From a0c7e939267290dc23e9ac76d76abbac5f7874a5 Mon Sep 17 00:00:00 2001 From: Keith Kranker Date: Wed, 5 Jun 2019 09:51:35 -0600 Subject: [PATCH] wrap long lines in the help file --- cic.sthlp | 57 ++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 35 insertions(+), 22 deletions(-) diff --git a/cic.sthlp b/cic.sthlp index 924d740..333d4a7 100644 --- a/cic.sthlp +++ b/cic.sthlp @@ -1,6 +1,5 @@ {smcl} {* $Id: cic.sthlp $}{...} -{* Copyright (C) Mathematica This code cannot be copied, distributed or used without the express written permission of Mathematica Policy Research, Inc.}{...} {vieweralsosee "" "--"}{...} {viewerjumpto "Title" "cic##title"}{...} {viewerjumpto "Syntax" "cic##syntax"}{...} @@ -38,16 +37,18 @@ {phang}{it:pvar} must contain values 0 or 1, representing the pre-intervention (0) and post-intervention (1) periods.{p_end} -{phang}{it:varlist} is a (optional) list of covariates variables (see the {help cic##remarks:remarks}) {p_end} +{phang}{it:varlist} is a (optional) list of covariates variables (see the {help cic##remarks:remarks}) {p_end} {marker estimator}{...} -{synoptset 12}{...} +{synoptset 16}{...} {synopthdr:estimator} {synoptline} {synopt :{opt continuous}}CIC estimator with continuous outcomes (Athey and Imbens 2006, equation 9){p_end} -{synopt :{opt dci}}CIC model with discrete outcomes, under the conditional independence assumption (Athey and Imbens 2006, equation 29){p_end} -{synopt :{opt bounds}}lower and upper bound estimates of discrete CIC model, without conditional independence (Athey and Imbens 2006, equation 25){p_end} +{synopt :{opt dci}}CIC model with discrete outcomes, under the conditional independence assumption +(Athey and Imbens 2006, equation 29){p_end} +{synopt :{opt bounds}}lower and upper bound estimates of discrete CIC model, without conditional independence +(Athey and Imbens 2006, equation 25){p_end} {synopt :{opt all}}all of the above{p_end} {synoptline} @@ -63,8 +64,9 @@ default is {opt vce(none)}{p_end} {synopt :{opt did}}calculates traditional DID and quantile DID estimates; by default this option is off, unless {it:varlist} exists in which case it is turned on{p_end} -{synopt :{opt unt:reated}}estimates the counterfactual effect of the policy for the untreated group (Athey and Imbens 2006, Setion 3.2){p_end} -{synopt :{opt rou:nd(#)}} rounds dependent variable to # units (=0 for no rounding, the default); +{synopt :{opt unt:reated}}estimates the counterfactual effect of the policy for the untreated group +(Athey and Imbens 2006, Setion 3.2){p_end} +{synopt :{opt rou:nd(#)}} rounds {it:depvar} to # units (=0 for no rounding, the default); any rounding is performed after adjusting for covariates, if applicable{p_end} {syntab:Reporting} @@ -98,8 +100,11 @@ see {help estimation options##display_options:[R] estimation options}.{p_end} {synopthdr:bsopts} {synoptline} {synopt :{opt reps(#)}} perform # bootstrap replications; default is 1000{p_end} -{synopt :{opt saving(filename[,replace])}} save bootstrap results to filename (optionally, replace specifies that filename be overwritten, if it exists.){p_end} -{synopt :{opt sepercentile}} obtain bootstrap standard errors from percentiles of bootstrap estimates instead of using Stata's default method. standard error = (p(97.5) - p(2.5)) / (2*1.96), where p(N) is Nth percentile of bootstrap iterations (this is the method used in Athey and Imbens' MATLAB code){p_end} +{synopt :{opt saving(filename[,replace])}} save bootstrap results to filename (optionally, +replace specifies that filename be overwritten, if it exists.){p_end} +{synopt :{opt sepercentile}} obtain bootstrap standard errors from percentiles of bootstrap +estimates instead of using Stata's default method. standard error = (p(97.5) - p(2.5)) / (2*1.96), where p(N) +is Nth percentile of bootstrap iterations (this is the method used in Athey and Imbens' MATLAB code){p_end} {synopt :{opt accel(vector)}} acceleration values for each statistic{p_end} {synopt :{opt mse}} use MSE formula for variance estimation{p_end} {synopt :{opt nodots}} suppress the replication dots{p_end} @@ -123,9 +128,13 @@ up the bsrweight() variables, PSUs, weights and strata before calling CIC.{p_end The sample size for {opt size(#)} is defined as follows: without weights, the sample in each group is calculated as the number of observations in the group; with fweights, the sample in each group is calculated as the sum of the fweights for observations in the group; -with iweights, the sample in each group is calculated as the sum of the iweights for observations in the group, divided by the sum of the weights for all observations, and multiplied by the value specified in size() (rounded to the nearest integer -- by default, size()==the sum of the iweights); -with aweights, the weights are normalized to mean 1. then, the sample in each group is calculated as the sum of the weights for observations in the group (rounded to the nearest integer). -This sub-option is allowed only with pweights, aweights, and iweights. With unweighted samples, you could generate a variable equal to one and use it as an iweight.