Comment Re:Wow! (Score 1) 198
If the model cannot be tested, it is useless. If you are able to create the model, then you should be able to test it. That is not rocket science, it is common sense.
beta=solve(t(x) %*% x) %*% t(x) %*% y,
NO, NO, NO!
beta=solve(crossprod(X,X),crossprod(X,y))
is much nicer, and it is less susceptible to round-of errors.
2.4 statute miles of surgical tubing at Yale U. = 1 I.V.League