Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
David Hoaglin <[email protected]> |

To |
[email protected] |

Subject |
Re: st: Relative Importance of predictors in regression |

Date |
Mon, 4 Nov 2013 17:28:16 -0500 |

Hi, Sam. I'm not sure what you mean by "the mathematical expression for 'held constant,'" other than setting each of the other predictors to some particular value. The general interpretation of the coefficient of a predictor in a multiple regression is that it tells how the dependent variable changes per unit increase in that predictor, adjusting for simultaneous linear change in the other predictors in the data at hand. If the model has n observations on Y and p predictors (including the constant, if present), and the data on the predictors form the columns of the (full-rank) matrix X, the mathematics of ordinary least squares involves projecting Y on the subspace of n-space spanned by the columns of X. Nothing in that process of projection holds the other predictors constant at particular values. Regards, David Hoaglin On Mon, Nov 4, 2013 at 3:39 PM, Lucas <[email protected]> wrote: > What would be the mathematical expression for "held constant"? And > what is the mathematical expression to which you are comparing it that > leads you to reject "held constant"? > > Thanks a bunch! > > Sam * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/

**Follow-Ups**:

**References**:**st: Relative Importance of predictors in regression***From:*Nikos Kakouros <[email protected]>

**Re: st: Relative Importance of predictors in regression***From:*David Hoaglin <[email protected]>

**Re: st: Relative Importance of predictors in regression***From:*Lucas <[email protected]>

- Prev by Date:
**Re: st: Saving variable response sets over many datasets** - Next by Date:
**Re: st: Mata order() indeterminate** - Previous by thread:
**Re: st: Relative Importance of predictors in regression** - Next by thread:
**Re: st: Relative Importance of predictors in regression** - Index(es):