{"id":6435082,"identifier":"DVN/X4Y2FL","persistentUrl":"https://doi.org/10.7910/DVN/X4Y2FL","protocol":"doi","authority":"10.7910","separator":"/","publisher":"Harvard Dataverse","publicationDate":"2023-12-19","storageIdentifier":"file://10.7910/DVN/X4Y2FL","datasetType":"dataset","datasetVersion":{"id":331779,"datasetId":6435082,"datasetPersistentId":"doi:10.7910/DVN/X4Y2FL","storageIdentifier":"file://10.7910/DVN/X4Y2FL","versionNumber":1,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","deaccessionLink":"","UNF":"UNF:6:1hQlAh8RGzLi+kKnI82oXw==","lastUpdateTime":"2023-12-19T12:58:16Z","releaseTime":"2023-12-19T12:58:16Z","createTime":"2022-08-29T15:37:54Z","publicationDate":"2023-12-19","citationDate":"2023-12-19","termsOfUse":"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.","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.","fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Replication Data for: Differentially Private Survey Research"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Evans, Georgina"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Harvard University"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"King, Gary"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Harvard University"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Smith, Adam"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Boston University"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Thakurta, Abhradeep"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of California Santa Cruz"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Evans, Georgina"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"Harvard University"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"georginaevans@g.harvard.edu"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"Survey researchers have long protected the privacy of respondents via de-identification (removing names and other directly identifying information) before sharing data. Although these procedures help, recent research demonstrates that they fail to protect respondents from intentional re-identification attacks, a problem that threatens to undermine vast survey enterprises in academia, government, and industry. This is especially a problem in political science because political beliefs are not merely the subject of our scholarship; they represent some of the most important information respondents want to keep private. We confirm the problem in practice by re-identifying individuals from a survey about a controversial referendum declaring life beginning at conception. We build on the concept of “differential privacy” to offer new data sharing procedures with mathematical guarantees for protecting respondent privacy and statistical validity guarantees for social scientists analyzing differentially private data. The cost of these new procedures is larger standard errors, which can be overcome with somewhat larger sample sizes."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2022-08-29"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Social Sciences"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Privacy"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Statistics"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Inference"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Evans, Georgina, Gary King, Adam D. Smith, and Abhradeep Thakurta. [date]. \"Differentially Private Survey Research.\" <i>American Journal of Political Science</i> Forthcoming. <a href=\"http://ajps.org/\" target=\"_blank\">http://ajps.org/</a>"}}]},{"typeName":"notesText","multiple":false,"typeClass":"primitive","value":"This dataset underwent an independent verification process, complying with the AJPS Verification Policy updated June 2023, 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.\n<br></br>\nThe associated article has been awarded the Open Materials Badge. 