Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

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

Re: st: Fractional Response Model with Dynamic Component

From   Nick Cox <>
Subject   Re: st: Fractional Response Model with Dynamic Component
Date   Tue, 13 Nov 2012 01:00:08 +0000

Minimal references that are name (date) are deprecated on Statalist,
as is explained in the Statalist FAQ that you were asked to read
before posting.

The main idea you refer to has much longer roots than your references
imply. That apart, I can't see any reason to regard a time component
as out of order. The point is just that bounded responses are
appropriately dealt with by ensuring that predictions are also bounded
by the use of an appropriate link function: not everyone uses that

Jeff Wooldridge (many dates) is an occasional poster on this list. If
you're lucky, he may add a comment.


On Mon, Nov 12, 2012 at 9:50 PM, Anna-Leigh Stone
<> wrote:
> Hello Statalist,
> I am interested in using the Papke and Wooldridge (2008) fractional
> response model. I have a dependent variable that lies within the zero
> and one range for the dependent variable with values that lie at zero
> but not one. However, the model will not converge without a dynamic
> component added in. I am using quarterly data so that there is a need
> for lagged values of the dependent variable. I know that Loudermilk
> (2007) added in a dynamic component into the Tobit model. Is there an
> appropriate way to add in a dynamic component into the fractional
> response model?
> Thank you for any help you can provide,
> Anna-Leigh
> --
> Anna-Leigh Stone
> Finance PHD Candidate 2014
> MA/EC 2011
> MSF 2010
> *
> *   For searches and help try:
> *
> *
> *
*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index