Feddback Regression

Hi Mathew,

first of all I want thank you really very much for your tireless efforts to make Optuma still better. I am very curious about v1.6 with all its new tools and improvements.

Concerning your video about the use of regression, correlation, alpha, and beta I am very pleased to hear that you make the current somewhat confusing calculations about r-squared to a consistent and comparable one.

In this regard I want mention for those interested in this topic a forum post in which we have already discussed this matter intensively. The link is: https://forum.optuma.com/topic/regression-r-squared/

Concerning “beta” I want ask you Mathew whether you have also changed the calculation from normal percentage calculation to LN calculation as I have described it in the post “Beta #2”? The link to this post: https://forum.optuma.com/topic/beta-2/

Thanks again for your great efforts to make Optuma the best technical and quantitative analysis program available.

Thomas

Addendum: The video about regression, correlation, alpha, and beta was published on Twitter.

The Link: https://twitter.com/Optuma

Thomas

Hi Thomas,

Thanks for the reminder - I still need to look into this.

Since Beta is the slope of the regresion line, and all four values (correlation, alpha, beta, and r²) are components of the same regression calculation, they would all use the Ln instead of % change. I believe that is the expected behaviour but please let me know if you think otherwise.

All the best

Mathew

 

Hi Mathew,

that is exactly my thinking. All calculations should use the Ln instead of the % change calculations.

Thanks

Thomas

Ok - example of the new calculations on the Beta Post https://forum.optuma.com/topic/beta-2/