Skip to main content Accessibility help
×
Home
Hostname: page-component-684899dbb8-8hm5d Total loading time: 0.268 Render date: 2022-05-19T22:58:00.778Z Has data issue: true Feature Flags: { "shouldUseShareProductTool": true, "shouldUseHypothesis": true, "isUnsiloEnabled": true, "useRatesEcommerce": false, "useNewApi": true }

Machine Learning Predictions as Regression Covariates

Published online by Cambridge University Press:  11 November 2020

Christian Fong
Affiliation:
Assistant Professor, Department of Political Science, University of Michigan, Ann Arbor, MI, USA. Email: cjfong@umich.edu
Matthew Tyler*
Affiliation:
Ph.D. Candidate, Department of Political Science, Stanford University, Stanford, CA, USA. Email: mdtyler@stanford.edu
*
Corresponding author Matthew Tyler

Abstract

In text, images, merged surveys, voter files, and elsewhere, data sets are often missing important covariates, either because they are latent features of observations (such as sentiment in text) or because they are not collected (such as race in voter files). One promising approach for coping with this missing data is to find the true values of the missing covariates for a subset of the observations and then train a machine learning algorithm to predict the values of those covariates for the rest. However, plugging in these predictions without regard for prediction error renders regression analyses biased, inconsistent, and overconfident. We characterize the severity of the problem posed by prediction error, describe a procedure to avoid these inconsistencies under comparatively general assumptions, and demonstrate the performance of our estimators through simulations and a study of hostile political dialogue on the Internet. We provide software implementing our approach.

Type
Article
Copyright
© The Author(s) 2020. Published by Cambridge University Press on behalf of the Society for Political Methodology

