HTT squablles

[mathdotcom]

The relationship is one thing, but the R^2 (R squared) value is another. Similar to a correlation coefficient, it tells you how "close" the relationship is. Absolute values above about 0.6 or 0.7 show stronger relationships, values below can tend toward randomness depending upon how many data points are in the regression.

No.

[TomG]

this is mathlers and my favorite video game

[jgilmartin]

Square One in the motherfuckin house

[mathdotcom]

this is mathlers and my favorite video game

Nice

[Wrecktangle]

No.

Yes, get a clue.

[mathdotcom]

Yes, get a clue.

No.

[bztips]

Wreck -- stick with your Bayesian priors, which (I hope) you know more about than the misleading garbage you posted here.

[Wrecktangle]

If you clowns don't know anything about the r squared statistic or the value of examining your residuals, you should quit posting here. These are basic statistical techniques and the both of you should fess up to the fact that you don't even use it except in the most simplistic of ways. "math" dotcom uncorks a bullshit textbook answer to this problem without giving the OP anything meaningful; but we knew he was pretty useless when he mentioned that game theory had no utility in sports forecasting a year or so back.

Since Ganch has left, this forum has been overrun with pseudo-math bullies. And you zeros are perfect examples.

[mathdotcom]

Wrecktangle give me a baseball winner tomorrow. I'll give you 12 hours to calculate the Nash equilibrium

[mathdotcom]

My most successful model had an R-squared of 0.0054