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 at the end of May, and its replacement, statalist.org is already up and running.


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

Re: Again the requrest: SIMULATION TO INTERPRET AND PRESENT LOGIT RESULTS without formatting - hopefully looks better


From   Scott Merryman <scott.merryman@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: Again the requrest: SIMULATION TO INTERPRET AND PRESENT LOGIT RESULTS without formatting - hopefully looks better
Date   Fri, 2 Mar 2012 15:20:33 -0600

On Fri, Mar 2, 2012 at 11:02 AM, Alexander M. Jais
<jais@win.rwth-aachen.de> wrote:
<snip>
* How do I code the Interaction Variable and Independent Variable,
which are NOT binary – the explanation in Zellner shows only the
binary interaction term (see lines 3, 10, … in Do file below; based
on Zellner 2009, also attached, see pages 21-23) ?

* Why is in line 8 all independent variables set to zero?
<snip>

1.  How do you want to code the interaction of two ordinal variables?
In the example below using two continuous variables, mpg is allowed
vary over a range of values while gear_ratio is set at the minimum or
maximum value.

2.  From page 10 of the paper:  "The ambivalent firm, as defined by
Hoetker (2007b), is modeled by setting the values of the independent
variables other than asset specificity and demand uncertainty to zero,
and serves as a useful illustration because the predicted
probabilities for this hypothetical firm vary substantially..."


Example:

sysuse auto, clear
gen  mpggear= mpg*gear

estsimp logit fore mpg gear price mpggear
foreach var in X Y0 Y1 Y0lb Y1lb Y0ub Y1ub dY dYlb dYub {
gen `var' = .
}
setx price mean
qui {
forvalues obs = 20(1)40 {
	replace X = `obs' in `obs'
	setx mpg  `obs'+1
	foreach as_lev in 0 1 {
		if `as_lev' == 0 {
			qui sum gear
			local gear_lev = r(min)
		}
		if `as_lev' == 1 {
			qui sum gear
			local gear_lev = r(max)
		}		
		setx gear `gear_lev' mpggear `gear_lev'*`obs'
		simqi, genpr(Y`as_lev'_tmp) prval(1)
		sum Y`as_lev'_tmp, meanonly
		replace Y`as_lev' = r(mean) in `obs'
		_pctile Y`as_lev'_tmp, p(2.5, 97.5)
		replace Y`as_lev'lb = r(r1) in `obs'
		replace Y`as_lev'ub = r(r2) in `obs'
	}
drop *_tmp
}
}
twoway rbar Y0ub Y0lb X, mw msize(1) lcolor(gs12) fcolor(gs16)  ///
  || line Y0 X, color(gs12) ///
  || rspike Y1ub Y1lb X, color(gs0) lp(dot)  ///
  || line Y1 X, color(gs0) ///
  || , yscale (r(0 1)) ylabel(0(.2)1) ///
   legend(order(2 "Minimum Gear Ratio" 4 "Maximum Gear Ratio") size(*.7)) ///
   xtitle("MPG") ytitle("Probility of Foreign Origin") graphregion(fcolor(gs16))


Scott

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


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