[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
"Nick Cox" <n.j.cox@durham.ac.uk> |

To |
<statalist@hsphsun2.harvard.edu> |

Subject |
st: RE: xtpcse vs. xtpcse, noconstant |

Date |
Mon, 9 Aug 2004 09:14:27 +0100 |

On the R^2, your starting point is now a prediction of zero, not a prediction of the mean response. In a much simpler case, below, dropping the constant gives a higher R-sq but a totally ludicrous model. Why then does the R-sq look so good? Because the predictions -- which range from 11 to 30 mpg -- are much closer to the data than a prediction of 0 than the predictions of the first model to the mean of -mpg-. Your model is more complicated, and I can't see your data, but I guess that the same applies. If there is a really good reason, like a law of physics, to force predictions through the origin, then do it. (One can certainly improve on a linear regression of -mpg- on -weight-, a secondary point.) . sysuse auto, clear (1978 Automobile Data) . reg mpg weight Source | SS df MS Number of obs = 74 -------------+------------------------------ F( 1, 72) = 134.62 Model | 1591.9902 1 1591.9902 Prob > F = 0.0000 Residual | 851.469256 72 11.8259619 R-squared = 0.6515 -------------+------------------------------ Adj R-squared = 0.6467 Total | 2443.45946 73 33.4720474 Root MSE = 3.4389 ------------------------------------------------------------------------------ mpg | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- weight | -.0060087 .0005179 -11.60 0.000 -.0070411 -.0049763 _cons | 39.44028 1.614003 24.44 0.000 36.22283 42.65774 ------------------------------------------------------------------------------ . reg mpg weight , noconst Source | SS df MS Number of obs = 74 -------------+------------------------------ F( 1, 73) = 259.18 Model | 28094.8545 1 28094.8545 Prob > F = 0.0000 Residual | 7913.14549 73 108.399253 R-squared = 0.7802 -------------+------------------------------ Adj R-squared = 0.7772 Total | 36008 74 486.594595 Root MSE = 10.411 ------------------------------------------------------------------------------ mpg | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- weight | .006252 .0003883 16.10 0.000 .0054781 .007026 ------------------------------------------------------------------------------ Nick n.j.cox@durham.ac.uk chris carambas > I estimated an xtpcse model, and I observed that any of my > runs without > noconstant option has very low R-squared (i.e. 0.08--and this > is the same > result if I run it in xtreg which has no nocons option) but > with noconstant > option, all R-squared become high (i.e. from 0.80).Does anyone have > explanation for that? * * For searches and help try: * http://www.stata.com/support/faqs/res/findit.html * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

- Prev by Date:
**st: Questions about gllamm** - Next by Date:
**st: Autocorrelation and IV in Panel data** - Previous by thread:
**st: Questions about gllamm** - Next by thread:
**st: Autocorrelation and IV in Panel data** - Index(es):

© Copyright 1996–2014 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |