{"status":"OK","data":{"id":420820,"identifier":"5CZLAW","persistentUrl":"https://doi.org/10.34894/5CZLAW","protocol":"doi","authority":"10.34894","separator":"/","publisher":"DataverseNL","publicationDate":"2024-05-07","storageIdentifier":"surf://10.34894/5CZLAW","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9999,"datasetType":"dataset","locks":[],"latestVersion":{"id":27611,"datasetId":420820,"datasetPersistentId":"doi:10.34894/5CZLAW","datasetType":"dataset","storageIdentifier":"surf://10.34894/5CZLAW","versionNumber":1,"internalVersionNumber":21,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","deaccessionLink":"","lastUpdateTime":"2024-05-07T16:31:20Z","releaseTime":"2024-05-07T16:31:20Z","createTime":"2024-04-24T12:19:35Z","publicationDate":"2024-05-07","citationDate":"2024-05-07","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9999,"termsOfUse":"MIT License\n\nCopyright (c) 2019 Edo\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.","fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Replication Data for: Simplifying Imputation with Many Predictors in MICE Using Principal Component Analysis"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Costantini, Edoardo"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Tilburg University"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0001-9581-9913"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Costantini, Edoardo"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"Tilburg University"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"The data package for the Ph.D. thesis titled <i>Simplifying Imputation with Many Predictors in MICE Using Principal Component Analysis</i> written by Edoardo Costantini."}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Social Sciences"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Missing datay"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Imputation"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"PCA"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Survey"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Social sciences"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Tilburg University"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Costantini, E., Lang, K. M., Reeskens, T., & Sijtsma, K. (2023). High-dimensional imputation for the social sciences: A comparison of state-of-the-art methods. Sociological Methods & Research."},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"doi"},"publicationIDNumber":{"typeName":"publicationIDNumber","multiple":false,"typeClass":"primitive","value":"10.1177/00491241231200194"}},{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Costantini, E., Lang, K. M., Sijtsma, K., & Reeskens, T. (2024). Solving the manyvariables problem in MICE with principal component regression. Behavior Research Methods, 56(3), 1715–1737."},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"doi"},"publicationIDNumber":{"typeName":"publicationIDNumber","multiple":false,"typeClass":"primitive","value":"10.3758/s13428-023-02117-1"}},{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Costantini, E., Lang, K. M., & Sijtsma, K. (2023). Supervised dimensionality reduction for multiple imputation by chained equations. arXiv preprint."},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"doi"},"publicationIDNumber":{"typeName":"publicationIDNumber","multiple":false,"typeClass":"primitive","value":"10.48550/arXiv.2309.01608"}}]},{"typeName":"notesText","multiple":false,"typeClass":"primitive","value":"MD files in this dataset can be opened using any text editor. The MACOSX folder in the dataset can be ignored as it was created automatically by OS X creating the zip file. <br><br>\nThe general README.md file in this dataset describes the contents of the data package containing five folders:\n<ul>\n<li>'chapter-2` contains the code and data files to reproduce the results for the second chapter of the thesis.\n<li>'chapter-3` contains the code and data files to reproduce the results for the third chapter of the thesis.\n<li>'hapter-4` contains the code and data files to reproduce the results for the fourth chapter of the thesis.\n<li>'chapter-5` contains the code and data files to reproduce the results for the fifth chapter of the thesis.\n<li>`thesis` contains the code and data files to reproduce the exact figures and tables in the thesis.\n</ul>\n<br>\nMetadata and data collection<br>\n\nFor every chapter in the thesis, the record of who worked on which files is reported as a `.csv` file registering the **git log** of every project. The `.csv` files were obtained with the following Zsh commands:<br>\n```zsh<br>\necho changes, date, contributor, message > log-changes.csv\ngit log --name-status --pretty=format:%h,%ai,%aL,%s >> log-changes.csv\n```\n<br><br>\nTwo main **datasets** were used throughout the chapters of the thesis:<br>\n<ul>\n<li> *European Value Study* questionnaire data, as available on the GESIS portal (https://doi.org/10.4232/1.13511)\n<li>*Fireworks disaster data*, as made available in the CRAN version of the R package *mice* (see [here](https://github.com/cran/mice/blob/master/data/fdd.rda)), originally collected by de Roos, C., Greenwald, R., den Hollander-Gijsman, M., Noorthoorn, E., van Buuren, S., & de Jongh, A. (2011). A randomised comparison of cognitive behavioural therapy (CBT) and eye movement desensitisation and reprocessing (EMDR) in disaster-exposed children. *European Journal of Psychotraumatology*, *2*(1). https://doi.org/10.3402/ejpt.v2i0.5694\n</ul>\nThe rest of the data used in this thesis were simulated by computer scripts to evaluate the properties of different statistical approaches.