|
View: |
Part 1: Document Description
|
|
Citation |
|
|---|---|
|
Title: |
Replication Data for: When Should We Use Unit Fixed Effects Regression Models for Causal Inference with Longitudinal Data? |
|
Identification Number: |
doi:10.7910/DVN/YUM3K8 |
|
Distributor: |
Harvard Dataverse |
|
Date of Distribution: |
2019-01-18 |
|
Version: |
1 |
|
Bibliographic Citation: |
Kim, In Song; Kosuke Imai, 2019, "Replication Data for: When Should We Use Unit Fixed Effects Regression Models for Causal Inference with Longitudinal Data?", https://doi.org/10.7910/DVN/YUM3K8, Harvard Dataverse, V1, UNF:6:xiKBfdYXpLCslGVM+Lw+jw== [fileUNF] |
|
Citation |
|
|
Title: |
Replication Data for: When Should We Use Unit Fixed Effects Regression Models for Causal Inference with Longitudinal Data? |
|
Identification Number: |
doi:10.7910/DVN/YUM3K8 |
|
Authoring Entity: |
Kim, In Song (Massachusetts Institute of Technology) |
|
Kosuke Imai (Harvard University) |
|
|
Producer: |
In Song Kim |
|
Distributor: |
Harvard Dataverse |
|
Access Authority: |
In Song Kim |
|
Depositor: |
Kim, In Song |
|
Date of Deposit: |
2018-11-21 |
|
Holdings Information: |
https://doi.org/10.7910/DVN/YUM3K8 |
|
Study Scope |
|
|
Keywords: |
Social Sciences, Panel data, Directed acyclic graph |
|
Abstract: |
Many researchers use unit fixed effects regression models as their default methods for causal inference with longitudinal data. We show that the ability of these models to adjust for unobserved time-invariant confounders comes at the expense of dynamic causal relationships, which are permitted under an alternative selection-on-observables approach. Using the nonparametric directed acyclic graph, we highlight two key causal identification assumptions of unit fixed effects models: past treatments do not directly influence current outcome, and past outcomes do not affect current treatment. Furthermore, we introduce a new nonparametric matching framework that elucidates how various unit fixed effects models implicitly compare treated and control observations to draw causal inference. By establishing the equivalence between matching and weighted unit fixed effects estimators, this framework enables a diverse set of identification strategies to adjust for unobservables in the absence of dynamic causal relationships between treatment and outcome variables. We illustrate the proposed methodology through its application to the estimation of GATT membership effects on dyadic trade volume. |
|
Notes: |
This dataset underwent an independent verification process that replicated the tables and figures in the primary article. For the supplementary materials, verification was performed solely for the successful execution of code. The verification process was carried out by the Odum Institute for Research in Social Science at the University of North Carolina at Chapel Hill. <br></br> The associated article has been awarded Open Materials and Open Data Badges. Learn more about the Open Practice Badges from the <a href="https://osf.io/tvyxz/wiki/home/" target="_blank">Center for Open Science</a>.<br></br> <img src="http://www.odum.unc.edu/archive/cos_open_data.png" alt="Open Data Badge" height="77" width="80"> <img src="http://www.odum.unc.edu/archive/cos_open_materials.png" alt="Open Materials Badge" height="77" width="80"> |
|
Methodology and Processing |
|
|
Sources Statement |
|
|
Data Access |
|
|
Disclaimer: |
