Timeline for Generate a random variable with a defined correlation to an existing variable(s)
Current License: CC BY-SA 3.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 5, 2022 at 1:07 | comment | added | eagle34 | Got it, thanks! This answer was helpful: stats.stackexchange.com/questions/120179/… | |
| Jan 4, 2022 at 5:14 | comment | added | Aksakal | @eagle34, this should work for any sample size if done right. if you feed the uncorrelated data, you get the right correlations. so, look at the correlation matrix of X. is it very close to the unit matrix? | |
| Jan 4, 2022 at 2:55 | comment | added | eagle34 | Thanks. Should this work for small sample sizes? E.g. T=65? I tried it for that T and the empirical correlations were quite far from the values specified in R. | |
| Jan 4, 2022 at 2:40 | comment | added | Aksakal | It works because C can be seen as a square root of covariance matrix. The math works out this way | |
| Nov 12, 2017 at 16:16 | history | edited | Aksakal | CC BY-SA 3.0 |
typo
|
| Nov 10, 2017 at 23:03 | history | answered | Aksakal | CC BY-SA 3.0 |