推荐3篇2024年《数量经济技术经济研究》上使用ddtiming命令进行培根分解的论文

学术   教育   2024-12-09 22:41   陕西  

推荐3篇《数量经济技术经济研究》2024年第3期上使用ddtiming命令进行培根分解的论文



论文1:全国统一大市场与经济增长——来自安徽省加入长三角城市经济协调会的证据

构建渐进双重差分模型,采用Goodman-Bacon分解进行稳健性检验

使用的命令为ddtiming,复刻结果为:

上述结果与附表4结果完全一致。根据附录表4的数据显示,恰当的处理效应估计数为1.845,其对应的权重高达77.1%,占据了较大的比例;而不恰当的处理效应估计数为0.642,其权重为22.9%,占比相对较小。这些发现支持了基准回归估计值并未受到显著偏差影响的观点。


论文2:“亩均论英雄”改革与企业高质量发展——基于效率变革和动力变革的视角

渐进式双重差分模型

平行趋势检验

诚实双重差分方法(Honest DID)

双向固定效应偏误识别与异质性处理效应检验

安慰剂检验

稳健性检验


采用Goodman-Bacon分解进行稳健性检验 ,使用的命令为ddtiming,复刻结果为:

原文结果为:


论文3:推荐文章:碳达峰目标如何引领城市低碳转型——来自准自然实验的证据

psm

  • psmatch2

  • pstest

  • 描述性统计

  • tabstat

  • 基准回归

  • xtreg 

  • 平行趋势

  • xtreg

  • coefplot

  • 异质性处理偏误

  • ddtiming

  • twowayfeweights

Bacon分解

Goodman-Bacon(2021)指出多时点DID分析中,采用双向固定效应估计量等于所有可能的2*2 DID双重差分估计量的加权平均值,可能存在偏误。

根据 Goodman-Bacon (2021)的研究,所有的2x2-DID估计值可以分为三类,即“新处理个体”(实验组)将“未处理个体”当作对照组、"新处理个体”(实验组)将“尚未”处理的个体当作对照组以及“新处理个体”(实验组)将“已经处理”过的个体当作对照组。第三类结果变量中已经包含了处理效应,所寻找的对照组并不是科学的。

采用Goodman-Bacon分解法进行检验。结果如下:






培根分解结果表明:

组1以“尚未接受处理组”为控制组

组2是以“较早接受处理组”作为对照的“不良”控制组,权重仅为1.3%

组3是以“从未接受处理组”作为对照的“良好”控制组,权重达到95.3%,几乎解释了全部基线回归结果。

这意味着估计结果受异质性处理效果的影响较小,本研究结果仍然稳健

原文使用ddtiming命令代码为:

 ddtiming lncg tg,i(dist) t(year)Calculating treatment times...Calculating weights...Estimating 2x2 diff-in-diff regressions...
Diff-in-diff estimate: -0.266
DD Comparison Weight Avg DD Est-------------------------------------------------Earlier T vs. Later C 0.034 0.093Later T vs. Earlier C 0.013 -0.258T vs. Never treated 0.953 -0.279-------------------------------------------------T = Treatment; C = Comparison
. ddtiming lnco2 tg,i(dist) t(year)Calculating treatment times...Calculating weights...Estimating 2x2 diff-in-diff regressions...
Diff-in-diff estimate: -0.213
DD Comparison Weight Avg DD Est-------------------------------------------------Earlier T vs. Later C 0.034 0.064Later T vs. Earlier C 0.013 -0.320T vs. Never treated 0.953 -0.222-------------------------------------------------T = Treatment; C = Comparison
. end of do-file
.


ddtiming命令简介

ddtiming是一个Stata命令,基于Goodman-Bacon(2021), 实现了双重差分(DD)估计随处理时间变化的分解。双向固定效应DD模型是所有可能的两组/两期DD估计量的加权平均。该命令生成 2x2 DD估计值及其相关权重的散点图。

