Suppose I want to create the latex output for the example in ivprobit. That is:
use http://www.stata-press.com/data/r11/laborsup.dta
ivprobit fem_work fem_educ kids (other_inc = male_educ), first
margins, dydx(_all) pred(pr)
I want to have one column with the first stage, and one with the marginal effects.
What is the best way of doing this?
There might be a more clever way of doing this that does not involve re-estimating the first stage:
webuse laborsup
ivprobit fem_work fem_educ kids (other_inc = male_educ), first
margins, dydx(_all) predict(pr) post
estimates store ivp
reg other_inc male_educ fem_educ kids
estimates store first_stage
estout first_stage ivp, style(tex)
Related
After running these command all day, my head is on fire, I am now reaching out.
Please don't direct me to papers about Suest that are commonly mentioned on the web, I already checked them.
It seems there is a problem with storing the dy/dx values of the AME to merge between different models in the suest command in order to perform the test command.
What I would like to test is if the AME of the lower class/upper class/middle class in one regime/context is statistically significant from the lower class situated in another regime/context.
Dependent variable: 3 categories: renter, mortgaged homeownership, outright homeownership.
*Liberal_market
mlogit owner_housing_debt2 United_States United_Kingdom Swizerland c.age_centered
ib0.lower_class ib0.upper_class if homeownership_regimes==1 ,
baseoutcome(1)
margins , dydx(lower_class upper_class) coeflegend post
est store Liberal_market
*Family_financial_support
mlogit owner_housing_debt2 Belgium Finland France Ireland Luxembourg Norway Spain
ib0.lower_class ib0.upper_class if homeownership_regimes==2 , baseoutcome(1)
margins , dydx(lower_class upper_class) coeflegend post
est store Family_financial_support
est table Liberal_market Family_financial_support
suest Liberal_market Family_financial_support
**In the end, this is what I want to do:
test [Liberal_market]1.lower_class =[Family_financial_support]1.lower_class
*error message
Liberal_market was estimated with a nonstandard vce (delta)
r(322);
-Unfortunately, the following answer from Statalist regarding the nonstandard vce in suest- didn’t help me either
https://www.statalist.org/forums/forum/general-stata-discussion/general/1511169-can-not-use-suest-for-margins-after-probit-or-regress
Will appreciate your solution:)
Thank you. I tried your recommendation. Unfortunately, I could not find an organized document with examples for xlincom with margins.
I tried the following code, but my problem is withdrawing the margins of the independent variable categories (1.lower_class and 1.upper_class) from the 2 separate mlogit reg after suest. I mean, how to define in the command that I want 1.lower class from model A and 1.lower_class from model B in the margins and in the xlincom. Please see my example below:
mlogit owner_housing_debt2 ib0.lower_class ib0.upper_class if regime==1,
baseoutcome(1)
est store A
mlogit owner_housing_debt2 ib0.lower_class ib0.upper_class if regime==2,
baseoutcome(1)
est store B
suest A B
margins 1.lower_class 1.upper_class, coeflegend post
lincom _b[1.lower_class] - _b[1.upper_class]
I´m trying to print my CI with esttab in this order:
My code with the cars.csv dataset form https://gist.github.com/noamross/e5d3e859aa0c794be10b#file-cars-csv:
clear all
import excel "C:\Users\luism\Desktop\archive/cars_usa.xlsx", sheet("hoja1") firstrow
destring mileage, force replace
reg price mileage
estimates store model_1
esttab model_1 using "C:\Users\luism\Desktop\archive/results.csv", replace beta ci
This is what I got when I separate by commas the results.csv file.
I would like to print the upper bound below the lower bound, not next to after I separate by commas the results.csv. Thanks
estadd allows you to add anything as a scalar and include it as follows:
sysuse auto , clear
reg price mpg
matrix results = r(table)
estadd scalar upperCI = results[rownumb(results,"ul"),colnumb(results,"mpg")]
estadd scalar lowerCI = results[rownumb(results,"ll"),colnumb(results,"mpg")]
esttab, stats(lowerCI upperCI)
This is exactly what Dimitry was suggesting in his comment. Wouter's comment is true to the extent that this isn't, strictly speaking, an "option" of esttab or estout. However, estadd provides a large amount of flexibility to esttab and it's worth knowing about.
I have the following model:
Y_{it} = alpha_i + B1*weight_{it} + B2*Dummy_Foreign_{i} + B3*(weight*Dummy_Foreign)_ {it} + e_{it}
and I am interested on the effect on Y of weight for foreign cars and to graph the evolution of the relevant coefficient across quantiles, with the respective standard errors. That is, I need to see the evolution of the coefficients (B1+ B3). I know this is a non-linear effect, and would require some sort of delta method to obtain the variance-covariance matrix to obtain the standard error of (B1+B3).
Before I delve into writing a program that attempts to do this, I thought I would try and ask if there is a way of doing it with grqreg. If this is not possible with grqreg, would someone please guide me into how they would start writing a code that computes the proper standard errors, and graphs the quantile coefficient.
For a cross section example of what I am trying to do, please see code below.
I use grqred to generate the evolution of the separate coefficients (but I need the joint one)-- One graph for the evolution of (B1+B3) with it's respective standard errors.
Thanks.
