[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118221-en":3,"doc-seo-118221-105":30,"detail-sidebar-cat-0-en-105":82},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118221,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Examining Regression Assumption Violations in Machine Learning Models - Using the Wisconsin Longitudinal Study Dataset","Poster research examines how violations of linear regression assumptions affect machine learning model reliability in social science contexts. Using the Wisconsin Longitudinal Study dataset with N>2,000, the study identifies departures related to homoscedasticity and normality of residuals, while other assumptions remain satisfied. Results are replicated from prior work and extended using three supervised learning models. Monte Carlo simulation (N=3000) with multiple replications generates data with known predictors and outcomes to evaluate performance changes, false positives/negatives, and model fit implications.","Hope College  \n4-12-2024  \nExamining Regression Assumption Violations in MachineLearning Models Using the Wisconsin Longitudinal Study Dataset  \nGrace Mooney AndersonHope College  \nMelia Brewer  \nHope College  \nFollow this and additional works at:https://digitalcommons.hope.edu/curca_23  \nPart of the Psychology Commons  \nRecommended Citation  \nRepository citation:Anderson,Grace Mooney and Brewer,Melia,\"Examining Regression AssumptionViolations in Machine Learning Models Using the Wisconsin Longitudinal Study Dataset\"(2024).23rdAnnual A.Paul and Carol C.Schaap Celebration of Undergraduate Research and Creative Activity (2024).Paper 3.  \nhttps://digitalcommons.hope.edu/curca_23/3April 12,2024.Copyright ◎2024 Hope College,Holland,Michigan.  \nThis Poster is brought to you for free and open access by the The A.Pauland Carol C.Schaap Celebration ofUndergraduate Research and Creative Activity at Hope College Digital Commons.It has been accepted for inclusionin 23rd Annual A.Paul and Carol C.Schaap Celebration of Undergraduate Research and Creative Activity (2024)byan authorized administrator of Hope College Digital Commons.For more information,please contactdigitalcommons@hope.edu,barneycj@hope.edu.  \nnT  \nU        Examining RegressIon ASSumption Vi0lations in Machine Learning M  odelsC O LL E G EUsing the Wisconsin Longitudinal Study Dataset  \nGrace Mooney Anderson,Melia Brewer,&Robert D.Henry (faculty mentor)  \n# Results\n\nResults  \n# Introduction\n\nNormality of Residuals  \n● Machine learning (ML)is becoming increasinglyrelevant in the social sciences  \nDots should fall along the line  \n● Many who use ML models do not verify the  \nassumptions of linear regression (Yarkoni&Westfall,2017)  \n● We will use a large dataset(N>2,000)and replicate thefindings of an accompanying study and replicate thesefindings using ML  \nStandard Normal Distribution Quantiles  \nWithin the WLS dataset,we found violations of the assumptions of  \nhomoscedasticity(above)and normality of residuals (right).All  \n● We will then simulate a dataset  \n# Discussion\n\nother assumptions were met.  \n● We hypothesized that the reliability of ML is dampenedwith the presence of these violations  \nClark and  \nLinear  \nRegularized Support Vector  \nRandom  \nLee(2021)  \nRegression  \nRegression*  \nMachine^  \nForest^  \no For instance,the probability of Type I errorsincreasing when heteroscedasticity exists  \n● Overall,when regression assumptions are violated inML,the risk for false positive/negative results may beless than in the original regression model  \nMental Health  \n-0.7  \n-9.9  \n100  \n100  \nSocial  \n0.6  \n2.4  \n17.1  \n32.8  \nParticipation  \n● ML may be a useful tool for linear regressionassumption violations  \n1.5  \nEducation  \n1.0  \n10.1  \n15.8  \nMethod  \nPhysical  \n25.6  \n0.2  \n1.9  \n5.6  \n● Understanding these implications of assumption  \nHealth  \nviolations in ML can significantly improve replicabilityof models  \n-3.3  \n-0.5  \n1.4  \n0.7  \nNever Married  \n● Utilized data from the Wisconsin Longitudinal Study(WLS)  \n-0.1  \n36.3  \nIQ  \n-0.1  \n2.1  \n● More work to be done to understand the implications ofthese violations for model fit  \n4.7  \n1.3  \n0.5  \n5.1  \nFemale  \n● Replicated findings from Clark and Lee(2021)whichlooked into how both early-and later-life variablescorrelate with later-life subjective well-being usingordinary least squares (OLS)linear regression  \n-0.3  \nNumber of  \n0.6  \n19.2  \n一  \n● Future directions:attempt to \"fix\"these violations andre-run regression and machine learning models  \nSiblings  \nSingle Parent  \n0.03  \n0.2  \n1.5  \nHousehold  \n● Utilized three supervised learning models:o Regularized regressiono Support vector machineo Random forest  \n/  \n23.8  \nMom Age at  \n-0.1  \n一  \nBirth  \nReferences  \nRetired  \n-0.1  \n4.7  \n一  \nSeparated  \n一  \n0.1  \n3.1  \nClark,A.E.&Lee,T.(2021).Early-life correlates of later-lifewell-being:Evidence from the Wisconsin Longitudinal Study.Journal of Economic Behavior &Organization,181,360-368.https://doi.org/10.1016/j","cbCaig9Evz3h3q98","https://ap.wps.com/l/cbCaig9Evz3h3q98","pdf",473885,1,2,"English","en",105,"# Introduction\n## Normality of Residuals\n# Results\n## Assumption violations detected in WLS\n# Discussion\n## Implications for reliability, Type I errors, and replicability\n## Modeling approaches and future directions","[{\"question\":\"How does the study evaluate effects beyond the original WLS analysis?\",\"answer\":\"It replicates findings from prior work and also runs Monte Carlo simulation (N=3000) with multiple replications to create simulated datasets with five predictors and one outcome variable.\"}]","Examining Regression Assumption Violations in Machine Learning Models - Using the Wisconsin Longitudinal Study Dataset | PDF",1785682354,5,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":77,"head_meta":79,"extra_data":81,"updated_unix":28},"examining-regression-assumption-violations-in-machine-learning-models-using-the-wisconsin-longitudinal-study-dataset","",{"@graph":36,"@context":76},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":21},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/examining-regression-assumption-violations-in-machine-learning-models-using-the-wisconsin-longitudinal-study-dataset/118221/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70],{"name":71,"@type":72,"acceptedAnswer":73},"How does the study evaluate effects beyond the original WLS analysis?","Question",{"text":74,"@type":75},"It replicates findings from prior work and also runs Monte Carlo simulation (N=3000) with multiple replications to create simulated datasets with five predictors and one outcome variable.","Answer","https://schema.org",{"og:url":51,"og:type":78,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":80,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":83},[84,88,92,96,100,105,110,113,118,121,125],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Comic",60,"comic",{"id":101,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},6,"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},30,"research-report",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},9,"Religion & Spirituality",20,"religion-spirituality",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":119,"show_sort_weight":116,"slug":120},"World Cup","world-cup",{"id":122,"doc_module":4,"doc_module_name":46,"category_name":123,"show_sort_weight":122,"slug":124},10,"Lifestyle","lifestyle",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":29,"slug":128},19,"General","general"]