{"title":"Imputation methods for mixed datasets in bioarchaeology","authors":"Jessica Ryan-Despraz, Amanda Wissler","doi":"10.1007/s12520-024-02078-2","DOIUrl":null,"url":null,"abstract":"<div><p>Missing data is a prevalent problem in bioarchaeological research and imputation could provide a promising solution. This work simulated missingness on a control dataset (481 samples × 41 variables) in order to explore imputation methods for mixed data (qualitative and quantitative data). The tested methods included Random Forest (RF), PCA/MCA, factorial analysis for mixed data (FAMD), hotdeck, predictive mean matching (PMM), random samples from observed values (RSOV), and a multi-method (MM) approach for the three missingness mechanisms (MCAR, MAR, and MNAR) at levels of 5%, 10%, 20%, 30%, and 40% missingness. This study also compared single imputation with an adapted multiple imputation method derived from the R package “mice”. The results showed that the adapted multiple imputation technique always outperformed single imputation for the same method. The best performing methods were most often RF and MM, and other commonly successful methods were PCA/MCA and PMM multiple imputation. Across all criteria, the amount of missingness was the most important parameter for imputation accuracy. While this study found that some imputation methods performed better than others for the control dataset, each imputation method has advantages and disadvantages. Imputation remains a promising solution for datasets containing missingness; however when making a decision it is essential to consider dataset structure and research goals.</p></div>","PeriodicalId":8214,"journal":{"name":"Archaeological and Anthropological Sciences","volume":"16 11","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11496361/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Archaeological and Anthropological Sciences","FirstCategoryId":"89","ListUrlMain":"https://link.springer.com/article/10.1007/s12520-024-02078-2","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ANTHROPOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Missing data is a prevalent problem in bioarchaeological research and imputation could provide a promising solution. This work simulated missingness on a control dataset (481 samples × 41 variables) in order to explore imputation methods for mixed data (qualitative and quantitative data). The tested methods included Random Forest (RF), PCA/MCA, factorial analysis for mixed data (FAMD), hotdeck, predictive mean matching (PMM), random samples from observed values (RSOV), and a multi-method (MM) approach for the three missingness mechanisms (MCAR, MAR, and MNAR) at levels of 5%, 10%, 20%, 30%, and 40% missingness. This study also compared single imputation with an adapted multiple imputation method derived from the R package “mice”. The results showed that the adapted multiple imputation technique always outperformed single imputation for the same method. The best performing methods were most often RF and MM, and other commonly successful methods were PCA/MCA and PMM multiple imputation. Across all criteria, the amount of missingness was the most important parameter for imputation accuracy. While this study found that some imputation methods performed better than others for the control dataset, each imputation method has advantages and disadvantages. Imputation remains a promising solution for datasets containing missingness; however when making a decision it is essential to consider dataset structure and research goals.
期刊介绍:
Archaeological and Anthropological Sciences covers the full spectrum of natural scientific methods with an emphasis on the archaeological contexts and the questions being studied. It bridges the gap between archaeologists and natural scientists providing a forum to encourage the continued integration of scientific methodologies in archaeological research.
Coverage in the journal includes: archaeology, geology/geophysical prospection, geoarchaeology, geochronology, palaeoanthropology, archaeozoology and archaeobotany, genetics and other biomolecules, material analysis and conservation science.
The journal is endorsed by the German Society of Natural Scientific Archaeology and Archaeometry (GNAA), the Hellenic Society for Archaeometry (HSC), the Association of Italian Archaeometrists (AIAr) and the Society of Archaeological Sciences (SAS).