R用户可以使用名为bacondecomp的R包执行分解。

注意事项:Stata用户应该使用bacondecomp,这是Stata中Bacon分解的最新实现。

安装

要在 Stata 中安装命令,请在命令窗口中键入ddtiming

net describe ddtiming, from(https://tgoldring.com/code)
net install ddtiming

或输入

net install ddtiming, from(https://tgoldring.com/code)

示例 – 无过错离婚法

ddtiming可以复制古德曼-培根 (2021) 中的例子。下载并加载一个数据集,其中包含无过错离婚法和女性自杀率数据(Stevenson & Wolfers,2006):

net get ddtiming

use nofault_divorce.dta

为了进行比较,估计女性自杀对无过错离婚改革的双向固定效应DD模型:

areg asmrs treat i.year, a(state) vce(robust)

将Goodman-Bacon(2018)中的DD分解定理应用于双向固定效应DD模型:

ddtiming asmrs treat, i(state) t(year)

Stata 将生成 DD 估计值、相关权重和估计值的散点图。散点图复制了Goodman-Bacon (2021) 中的图 (6)。此外,我们可以在命令中添加选项来修改散点图的外观:

ddtiming asmrs treat, i(state) t(year) ddline(lwidth(thick)) ///
ylabel(-30(10)30) legend(order(3 4 1 2)) savegraph(nfd.jpg) ///
savedata(nfd) replace

操作结果

图片
图片
图片
图片

引文

请引用为:ddtiming

Goldring, T. (2019). ddtiming: Stata module to perform a Goodman-Bacon decomposition of difference-in-differences estimation. tgoldring.github.io/projects/ddtiming

References

Goodman-Bacon, A. (2021). Difference-in-differences with variation in treatment timing. Journal of Econometrics, 225(2), 254–277.

Stevenson, B., & Wolfers, J. (2006). Bargaining in the Shadow of the Law: Divorce Laws and Family Distress. The Quarterly Journal of Economics, 121(1): 267–288.


本视频里面用到的数据以及案例代码

要在Stata中安装ddtiming命令,可以在命令窗口中键入任意一种命令

net describe ddtiming, from(https://tgoldring.com/code)
  
net install ddtiming
*or type

net install ddtiming, from(https://tgoldring.com/code)



*- 例子-单边离婚法
  * ddtiming可以复制Goodman-Bacon(2021)中的例子。
  * 下载并加载无过错离婚法和女性自杀率的时间数据集(Stevenson & Wolfers, 2006):


  net get ddtiming
  
use nofault_divorce.dta

*注意,我们还是使用的为3月23日视频里面介绍那个案例数据

use bacon_example.dta, clear

 areg asmrs post i.year, a( stfips ) vce(robust)
结果省略

ddtiming asmrs post, i( stfips) t(year)
Calculating treatment times...
Calculating weights...
Estimating 2x2 diff-in-diff regressions...

Diff-in-diff estimate: -3.080   

DD Comparison              Weight      Avg DD Est
-------------------------------------------------
Earlier T vs. Later C       0.111          -0.187
Later T vs. Earlier C       0.265           3.512
T vs. Never treated         0.240          -5.331
T vs. Already treated       0.384          -7.044
-------------------------------------------------
T = Treatment; C = Comparison

ssc install bacondecomp
checking bacondecomp consistency and verifying not already installed...
installing into c:\ado\plus\...
installation complete.

 
. adoedit bacondecomp
c:\ado\plus/b/bacondecomp.ado

. bacondecomp asmrs post , ddetail
Computing decomposition across 14 timing groups
including an always-treated group and a never-treated group
------------------------------------------------------------------------------
       asmrs |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
        post |  -3.079926   1.111656    -2.77   0.006    -5.258732   -.9011193
------------------------------------------------------------------------------