\n<br><br>\n## Raw database<br><br>\n\nThe README file in every folder provides instructions on how to load the data used and which computer scripts to run to process the data. The versions of the data used for the analysis by the author are available in the respective chapter folders with one exception. The European Values Study data used in Chapters 2 and 4 could not be shared because of explicit terms of use limitations. However, the data are stored by GESIS and made available via password-protected online access, for which user registration is required. The DOI https://doi.org/10.4232/1.13511, also provided in the chapters using these data, points to the exact version of the data file.\n<p>\n## Material<br><br>\nAll material is available in the chapter folders. The README files contained in every chapter folder describe how to reproduce results.\n<p>\n## Statistical processing<br><br>\nAll computer scripts used to perform statistical processing are available in the chapter folders. The README files contained in every chapter folder describe how to reproduce results.\n<p>\n## Processed database<br><br>\nAll processed data used to generate the figures and tables in the thesis are available in the folder `thesis/data/`.\n<p>\n## Accepted or published manuscript or publication\n<br>\nDOIs for the three published chapters:<Br>\n<ul>\n<li>Chapter 2: https://doi.org/10.1177/00491241231200194\n<li>Chapter 3: https://doi.org/10.3758/s13428-023-02117-1\n<li>Chapter 4: https://doi.org/10.48550/arXiv.2309.01608\n</ul>\n\n## Disclaimer<br><br>\nIf any issues arise in replicating results while following instructions provided in this data package please refer to the instructions described in the chapters of the thesis.\n<br><br>\nThe README files of each chapter contain information on:\n<ul>\n<li>Name of chapter and summary\n<lI>Contents of the directory including mentioning of the subfolders\n<li>How to replicate results\n<li>Running the simulations\n<li>Simulation study\n<li>Collinearity study\n<li>EVS resampling study\n<li>Obtaining the plots and tables\n</ul>"},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["English"]},{"typeName":"producer","multiple":true,"typeClass":"compound","value":[{"producerName":{"typeName":"producerName","multiple":false,"typeClass":"primitive","value":"Tilburg University"}}]},{"typeName":"distributor","multiple":true,"typeClass":"compound","value":[{"distributorName":{"typeName":"distributorName","multiple":false,"typeClass":"primitive","value":"DataverseNL"}}]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Costantini, Edoardo"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2024-04-24"},{"typeName":"kindOfData","multiple":true,"typeClass":"primitive","value":["Miscellaneous data (R scripts, R packages, databases, documentation)"]},{"typeName":"dataSources","multiple":true,"typeClass":"primitive","value":["Two main datasets were used throughout the chapters of the thesis:\n<ul>\n<li>*European Value Study* questionnaire data, as available on the GESIS portal (https://doi.org/10.4232/1.13511)\n<li>*Fireworks disaster data*, as made available in the CRAN version of the R package *mice* (see [here](https://github.com/cran/mice/blob/master/data/fdd.rda)), originally collected by de Roos, C., Greenwald, R., den Hollander-Gijsman, M., Noorthoorn, E., van Buuren, S., & de Jongh, A. (2011). A randomised comparison of cognitive behavioural therapy (CBT) and eye movement desensitisation and reprocessing (EMDR) in disaster-exposed children. *European Journal of Psychotraumatology*, *2*(1). https://doi.org/10.3402/ejpt.v2i0.5694\n</ul>\nThe rest of the data used in this thesis were simulated by computer scripts to evaluate the properties of different statistical approaches."]}]},"dansDataVaultMetadata":{"displayName":"Data Vault Metadata","name":"dansDataVaultMetadata","fields":[{"typeName":"dansDataversePid","multiple":false,"typeClass":"primitive","value":"doi:10.34894/5CZLAW"},{"typeName":"dansDataversePidVersion","multiple":false,"typeClass":"primitive","value":"1.0"},{"typeName":"dansBagId","multiple":false,"typeClass":"primitive","value":"urn:uuid:ce152b09-3855-4790-809d-760f89ce583b"},{"typeName":"dansNbn","multiple":false,"typeClass":"primitive","value":"urn:nbn:nl:ui:13-882d6d42-9fbd-4012-afaf-fbe8b0ce06e7"}]}},"files":[{"description":"Compressed data package.","label":"data-package.zip","restricted":false,"version":1,"datasetVersionId":27611,"dataFile":{"id":420821,"persistentId":"","filename":"data-package.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":15738221,"description":"Compressed data package.","storageIdentifier":"surf://store:18f10044351-01aa7a8af072","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"3b8a87606141b6706fc4471f7e3475bd17b63c2a"},"tabularData":false,"creationDate":"2024-04-24","publicationDate":"2024-05-07","lastUpdateTime":"2024-05-07T16:31:20Z","fileAccessRequest":false}}]}}}