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>\n<img src=\"https://odum.unc.edu/files/2020/03/OpenMaterials_PR-1.png\" alt=\"Open Materials Badge\" height=\"77\" width=\"80\">"},{"typeName":"producer","multiple":true,"typeClass":"compound","value":[{"producerName":{"typeName":"producerName","multiple":false,"typeClass":"primitive","value":"Georgina Evans"}}]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Evans, Georgina"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2022-08-29"},{"typeName":"dataSources","multiple":true,"typeClass":"primitive","value":["Rosenfeld, Bryn; Imai, Kosuke; Shapiro, Jacob, 2015, \"Replication Data for: An Empirical Validation Study of Popular Survey Methodologies for Sensitive Questions\", https://doi.org/10.7910/DVN/29911, Harvard Dataverse, V3, UNF:5:wfSfR7xnbL9XigVosud4zA== [fileUNF]"]}]},"geospatial":{"displayName":"Geospatial Metadata","name":"geospatial","fields":[]},"journal":{"displayName":"Journal Metadata","name":"journal","fields":[{"typeName":"journalVolumeIssue","multiple":true,"typeClass":"compound","value":[{"journalVolume":{"typeName":"journalVolume","multiple":false,"typeClass":"primitive","value":"Forthcoming"}}]}]}},"files":[{"label":"dp_hier_hist.R","restricted":false,"directoryLabel":"udps_file/utils","version":1,"datasetVersionId":331779,"dataFile":{"id":7673752,"persistentId":"","filename":"dp_hier_hist.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":8177,"storageIdentifier":"s3://dvn-cloud:18c60ce4198-8d3855ecc337","rootDataFileId":-1,"md5":"5cf51614afb081e43f29e64217385f82","checksum":{"type":"MD5","value":"5cf51614afb081e43f29e64217385f82"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"em_code.R","restricted":false,"directoryLabel":"udps_file/utils","version":1,"datasetVersionId":331779,"dataFile":{"id":7673750,"persistentId":"","filename":"em_code.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":6994,"storageIdentifier":"s3://dvn-cloud:18c60ce41a6-3cd0a20e1eb7","rootDataFileId":-1,"md5":"8677319388ded3ff34608a88804880f7","checksum":{"type":"MD5","value":"8677319388ded3ff34608a88804880f7"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"fig2a.R","restricted":false,"directoryLabel":"udps_file","version":1,"datasetVersionId":331779,"dataFile":{"id":7673758,"persistentId":"","filename":"fig2a.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":2611,"storageIdentifier":"s3://dvn-cloud:18c60ce4163-55c5d7f88fdb","rootDataFileId":-1,"md5":"e51fe3d91762beae8aa50dd775bdbc0e","checksum":{"type":"MD5","value":"e51fe3d91762beae8aa50dd775bdbc0e"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"fig2b.R","restricted":false,"directoryLabel":"udps_file","version":1,"datasetVersionId":331779,"dataFile":{"id":7673745,"persistentId":"","filename":"fig2b.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":2114,"storageIdentifier":"s3://dvn-cloud:18c60ce4170-9f5914adf257","rootDataFileId":-1,"md5":"3d9bb037bc783142a440c4b7d22455b2","checksum":{"type":"MD5","value":"3d9bb037bc783142a440c4b7d22455b2"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"fig3.R","restricted":false,"directoryLabel":"udps_file","version":1,"datasetVersionId":331779,"dataFile":{"id":7673751,"persistentId":"","filename":"fig3.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":1972,"storageIdentifier":"s3://dvn-cloud:18c60ce4184-7df3380a4377","rootDataFileId":-1,"md5":"167a25170a8bcb6a74807f9dd21b3a3b","checksum":{"type":"MD5","value":"167a25170a8bcb6a74807f9dd21b3a3b"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"fig4.R","restricted":false,"directoryLabel":"udps_file","version":1,"datasetVersionId":331779,"dataFile":{"id":7673756,"persistentId":"","filename":"fig4.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":5436,"storageIdentifier":"s3://dvn-cloud:18c60ce4190-208495a2301d","rootDataFileId":-1,"md5":"719c530790089bca14d6872c237e3d20","checksum":{"type":"MD5","value":"719c530790089bca14d6872c237e3d20"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"k_sims.tab","restricted":false,"directoryLabel":"udps_file/data","version":3,"datasetVersionId":331779,"dataFile":{"id":7673753,"persistentId":"","filename":"k_sims.tab","contentType":"text/tab-separated-values","friendlyType":"Tab-Delimited","filesize":100230,"storageIdentifier":"s3://dvn-cloud:18c60ce41c4-a8676de925ec","originalFileFormat":"text/csv","originalFormatLabel":"Comma Separated Values","originalFileSize":100319,"originalFileName":"k_sims.csv","UNF":"UNF:6:khzDUos3LKNK++SA0qos2g==","rootDataFileId":-1,"md5":"a1d3f915a60e3f6ffcfa58db30a3c1f3","checksum":{"type":"MD5","value":"a1d3f915a60e3f6ffcfa58db30a3c1f3"},"tabularData":true,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"logit_regression.R","restricted":false,"directoryLabel":"udps_file/utils","version":1,"datasetVersionId":331779,"dataFile":{"id":7673748,"persistentId":"","filename":"logit_regression.