beta 和 correlation 的关系

• accepted

  Assuming you're talking about a simple regression model Yi=α+βXi+εi

  estimated by least squares, we know from wikipedia that
  β^=cor(Yi,Xi)⋅SD(Yi)SD(Xi)
  Therefore the two only coincide when SD(Yi)=SD(Xi)

  . That is, they only coincide when the two variables are on the same scale, in some sense. The most common way of achieving this is through standardization, as indicated by @gung.

  The two, in some sense give you the same information - they each tell you the strength of the linear relationship between Xi

  and Yi

  . But, they do each give you distinct information (except, of course, when they are exactly the same):

  • The correlation gives you a bounded measurement that can be interpreted independently of the scale of the two variables. The closer the estimated correlation is to ±1

• , the closer the two are to a perfect linear relationship. The regression slope, in isolation, does not tell you that piece of information.

• The regression slope gives a useful quantity interpreted as the estimated change in the expected value of Yi

  for a given value of Xi . Specifically, β^ tells you the change in the expected value of Yi corresponding to a 1-unit increase in Xi . This information can not be deduced from the correlation coefficient alone.