The <i>American Journal of Political Science</i> and the Odum Institute for Research in Social Science are not responsible for the accuracy or quality of data uploaded within the <i>AJPS</i> Dataverse, for the use of those data, or for interpretations or conclusions based on their use. |
|
Notes: |
This dataset is made available with limited information on how it can be used. You may wish to communicate with the Contact(s) specified before use. |
|
Other Study Description Materials |
|
|
Related Publications |
|
|
Citation |
|
|
Title: |
Imai, Kosuke, and In Song Kim. 2019. “When Should We Use Unit Fixed Effects Regression Models for Causal Inference with Longitudinal Data?” <i>American Journal of Political Science</i> 63 (2): 467–90. |
|
Identification Number: |
10.1111/ajps.12417 |
|
Bibliographic Citation: |
Imai, Kosuke, and In Song Kim. 2019. “When Should We Use Unit Fixed Effects Regression Models for Causal Inference with Longitudinal Data?” <i>American Journal of Political Science</i> 63 (2): 467–90. |
|
File Description--f3323493 |
|
|
File: CountryCodeNameISO2ISO3.tab |
|
|
|
|
Notes: |
UNF:6:IO4Jq7SP7KiGIIcjl/AKpg== |
|
File Description--f3323497 |
|
|
File: gattmbr.tab |
|
|
|
|
Notes: |
UNF:6:KCBCDpTncba1cf1J6oOhRg== |
|
File Description--f3323502 |
|
|
File: TGR2007.tab |
|
|
|
|
Notes: |
UNF:6:dSv5FLpP4YYwITqci7dDkg== |
|
List of Variables: |
|
|
Variables |
|
|
f3323493 Location: |
Summary Statistics: Min. 0.0; StDev 259.4030215706084; Max. 899.0; Valid 289.0; Mean 453.19377162629706; Variable Format: numeric Notes: UNF:6:ob7BDZfsDfe+JEu1XCxw2g== |
|
f3323493 Location: |
Variable Format: character Notes: UNF:6:BHTlj4kC/9zBS7aZJh2jiw== |
|
f3323493 Location: |
Variable Format: character Notes: UNF:6:g3Nchhm2BA5Kh6f7sY1qBg== |
|
f3323493 Location: |
Variable Format: character Notes: UNF:6:WIx2bNKHTAOuoXYAQekPKA== |
|
f3323493 Location: |
Variable Format: character Notes: UNF:6:zp1ozm27a/rc4frxRnWIzw== |
|
f3323493 Location: |
Variable Format: character Notes: UNF:6:qjs2fGsBHSGNkIYel56/Pw== |
|
f3323493 Location: |
Variable Format: character Notes: UNF:6:eSmQFluaHvolEqTs2BlRYw== |
|
f3323493 Location: |
Summary Statistics: Min. 0.0; StDev 116.3311544686112; Max. 2006.0; Valid 289.0; Mean 1960.5882352941176 Variable Format: numeric Notes: UNF:6:e4oFf2DDwGZO2oZICwjozA== |
|
f3323493 Location: |
Summary Statistics: Valid 289.0; Mean 2042.3529411764705; StDev 123.71831805444974; Max. 2061.0; Min. 0.0 Variable Format: numeric Notes: UNF:6:v0cF2oUpWKA3LBEB6TL8eA== |
|
f3323497 Location: |
Variable Format: character Notes: UNF:6:EV89qdng4okufDtg9U+XzQ== |
|
f3323497 Location: |
Summary Statistics: Valid 8559.0; Mean 493.51349456711483; StDev 247.66077991070654; Min. 111.0; Max. 968.0 Variable Format: numeric Notes: UNF:6:Yb9sSDC+0Rc4rHlkhUVVeQ== |
|
f3323497 Location: |
Summary Statistics: Valid 8559.0; Mean 1975.7249678700782; Max. 2002.0; Min. 1948.0; StDev 15.279741625188905; Variable Format: numeric Notes: UNF:6:4zCTKJbMWvMu62u7KDGI6A== |
|
f3323497 Location: |
Variable Format: character Notes: UNF:6:pWRpYtb8KGkjX0Q3w46Dag== |
|
f3323502 Location: |
Summary Statistics: Valid 234597.0; Min. 111.0; Max. 964.0; StDev 189.23043033444364; Mean 295.07338116038954 Variable Format: numeric Notes: UNF:6:47iTPndjLshnQa1niWyfrg== |
|
f3323502 Location: |
Summary Statistics: StDev 223.20255234189833; Min. 112.0; Valid 234597.0; Mean 571.5029944970356; Max. 968.0 Variable Format: numeric Notes: UNF:6:R6cE8uXwwhMgIVrcPlHMDA== |
|
f3323502 Location: |