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Footnotes

Edited by Jeff Gill

References

Aigner, D. J. (1973). “Regression with a Binary Independent Variable Subject to Errors of Observation.” Journal of Econometrics 1(1):4959.CrossRefGoogle Scholar
Anastasopoulos, J., Badani, D., Lee, C., Ginosar, S., and Ryland Williams, J. (2016). “Photographic Home Styles in Congress: A Computer Vision Approach.” https://arxiv.org/pdf/1611.09942.pdf.Google Scholar
Cameron, A. C. and Trivedi, P. K. (2005). Microeconometrics: Methods and Applications. Cambridge: Cambridge University Press.CrossRefGoogle Scholar
Dimitriadou, E., Hornik, K., Leisch, F., Meyer, D., Weingessel, A., and Leisch, M. F. (2009). “Package ‘e1071’.” R Software package, http://cran.rproject.org/web/packages/e1071/index.html.Google Scholar
Fong, C., Malhotra, N., and Margalit, Y. (2019). “Political legacies: Understanding their singificance to contemporary political debates.” PS: Political Science & Politics 52(3):451456.Google Scholar
Fong, C. and Tyler, M. (2020a). “Replication Data for: Machine Learning Predictions as Regression Covariates.” Code Ocean, V1. https://doi.org/10.24433/CO.3552504.v1.CrossRefGoogle Scholar
Fong, C. and Tyler, M. (2020b). “Replication Data for: Machine Learning Predictions as Regression Covariates.” https://doi.org/10.7910/DVN/QQHBHY, Harvard Dataverse, V1,UNF:6:vgF7Ffh39tB+eQJxHpax7A== [fileUNF].Google Scholar
Grimmer, J., Messing, S., and Westwood, S. J. (2012). “How Words and Money Cultivate a Personal Vote: The Effect of Legislator Credit Claiming on Constituent Credit Allocation.” American Political Science Review 106(4):117.CrossRefGoogle Scholar
Grumbach, J. M. and Sahn, A. (2020). “Race and representation in campaign finance.” American Political Science Review 114(1):206221.CrossRefGoogle Scholar
Hopkins, D. J. and King, G. (2010). “A method of automated nonparametric content analysis for social science.” American Journal of Political Science 54(1):229247.CrossRefGoogle Scholar
Ibrahim, J. G., Chen, M.-H., Lipsitz, S. R., and Herring, A. H. (2005). “Missing-data methods for generalized linear models: A comparative review.” Journal of the American Statistical Association 100(469):332346.CrossRefGoogle Scholar
Imai, K. and Khanna, K. (2016). “Improving Ecological Inference by Predicting Individual Ethnicity from Voter Registration Records.” Political Analysis 24:263272.CrossRefGoogle Scholar
Iyyer, M., Enns, P., Boyd-Graber, J., and Resnik, P. (2014). “Political ideology detection using recursive neural networks.” In Proceedings of the Association for Computational Linguistics, pp. 111.Google Scholar
Jamal, A. A., Keohane, R. O., Romney, D., and Tingley, D. (2015). “Anti-Americanism and Anti-Interventionism in Arabic Twitter Discourses.” Perspectives on Politics 13(1):5573.CrossRefGoogle Scholar
Jerzak, C. T., King, G., and Strezhnev, A. (2018). “An Improved Method of Automated Nonparametric Content Analysis for Social Science.” https://gking.harvard.edu/files/gking/files/word.pdf.Google Scholar
Kane, T. J., Rouse, C. E., and Staiger, D. (1999). Estimating Returns to Schooling When Schooling Is Misreported. National Bureau of Economic Research.CrossRefGoogle Scholar
King, G., Pan, J., and Roberts, M. E. (2013). “How Censorship in China Allows Government Criticism but Silences Collective Expression.” American Political Science Review 107(2):326343.CrossRefGoogle Scholar
Munger, K. (2017). “Experimentally Reducing Partisan Incivility on Twitter.” http://kmunger.github.io/pdfs/jmp.pdf.Google Scholar
Mutz, D. C. and Reeves, B. (2005). “The new videomalaise: Effects of televised incivility on political trust.” American Political Science Review 99(1):115.CrossRefGoogle Scholar
Rubin, D. B. (2004). Multiple Imputation for Nonresponse in Surveys. Hoboken, NJ:John Wiley & Sons.Google Scholar
Socher, R., Perelygin, A., and Wu, J. (2013). “Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank.” In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Seattle, Washington, pp. 16311642. Seattle, Washington.Google Scholar
Stewart, B. M. and Zhukov, Y. M. (2009). “Use of Force and Civil–Military Relations in Russia: An Automated Content Analysis.” Small Wars & Insurgencies 20(2):319343.CrossRefGoogle Scholar
Theocharis, Y., Barberá, P., Fazekas, Z., Popa, S. A., and Parnet, O. (2016). “A Bad Workman Blames His Tweets: The Consequences of Citizens’ Uncivil Twitter Use when Interacting with Party Candidates.” Journal of communication 66(6):10071031.CrossRefGoogle Scholar
Supplementary material: Link

Fong and Tyler Dataset

Link
Supplementary material: PDF

Fong and Tyler supplementary material

Online Appendix

Download Fong and Tyler supplementary material(PDF)
PDF 617 KB
1
Cited by

Save article to Kindle

To save this article to your Kindle, first ensure coreplatform@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about saving to your Kindle.

Note you can select to save to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be saved to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

Find out more about the Kindle Personal Document Service.

Machine Learning Predictions as Regression Covariates
Available formats
×

Save article to Dropbox

To save this article to your Dropbox account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you used this feature, you will be asked to authorise Cambridge Core to connect with your Dropbox account. Find out more about saving content to Dropbox.

Machine Learning Predictions as Regression Covariates
Available formats
×

Save article to Google Drive

To save this article to your Google Drive account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you used this feature, you will be asked to authorise Cambridge Core to connect with your Google Drive account. Find out more about saving content to Google Drive.

Machine Learning Predictions as Regression Covariates
Available formats
×
×

Reply to: Submit a response

Please enter your response.

Your details

Please enter a valid email address.

Conflicting interests

Do you have any conflicting interests? *