Alexander,
How about something like this:
sysuse auto,clear
qui {
reg price disp length
gen b_disp = _b[disp]
gen b_length = _b[length]
scalar t_disp = _b[disp] / _se[disp]
scalar t_length = _b[length] / _se[length]
if abs(t_disp) > 1.96 {
local bar1 "1, bfcolor(red) blcolor(red)"
}
else {
local bar1 "1, bfcolor(blue) blcolor(blue)"
}
if abs(t_length) > 1.96 {
local bar2 "2, bfcolor(red) blcolor(red)"
}
else {
local bar2 "2, bfcolor(blue) blcolor(blue)"
}
}
graph bar (mean) b_* , bargap(30) ///
bar(`bar1') bar(`bar2') ytitle("Parameter Estimate") ///
blabel(bar, position(outside))
Hope this helps,
Scott
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of
> [email protected]
> Sent: Monday, August 23, 2004 1:08 PM
> To: [email protected]
> Subject: st: Nested If / then statement in a Bar Graph
>
>
>
>
> Hello,
>
> I am making a series of bar graphs in STATA, each of which plots the
> magnitudes of certain parameter estimates of different variables in a
> regression against each other. I want to somehow indicate on the graph
> which variables are significant and which are not, so I was thinking of
> changing the color of bars depending on whether or not the parameter
> estimate is significantly different from zero.
>
> In this light, after running my regression, I define:
>
> generate nafta_b = _b[nafta_der]
> scalar nafta_t = _b[nafta_der] / _se[nafta_der] (where nafta_der is one
> variable whose parameter estimate I want to plot)
>
> and I make the following graph:
>
> graph bar (mean) nafta_b and other similar variables, ///
> bargap(30) ///
> bar(1, bfcolor(red) blcolor(red) if nafta_t > 1.96) ///
> ytitle("Parameter Estimate")
> (and other graph options)
>
> My question is how can I get the bars to change colors, depending on
> whether or not the t-statistic is greater than 1.96? The if command
> nested
> in the bar statement doesn't work, and it won't let me put an if / then
> statement outside the statement. Any ideas on what I should do?
>
> Thank you, in advance, for your assistance with this.
>
*
* 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/