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":1747,"storageIdentifier":"s3://dvn-cloud:18c60ce419f-ff8e235d86d2","rootDataFileId":-1,"md5":"b4957bae19dfcfaf7b55e2d71ecd5a63","checksum":{"type":"MD5","value":"b4957bae19dfcfaf7b55e2d71ecd5a63"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"main_sims.tab","restricted":false,"directoryLabel":"udps_file/data","version":3,"datasetVersionId":331779,"dataFile":{"id":7673746,"persistentId":"","filename":"main_sims.tab","contentType":"text/tab-separated-values","friendlyType":"Tab-Delimited","filesize":202745,"storageIdentifier":"s3://dvn-cloud:18c60ce41ba-6e75c362d954","originalFileFormat":"text/csv","originalFormatLabel":"Comma Separated Values","originalFileSize":204725,"originalFileName":"main_sims.csv","UNF":"UNF:6:ybdf76nGv0zkZnO8zgTgPA==","rootDataFileId":-1,"md5":"dca0f9351c8cbe66b28a18255d8e5927","checksum":{"type":"MD5","value":"dca0f9351c8cbe66b28a18255d8e5927"},"tabularData":true,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"poisson_regression.R","restricted":false,"directoryLabel":"udps_file/utils","version":1,"datasetVersionId":331779,"dataFile":{"id":7673755,"persistentId":"","filename":"poisson_regression.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":1850,"storageIdentifier":"s3://dvn-cloud:18c60ce41b3-cfbb902ce88c","rootDataFileId":-1,"md5":"443ff0a7cd043fe41cd6f4bf8a472c6b","checksum":{"type":"MD5","value":"443ff0a7cd043fe41cd6f4bf8a472c6b"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"README","restricted":false,"directoryLabel":"udps_file","version":1,"datasetVersionId":331779,"dataFile":{"id":7673747,"persistentId":"","filename":"README","contentType":"text/plain; charset=US-ASCII","friendlyType":"Plain Text","filesize":2939,"storageIdentifier":"s3://dvn-cloud:18c60ce4177-8f61cfea5bbc","rootDataFileId":-1,"md5":"397bc77ab91b350e6ea2abfd7b04613b","checksum":{"type":"MD5","value":"397bc77ab91b350e6ea2abfd7b04613b"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"RUN_ALL.R","restricted":false,"directoryLabel":"udps_file","version":1,"datasetVersionId":331779,"dataFile":{"id":7673754,"persistentId":"","filename":"RUN_ALL.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":676,"storageIdentifier":"s3://dvn-cloud:18c60ce418a-04d381567ec9","rootDataFileId":-1,"md5":"778582e16a775fee2356fec2b2167820","checksum":{"type":"MD5","value":"778582e16a775fee2356fec2b2167820"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"run_simulations_k.R","restricted":false,"directoryLabel":"udps_file","version":1,"datasetVersionId":331779,"dataFile":{"id":7673749,"persistentId":"","filename":"run_simulations_k.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":3033,"storageIdentifier":"s3://dvn-cloud:18c60ce4169-40ab114f5e51","rootDataFileId":-1,"md5":"7e50c984ffb859bab5b27e55db4dd657","checksum":{"type":"MD5","value":"7e50c984ffb859bab5b27e55db4dd657"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"run_simulations.R","restricted":false,"directoryLabel":"udps_file","version":1,"datasetVersionId":331779,"dataFile":{"id":7673744,"persistentId":"","filename":"run_simulations.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":2044,"storageIdentifier":"s3://dvn-cloud:18c60ce415d-94cd37b98fcc","rootDataFileId":-1,"md5":"f29a08c6be0cfb1a3fc3138dce1f7c3c","checksum":{"type":"MD5","value":"f29a08c6be0cfb1a3fc3138dce1f7c3c"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"simulation_functions.R","restricted":false,"directoryLabel":"udps_file","version":1,"datasetVersionId":331779,"dataFile":{"id":7673757,"persistentId":"","filename":"simulation_functions.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":2696,"storageIdentifier":"s3://dvn-cloud:18c60ce4156-8060688d6e8a","rootDataFileId":-1,"md5":"69cd3aaf53f8c81dc6ab70f360dac2e0","checksum":{"type":"MD5","value":"69cd3aaf53f8c81dc6ab70f360dac2e0"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}},{"label":"util_functions.R","restricted":false,"directoryLabel":"udps_file/utils","version":1,"datasetVersionId":331779,"dataFile":{"id":7673759,"persistentId":"","filename":"util_functions.R","contentType":"type/x-r-syntax","friendlyType":"R Syntax","filesize":2299,"storageIdentifier":"s3://dvn-cloud:18c60ce41ad-da7acdd3c069","rootDataFileId":-1,"md5":"f22711fccd184cc8746d12ee95c13994","checksum":{"type":"MD5","value":"f22711fccd184cc8746d12ee95c13994"},"tabularData":false,"creationDate":"2023-12-12","publicationDate":"2023-12-19","fileAccessRequest":false}}],"citation":"Evans, Georgina; King, Gary; Smith, Adam; Thakurta, Abhradeep, 2023, \"Replication Data for: Differentially Private Survey Research\", https://doi.org/10.7910/DVN/X4Y2FL, Harvard Dataverse, V1, UNF:6:1hQlAh8RGzLi+kKnI82oXw== [fileUNF]"}}