Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: RE: Fractional Logit

From   Rijo John <>
To   Statalist <>
Subject   Re: st: RE: Fractional Logit
Date   Fri, 28 Oct 2005 17:36:43 +0530 (IST)

Thanks Nick. I am trying to estimate the impact of spending on a
particular commodity (say X) on the purchase of other goods and services.
So I have the share of, say commodity Y (Its share in household budget) as
the dependent variable and the expenditure on commodity X along with
various control variables for household as explanatory variables. This can
be a standrad OLS estimation. But since the depended variable is a
fraction and  is bound between 0 and 1 we go for fractional logit model.

I hope this clarifies the problem. Given this I would like to know what
would be the right choice of family and link in GLM.

"family(gaussian) link(logit)" or "family(binomial) link(logit)" or some
other combination?

in "family(binomial) link(logit)" is it tru that stata takes all values
other than 0 in the dependent variable as 1. If thats the case it does not
take the budget share (absolute amount) information into account. It will
only see if the budget share is absent or not.

Kindly advise.


On Fri, 28 Oct 2005, Nick Cox wrote:

<This is a repeat posting. The original
<got no replies. One possible reason for
<that is that it is near impossible to
<say what is the "right answer", absent
<any idea of your data or your scientific
<problem. Different families might be
<appropriate depending on the data and
<on your ideas about generative processes.
<Rijo John
<>  I am estimating a Fractional logit model. Stata help says
<> using
<> glm y x1 x2...xk, family(binomial) link(logit)
<> is same as "logistic" command and the later is infact
<> preferred. Because
<> family(binomial) means that y has the Bernoully distribution
<> with values 0
<> and 1 only. But my y variable is a continuous variable (a
<> fraction) taking
<> any values between 0 and 1. In this case which family and
<> link should I be
<> using?
<> Is "family(gaussian) link(logit)" the right one?
<> Also what is the criteria of deciding which scale parameter
<> to be used?
<> I mean whether scale(1) or scale(x2) etc.
<*   For searches and help try:

Rijo.M.John,Research Scholar
Indira Gandhi Institute of Development Research,
Film City Road, Goregaon East,
Mumbai, India-400065.
contact: (+91)9892412476

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index