Bacon Decomposition

+---------------------------------------------------+
|                      |         Beta   TotalWeight |
|----------------------+----------------------------|
|         Early_v_Late |  3.089867353   .0001259938 |
|         Late_v_Early | -23.83420181   .0006803664 |
|         Early_v_Late |  .7286439538   .0008819564 |
|         Late_v_Early | -8.258329391   .0045861736 |
|         Early_v_Late |  2.404874802   .0005291738 |
|         Late_v_Early |  22.15005112   .0022930868 |
|         Early_v_Late |  1.676301956    .000566972 |
|         Late_v_Early | -7.148348331     .00283486 |
|         Early_v_Late |  4.613049507   .0004535776 |
|         Late_v_Early |  26.58180046   .0018899067 |
|         Early_v_Late | -7.006736755   .0009260543 |
|         Late_v_Early | -5.394356728   .0033073366 |
|         Early_v_Late |  .6727053523   .0025198756 |
|         Late_v_Early |  -7.43382597    .012095402 |
|         Early_v_Late |  3.899661064   .0022678879 |
|         Late_v_Early |  27.04117584   .0090715515 |
|         Early_v_Late | -7.521428585   .0061736949 |
|         Late_v_Early | -6.398066521   .0211669536 |
|         Early_v_Late | -3.244979858   .0015119253 |
|         Late_v_Early | -3.630996227   .0045357758 |
|         Early_v_Late |  .1488796175   .0009449533 |
|         Late_v_Early | -5.158778191   .0043467852 |
|         Early_v_Late | -2.910137653   .0009071552 |
|         Late_v_Early |  23.89071274   .0034774283 |
|         Early_v_Late | -9.381551743   .0027781627 |
|         Late_v_Early | -6.318483829    .009128249 |
|         Early_v_Late | -8.437994003   .0009071552 |
|         Late_v_Early | -6.468858719   .0026080712 |
|         Early_v_Late |  4.291956902    .001700916 |
|         Late_v_Early |  6.192469597   .0043467852 |
|         Early_v_Late |  9.615415573   .0007559626 |
|         Late_v_Early |  .6682447195   .0033262358 |
|         Early_v_Late |  5.732773304   .0007559626 |
|         Late_v_Early |  29.61791611    .002771863 |
|         Early_v_Late |  2.411342144    .002469478 |
|         Late_v_Early |  4.052882671   .0077612166 |
|         Early_v_Late |  5.130411148   .0009071552 |
|         Late_v_Early |  4.886719704   .0024946767 |
|         Early_v_Late |  8.392121315   .0022678879 |
|         Late_v_Early |  10.78344917   .0055437261 |
|         Early_v_Late |   3.15568161   .0003779813 |
|         Late_v_Early |  3.873969555   .0008315589 |
|         Early_v_Late |  3.482367754   .0004409782 |
|         Late_v_Early |  4.239864349   .0018521086 |
|         Early_v_Late |  -7.72107935   .0004535776 |
|         Late_v_Early |  28.58859062   .0015875215 |
|         Early_v_Late | -8.404179573   .0015434237 |
|         Late_v_Early |  3.740804911   .0046302713 |
|         Early_v_Late | -9.093745232   .0006047701 |
|         Late_v_Early |  .6837824583   .0015875215 |
|         Early_v_Late |  1.421976328    .001700916 |
|         Late_v_Early |  11.66159821   .0039688039 |
|         Early_v_Late | -16.38343239   .0003779813 |
|         Late_v_Early | -6.338175297   .0007937608 |
|         Early_v_Late | -14.61515999   .0001385932 |
|         Late_v_Early | -7.964285851   .0002645869 |
|         Early_v_Late | -3.567538977   .0015119253 |
|         Late_v_Early | -13.05292702    .006047701 |
|         Early_v_Late | -10.86773682   .0015875215 |
|         Late_v_Early |  13.24829674   .0052917384 |
|         Early_v_Late |   -7.6874547   .0055563254 |
|         Late_v_Early | -9.137350082   .0158752156 |
|         Early_v_Late | -6.326669693   .0022678879 |
|         Late_v_Early | -11.05425262   .0056697199 |
|         Early_v_Late |  4.825609684   .0068036641 |
|         Late_v_Early |    .64386338   .0151192535 |