(I am using Stata 14.1 on Windows 10):
clear
sysuse auto
set scheme s1color
gen gptm = 1000/mpg
label var gptm "gallons / 1000 miles"
gen weight_foreign= weight*foreign
label var weight_foreign "Interaction weight and foreign car"
qreg gptm weight foreign weight_foreign , q(.5)
grqreg weight weight_foreign , ci ols olsci reps(40)
*** Question 1: How to constuct the plot of the coefficient of interest?
Your second question is off-topic here since it is statistical. Try the CV SE site or Statalist.
Here's how you might do (1) in a cross section, using margins and marginsplot:
clear
set more off
sysuse auto
set scheme s1color
gen gptm = 1000/mpg
label var gptm "gallons / 1000 miles"
sqreg gptm c.weight##i.foreign, q(10 25 50 75 95) reps(500) coefl
margins, dydx(weight) predict(outcome(q10)) predict(outcome(q25)) predict(outcome(q50)) predict(outcome(q75)) predict(outcome(q95)) at(foreign=(0 1))
marginsplot, xdimension(_predict) xtitle("Quantile") ///
legend(label(1 "Domestic") label(2 "Foreign")) ///
xlabel(none) xlabel(1 "Q10" 2 "Q25" 3 "Q50" 4 "Q75" 5 "Q95", add) ///
title("Marginal Effect of Weight By Origin") ///
ytitle("GPTM")
This produces a graph like this:
I didn't recast the CI here since it would look cluttered, but that would make it look more like your graph. Just add recastci(rarea) to the options.
Unfortunately, none of the panel quantile regression commands play nice with factor variables and margins. But we can hack something together. First, you can calculate the sums of coefficients with nlcom (instead of more natural lincom, which the lacks the post option), store them, and use Ben Jann's coefplot to graph them. Here's a toy example to give you the main idea where we will look at the effect of tenure for union members:
set more off
estimates clear
webuse nlswork, clear
gen tXu = tenure*union
local quantiles 1 5 10 25 50 75 90 95 99 // K quantiles that you care about
local models "" // names of K quantile models for coefplot to graph
local xlabel "" // for x-axis labels
local j=1 // counter for quantiles
foreach q of numlist `quantiles' {
qregpd ln_wage tenure union tXu, id(idcode) fix(year) quantile(`q')
nlcom (me_tu:_b[tenure]+_b[tXu]), post
estimates store me_tu`q'
local models `"`models' me_tu`q' || "'
local xlabel `"`xlabel' `j++' "Q{sub:`q'}""'
}
di "`models'
di `"`xlabel'"'
coefplot `models' ///
, vertical bycoefs rescale(100) ///
xlab(none) xlabel(`xlabel', add) ///
title("Marginal Effect of Tenure for Union Members On Each Conditional Quantile Q{sub:{&tau}}", size(medsmall)) ///
ytitle("Wage Change in Percent" "") yline(0) ciopts(recast(rcap))
This makes a dromedary curve, which suggests that the effect of tenure is larger in the middle of the wage distribution than at the tails:
I wonder if you could help me figure it out a quite simple question of how I can save an extracted statistic from a regression in a separate dataset (or file), and also add more statistics from the other regression to it later?
For example, the statistic from one regression can be extracted as e(f) and from another one is also as e(f).
Roger Newson's parmest is great for dealing with "resulsets," which are Stata datasets created from the output of a Stata command. The help file has a nice example of combining three regressions into a single file that I modified here to include R^2 [stored in e(df_r)]:
sysuse auto, clear
tempfile tf1 tf2 tf3
parmby "reg price weight", lab saving(`"`tf1'"', replace) idnum(1) idstr(M1) escal(r2)
parmby "reg price foreign", lab saving(`"`tf2'"', replace) idnum(2) idstr(M2) escal(r2)
parmby "reg price weight foreign", lab saving(`"`tf3'"', replace) idnum(3) idstr(M3) escal(r2)
drop _all
append using `"`tf1'"' `"`tf2'"' `"`tf3'"'
list idnum idstr es_1, noobs nodis
I'm trying to create a bar chart in which the frequency is outside the bar and the percentage inside, is it possible? Would post a picture but the system doesn't allow for it yet.
As others pointed out, this is a poor question without code.
It is possible to guess that you are using graph bar. That makes you choose at most one kind and position of bar labels. Much more is possible with twoway bar so long as you do a little work.
sysuse auto, clear
contract rep78 if rep78 < .
su _freq
gen _pc = 100 * _freq / r(sum)
gen s_pc = string(_pc, "%2.1f") + "%"
gen one = 1
twoway bar _freq rep78, barw(0.9) xla(1/5, notick) bfcolor(none) ///
|| scatter one _freq rep78, ms(none ..) mla(s_pc _freq) mlabcolor(black ..) ///
mlabpos(0 12) scheme(s1color) ysc(r(0 32)) yla(, ang(h)) legend(off)
In short:
contract collapses to a dataset of frequencies.
Calculation of percents is trivial, but you need a formatted version in a string variable if the labels are not to look silly. Precise format is at choice.
The frequency scale on the axis is arguably redundant given the bar labels, and could be omitted.
The example puts labels within the bar just above its base at the level of frequency equal to 1. That's a choice for this example and would be too close to the axis if the typical frequencies were much higher.