{p_end} +with iweights, the sample in each group is calculated as the sum of the iweights for observations in the group, +divided by the sum of the weights for all observations, and multiplied by the value specified in size() +(rounded to the nearest integer -- by default, size()==the sum of the iweights); +with aweights, the weights are normalized to mean 1. then, the sample in each group is calculated as the sum +of the weights for observations in the group (rounded to the nearest integer). +This sub-option is allowed only with pweights, aweights, and iweights. With unweighted samples, +you could generate a variable equal to one and use it as an iweight.{p_end} {marker description}{...} @@ -176,9 +185,9 @@ allowing one to calculate average treatment effects or estimate effects at speci {pstd} This Stata command, {cmd:cic}, implements the CIC estimator from Athey and Imbens (2006). -{cmd:cic} is written in Mata with an effort to maximize parallel computing; in tests (not shown), I found {cmd:cic} estimated -the model more quickly that the Matlab code previously distributed by Athey and Imbens. -The cic command also offers several previously unavailable features (e.g., to allow for covariates). +{cmd:cic} is written in Mata with an effort to maximize parallel computing; in tests (not shown), +I found {cmd:cic} estimated the model more quickly than the Matlab code previously distributed by Athey and Imbens. +The {cmd:cic} command also offers several previously unavailable features (e.g., to allow for covariates). In addition, you can use Stata's {help bootstrap}: prefix, which offers more flexibility for computing bootstrapped standard errors (e.g., strata, blocks). @@ -188,9 +197,9 @@ Athey and Imbens (2006) explain their methods (with proofs) in a fairly long and The appendix is also quite helpful. {pstd} -Covaraiates are implemented according to the parametric approach outlined in section 5.1. of Athey and Imbens (2006). -"... apply the CIC estimator to the residuals from an ordinary least squares regression with the effects of the dummy -variables added back in." (p. 466) +Covaraiates are implemented according to the parametric approach outlined by Athey and Imbens (2006): +"... apply the CIC estimator to the residuals from an ordinary least squares regression +with the effects of the dummy variables added back in." (p. 466) {marker examples}{...} @@ -226,14 +235,18 @@ available at {browse "https://athey.people.stanford.edu/research"} {title:References} {psee} -Athey, Susan and Guido W. Imbens. "Identification and Inference in Nonlinear Difference-in-Differences Models." *Econometrica*, vol. 74, no. 2, March 2006, pp. 431-497. ({browse "http://dx.doi.org/10.1111/j.1468-0262.2006.00668.x"}) +Athey, Susan and Guido W. Imbens. "Identification and Inference in Nonlinear Difference-in-Differences Models." +*Econometrica*, vol. 74, no. 2, March 2006, pp. 431-497. ({browse "http://dx.doi.org/10.1111/j.1468-0262.2006.00668.x"}) {psee} -Imbens, Guido W. and Jeffery M. Wooldridge. "Recent Developments in the Econometrics of Program Evaluation." *Journal of Economic Literature*, vol. 47, no. 1, 2009, pp. 5–86. ({browse "http://dx.doi.org/10.1257/jel.47.1.5"}) +Imbens, Guido W. and Jeffery M. Wooldridge. "Recent Developments in the Econometrics of Program Evaluation." +*Journal of Economic Literature*, vol. 47, no. 1, 2009, pp. 5–86. ({browse "http://dx.doi.org/10.1257/jel.47.1.5"}) {psee} -Kranker, Keith. "The Effect of Disease Management Programs on Medicaid Expenditures." Doctoral dissertation. College Park, MD: University of Maryland, 2011. ({browse "http://hdl.handle.net/1903/12101"}) +Kranker, Keith. "The Effect of Disease Management Programs on Medicaid Expenditures." +Doctoral dissertation. College Park, MD: University of Maryland, 2011. ({browse "http://hdl.handle.net/1903/12101"}) {psee} -Kranker, Keith. "Effects of Medicaid Disease Management Programs on Medical Expenditures: Evidence from a Natural Experiment in Georgia." *Journal of Health Economics*, vol. 46, March 2016, pp. 52-69. +Kranker, Keith. "Effects of Medicaid Disease Management Programs on Medical Expenditures: Evidence from a Natural Experiment in Georgia." +*Journal of Health Economics*, vol. 46, March 2016, pp. 52-69. ({browse "http://dx.doi.org/10.1016/j.jhealeco.2016.01.008"}){p_end}