|         Early_v_Late |  2.691236258    .001700916 |
|         Late_v_Early | -4.655465126   .0034018321 |
|         Early_v_Late |  1.836740971   .0008315589 |
|         Late_v_Early | -6.611749649   .0015119253 |
|         Early_v_Late |  20.30932999   .0002267888 |
|         Late_v_Early |  7.368327141   .0003779813 |
|         Early_v_Late |  3.358542204   .0006929658 |
|         Late_v_Early | -4.764940262   .0023560837 |
|         Early_v_Late | -9.930462837   .0007559626 |
|         Late_v_Early |  19.64731598   .0021418943 |
|         Early_v_Late | -2.845511436   .0027781627 |
|         Late_v_Early |  -.215427205   .0067469666 |
|         Early_v_Late | -3.231632233   .0012095402 |
|         Late_v_Early | -2.357027531   .0025702729 |
|         Early_v_Late |  3.202227831   .0039688039 |
|         Late_v_Early |  6.197752476   .0074966296 |
|         Early_v_Late | -.0546139181   .0011339439 |
|         Late_v_Early |  .2491527498   .0019277048 |
|         Early_v_Late | -4.581885338   .0006929658 |
|         Late_v_Early | -6.757017612   .0010709471 |
|         Early_v_Late |  23.70957756   .0003023851 |
|         Late_v_Early |  21.65239143   .0004283788 |
|         Early_v_Late | -5.129266739   .0007370636 |
|         Late_v_Early |  2.485960007   .0009638524 |
|         Early_v_Late |  9.392490387   .0009449533 |
|         Late_v_Early |  .7609612942   .0024568787 |
|         Early_v_Late | -8.653765678   .0010583477 |
|         Late_v_Early |  20.62852859   .0022930868 |
|         Early_v_Late |  2.299735785   .0040129018 |
|         Late_v_Early |  3.604630232   .0074525319 |
|         Early_v_Late |  3.223866224   .0018143104 |
|         Late_v_Early |  4.552188396   .0029482542 |
|         Early_v_Late |  6.547305107    .006236692 |
|         Late_v_Early |   10.9064064   .0090085548 |
|         Early_v_Late |     5.205688   .0018899067 |
|         Late_v_Early |   6.71902132   .0024568787 |
|         Early_v_Late | -.8521057963   .0012473383 |
|         Late_v_Early | -2.820950985   .0014741271 |
|         Early_v_Late |  17.60421181   .0006047701 |
|         Late_v_Early |  19.93760681   .0006551676 |
|         Early_v_Late | -2.688749552    .001719815 |
|         Late_v_Early |    9.5492239    .001719815 |
|         Early_v_Late | -1.343767166   .0004031801 |
|         Late_v_Early |  1.879976273   .0003275838 |
|         Early_v_Late | -1.982551336   .0010079502 |
|         Late_v_Early |  8.675222397   .0024190804 |
|         Early_v_Late | -19.76277542   .0011339439 |
|         Late_v_Early |  28.40373802   .0022678879 |
|         Early_v_Late | -5.887892723   .0043215866 |
|         Late_v_Early |   11.7344656   .0074084342 |
|         Early_v_Late |  -.348316431    .001965503 |
|         Late_v_Early |  13.98102951   .0029482542 |
|         Early_v_Late |  6.036512852   .0068036641 |
|         Late_v_Early |  21.13029671   .0090715515 |
|         Early_v_Late |  3.112169027   .0020788973 |
|         Late_v_Early |  16.37677193   .0024946767 |
|         Early_v_Late |  .1411235332   .0013859315 |
|         Late_v_Early |  9.925600052   .0015119253 |
|         Early_v_Late |  16.27362823   .0006803664 |
|         Late_v_Early |  29.59807777   .0006803664 |
|         Early_v_Late | -1.641644478    .001965503 |
|         Late_v_Early |  22.16219139   .0018143104 |
|         Early_v_Late | -2.667479753   .0005039751 |
|         Late_v_Early |  12.13856983   .0003779813 |
|         Early_v_Late |   5.63313818   .0001259938 |
|         Late_v_Early |  16.86439133   .0000755963 |
|      Always_v_timing | -7.043688925   .3844322134 |
|       Never_v_timing | -5.330906825   .2402701287 |
+---------------------------------------------------+

数量经济学
见证计量经济学发展,更懂计量更懂你!
 最新文章