Eigenvalues and the condition index: diagnosing multicollinearity (Excel)
Вставка
- Опубліковано 17 жов 2024
- How might one detect multicollinearity in a regression model? One of the most informative ways of looking at the multicollinearity structure and severity is to calculate the eigenvalues and the condition index of the correlation matrix between explanatory variables. However, this can be computationally challenging. Today, we are tackling eigenvalue calculation and its interpretation for multicollinearity and regression model quality in Excel.
Don't forget to subscribe to NEDL and give this video a thumbs up for more videos in Econometrics!
Please consider supporting NEDL on Patreon: / nedleducation
You can find the spreadsheets for this video and some additional materials here: drive.google.com/drive/folders/1sP40IW0p0w5IETCgo464uhDFfdyR6rh7
Please consider supporting NEDL on Patreon: www.patreon.com/NEDLeducation
i'm actually super interested in how you did that multiple correlation, are these correlations of each economic indicator to the entire table? i am trying to replicate this for component returns of the s&p 500 if the columns are each component and the rows are log returns how do you setup the array/index system
is it possible to cover how you did the matrix, just the excel function, i did get the index to work when i applied to s&p 500 components. i will try again but i thought it would be a good excel video also.
Your videos are diamond in the coalmine of UA-cam ❤️❤️
Excellent video. Clever hacks for calculating eigenvalues!!
At the beginning I kept thinking how is he going to do this in native excel. Very clever use of excel and then graphing the function was very helpful. Thank you!
Hi, and thanks so much for such kind words, appreciate your feedback!
You are awesome!
Hi Saba,
Great work. I am curious about Kalman filters for pair trade. How to calculate in excel. Pl. Make vdo on that.
Thanks
Robin
Hi Robin, and many thanks for the suggestion! I might do a video on that at some point if and when I figure out how to implement Kalman filter in Excel in an audience-friendly way.
@@NEDLeducation Great .. I saw ADF in excel VDO. it is amazing ..simple and efficient. Hats off to your skills. Take Care ... Hope to see next vdo soon.
Another amazing video Savva! Can the same logic be applied to time-series data? This is cross-sectional data, right?
Hi Ivan, and thanks for yet another excellent question! The test is perfectly applicable to time-series data as well (same goes for the variance inflation factors or any other multicollinearity test I have covered so far).
Can you do a vid please on Kalman filter for univariate time series prediction and smoothing. Thanks.
Hi, and thanks for the suggestion! Might do a video on that at some point in the distant future if I figure out how to implement that in Excel in an audience-friendly format.