Summary Statistics: Valid 234597.0; Mean 1980.9579491638838; StDev 12.471676750509793; Min. 1948.0; Max. 1999.0; Variable Format: numeric Notes: UNF:6:xL1JHsZmmU+VrU3PvWnC9g== |
|
f3323502 Location: |
Summary Statistics: Valid 234597.0; StDev 0.043755134915226264; Mean 0.0019181830969760836; Max. 1.0; Min. 0.0 Variable Format: numeric Notes: UNF:6:9tTeU4+t9MsmfMlsOD8kng== |
|
f3323502 Location: |
Summary Statistics: Valid 234597.0; Mean 0.014066676044464892; StDev 0.11776614024113874; Min. 0.0; Max. 1.0; Variable Format: numeric Notes: UNF:6:SjzZh36PQ/IhcnFWDF01tw== |
|
f3323502 Location: |
Summary Statistics: Valid 234597.0; Min. -16.090465545654297; Mean 10.061658142028737; Max. 20.811248779296875; StDev 3.335954515429326; Variable Format: numeric Notes: UNF:6:4bnKISELlQfVaDis3GHB+Q== |
|
f3323502 Location: |
Summary Statistics: StDev 0.11990889888771851; Valid 234597.0; Mean 0.014590979424296638; Max. 1.0; Min. 0.0; Variable Format: numeric Notes: UNF:6:YwknP4QeXLBO5lL4UOHujQ== |
|
f3323502 Location: |
Summary Statistics: Min. 35.38759994506836; StDev 2.6761922683780095; Valid 234597.0; Mean 47.881033842767195; Max. 59.089962005615234 Variable Format: numeric Notes: UNF:6:pObCP7ClPITJ/XHTDCtpxw== |
|
f3323502 Location: |
Summary Statistics: Min. 9.716513633728027; StDev 1.5036339116825252; Max. 21.59728240966797; Valid 234597.0; Mean 16.03406676905609; Variable Format: numeric Notes: UNF:6:IUmQnsWCv/erYOAor+b1iw== |
|
f3323502 Location: |
Summary Statistics: StDev 0.4217263215815185; Valid 234597.0; Max. 1.0; Mean 0.23139682093140046; Min. 0.0 Variable Format: numeric Notes: UNF:6:toq3xoNvhwZZnS+qbW4knA== |
|
f3323502 Location: |
Summary Statistics: StDev 0.47629789926128274; Valid 234597.0; Max. 1.0; Mean 0.6521225761624866; Min. 0.0 Variable Format: numeric Notes: UNF:6:iPN8M5Lv62JZHsdnDcWPHQ== |
|
f3323502 Location: |
Summary Statistics: Max. 1.0; StDev 0.1991225391726441; Mean 0.04136029019975884; Valid 234597.0; Min. 0.0 Variable Format: numeric Notes: UNF:6:GuSLa5itLd9d2sc61HRTxg== |
|
f3323502 Location: |
Summary Statistics: Min. 0.0; Valid 234597.0; Max. 1.0; StDev 0.46104803058972244; Mean 0.30651713363777316 Variable Format: numeric Notes: UNF:6:JJPJ3WAY8z4CoqhN3j/TrQ== |
|
f3323502 Location: |
Summary Statistics: Min. 0.0; StDev 0.400092257095938; Max. 1.0; Mean 0.799878088807266; Valid 234597.0 Variable Format: numeric Notes: UNF:6:oTlj2HvkFcgOSzfYf8yuNg== |
|
f3323502 Location: |
Summary Statistics: Min. 0.0; Max. 1.0; Mean 0.5873434016632708; Valid 234597.0; StDev 0.49231307450477013; Variable Format: numeric Notes: UNF:6:yR1EYxsc3wURuZ8Q7LxSuQ== |
|
f3323502 Location: |
Summary Statistics: StDev 0.4995859974254592; Mean 0.47963102682466585; Min. 0.0; Valid 234597.0; Max. 1.0 Variable Format: numeric Notes: UNF:6:mEuRGXWF5XTIT0+VvYbNGg== |
|
f3323502 Location: |
Summary Statistics: Min. 111112.0; Valid 234597.0; StDev 189336.6114240276; Mean 295644.88415406394; Max. 964968.0 Variable Format: numeric Notes: UNF:6:css32LnHETGHoSo8GDyinQ== |
|
Label: |
BA_estimation.R |
|
Notes: |
type/x-r-syntax |
|
Label: |
Codebook.pdf |
|
Notes: |
application/pdf |
|
Label: |
DyadFE_estimation.R |
|
Notes: |
type/x-r-syntax |
|
Label: |
Figure4.R |
|
Notes: |
type/x-r-syntax |
|
Label: |
Figure5.R |
|
Notes: |
type/x-r-syntax |
|
Label: |
README.txt |
|
Notes: |
text/plain |
|
Label: |
Table2.R |
|
Notes: |
type/x-r-syntax |
|
Label: |
Table3.R |
|
Notes: |
type/x-r-syntax |
|
Label: |
Table4.R |
|
Notes: |
type/x-r-syntax |
|
Label: |
wfe_1.7.tar.gz |
|
Notes: |
application/x-gzip |