03:43 +00:00Commented Aug 8, 2024 at 18:03
- Yes you can. But the difficulty lies in selecting the correct type of calculation. That -I'm afraid- is entirely your call.jkpieterse– jkpieterse2024-08-09 09:47:50 +00:00Commented Aug 9, 2024 at 9:47
Add a comment |