Skip to main content
Changed title as it may be misleading with usual notations ($n$ is number of observation and $p$ is number of variables)
Link
gung - Reinstate Monica
  • 147.5k
  • 89
  • 406
  • 717
Changed title as it may be misleading with usual notations ($n$ is number of observation and $p$ is number of variables)
Link

Why is $n >< p$ a problem for OLS regression?

Tweeted twitter.com/StackStats/status/869882796965343232
Source Link
badmax
  • 2.3k
  • 15
  • 27

Why is $n > p$ a problem for OLS regression?

I realize I can't invert the $X'X$ matrix but I can use gradient descent on the quadratic loss function and get a solution. I can then use those estimates to calculate standard errors and residuals. Am I going to encounter any problems doing this?