{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_52598"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_52598","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"HARNESSING THE POWER OF APPLIED STATISTICS TO CONTRIBUTE TO SCIENTIFIC KNOWLEDGE PRODUCTION","abstract":"Thesis (Ph.D.)--Michigan State University. Statistics - Doctor of Philosophy, 2025","abstract_html":"Thesis (Ph.D.)--Michigan State University. Statistics - Doctor of Philosophy, 2025","abstract_has_math":false,"creators":["Pizzo, Gina Marie"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Viens, Frederi G","McCright, Aaron M","Huebner, Marianne","Sakhanenko, Lyudmila"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-11-18T18:59:09Z","subjects":["Statistics","Agriculture economics","Sociology","Agriculture--Economic aspects"],"languages":["eng"],"rights":["Attribution-NonCommercial-NoDerivatives 4.0 International"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:52598","local:Pizzo_grad.msu_0128D_21561"],"render_values":[{"text":"etd:52598","href":null,"code":true},{"text":"local:Pizzo_grad.msu_0128D_21561","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/rcac-av06","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/rcac-av06","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_52598","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Viens, Frederi G","McCright, Aaron M","Huebner, Marianne","Sakhanenko, Lyudmila"]},{"key":"dc:creator","label":"Author","values":["Pizzo, Gina Marie"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["text","Electronic dissertations"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Statistics","Agriculture economics","Sociology","Agriculture--Economic aspects"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NonCommercial-NoDerivatives 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:52598","local:Pizzo_grad.msu_0128D_21561","https://doi.org/doi:10.25335/rcac-av06"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph.D.)--Michigan State University. Statistics - Doctor of Philosophy, 2025","This dissertation research integrates applied statistical modeling, interdisciplinary collaboration, and public policy relevance to support climate-resilient agriculture and deepen understanding of scientists' philosophical commitments. The researcher has structured their training around applied statistical projects across diverse domains including agroecology, environmental science, economics, and the social sciences.A primary focus of this work is the development of Bayesian hierarchical models to assess the impacts of soil-health practices, specifically crop diversification, on field-level corn yields under variable climate conditions. The researcher designed statistical models that quantify the risk-mitigating effects of regenerative agricultural practices. These models provide field-level corn yield estimates for dry and average seasons, incorporating expert knowledge from agroecologists via principled Bayesian prior elicitation. The models serve policy-relevant purposes, such as informing USDA Farm Bill provisions, guiding Farm Service Agency programs, and influencing Risk Management Agency insurance pricing. Methodological innovations include neighborhood-based spatial modeling to manage edge effects and spatial correlations, as well as the use of high-performance computing to handle large-scale Midwestern datasets from states such as Illinois, Minnesota, Wisconsin, Ohio, and South Dakota.The current federal crop insurance system incentivizes simplified crop rotations, which are more vulnerable to weather stress, in part because they can be detrimental to soil health. This increases the risk for farmers and insurers. This is why field-level data is necessary for lenders and insurers to incorporate soil health into their risk assessments. The researcher integrated economic risk modeling by linking field-level yield predictions to revenue distributions under commodity price volatility. This analysis uses a combination of national price risk via Black-Scholes modeling and local elevator-based pricing data to estimate farm-level revenue uncertainty. Results suggest that input cost variability outweighs weather-related risks and that soil-health practices can reduce downside yield and revenue risks without sacrificing performance. Evidence also indicates a reduction in revenue variance when increasing crop rotation complexity, such as moving from two-crop to three-crop rotations. The research I have accomplished will help farmers capture more of the ecosystem services’ societal value of diversifying around cash crop rotations and adopting cover crops and other soil-healthy practices; and will help public and private policy-makers take steps to increase the adoption of these practices.Ongoing work aims to extend the modeling framework to more spatially diverse regions such as Michigan, where conventional assumptions about spatial scale and practice effects may not apply. In addition, the researcher will support the future development of a software tool for lenders and insurers to assess risk-reduction benefits of conservation practices. Our contributions will emphasize accessibility and interpretability for stakeholders unfamiliar with statistical modeling.Complementing this agricultural research, the researcher is also contributing to an NSF-funded project investigating the philosophical (ontological, epistemological, and axiological) commitments of U.S. scientists. This interdisciplinary effort includes philosopher, sociologist, and anthropologist collaborators, and involves a standardized survey administered to a stratified random sample of 4,113 tenure-system faculty at 83 Carnegie R1 institutions. The researcher has been involved in survey design, sampling frame development, and statistical analysis using latent variable structural equation modeling (SEM), further deepening expertise in measuring scientific disciplinarity.Together, these research experiences demonstrate the researcher’s capacity to develop and apply rigorous statistical tools across domains. By integrating Bayesian inference, agricultural economics, and structural equation modeling in the social sciences, the work aims to support agricultural resilience, inform public policy, and contribute to broader societal and environmental well-being.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","1 online resource (279 p.) : ill."]},{"key":"dc:title","label":"Title","values":["HARNESSING THE POWER OF APPLIED STATISTICS TO CONTRIBUTE TO SCIENTIFIC KNOWLEDGE PRODUCTION"]}]}],"canonical_facts":{"dc:contributor":["Viens, Frederi G","McCright, Aaron M","Huebner, Marianne","Sakhanenko, Lyudmila"],"dc:creator":["Pizzo, Gina Marie"],"dc:date":["2025"],"dc:description":["Thesis (Ph.D.)--Michigan State University. Statistics - Doctor of Philosophy, 2025","This dissertation research integrates applied statistical modeling, interdisciplinary collaboration, and public policy relevance to support climate-resilient agriculture and deepen understanding of scientists' philosophical commitments. The researcher has structured their training around applied statistical projects across diverse domains including agroecology, environmental science, economics, and the social sciences.A primary focus of this work is the development of Bayesian hierarchical models to assess the impacts of soil-health practices, specifically crop diversification, on field-level corn yields under variable climate conditions. The researcher designed statistical models that quantify the risk-mitigating effects of regenerative agricultural practices. These models provide field-level corn yield estimates for dry and average seasons, incorporating expert knowledge from agroecologists via principled Bayesian prior elicitation. The models serve policy-relevant purposes, such as informing USDA Farm Bill provisions, guiding Farm Service Agency programs, and influencing Risk Management Agency insurance pricing. Methodological innovations include neighborhood-based spatial modeling to manage edge effects and spatial correlations, as well as the use of high-performance computing to handle large-scale Midwestern datasets from states such as Illinois, Minnesota, Wisconsin, Ohio, and South Dakota.The current federal crop insurance system incentivizes simplified crop rotations, which are more vulnerable to weather stress, in part because they can be detrimental to soil health. This increases the risk for farmers and insurers. This is why field-level data is necessary for lenders and insurers to incorporate soil health into their risk assessments. The researcher integrated economic risk modeling by linking field-level yield predictions to revenue distributions under commodity price volatility. This analysis uses a combination of national price risk via Black-Scholes modeling and local elevator-based pricing data to estimate farm-level revenue uncertainty. Results suggest that input cost variability outweighs weather-related risks and that soil-health practices can reduce downside yield and revenue risks without sacrificing performance. Evidence also indicates a reduction in revenue variance when increasing crop rotation complexity, such as moving from two-crop to three-crop rotations. The research I have accomplished will help farmers capture more of the ecosystem services’ societal value of diversifying around cash crop rotations and adopting cover crops and other soil-healthy practices; and will help public and private policy-makers take steps to increase the adoption of these practices.Ongoing work aims to extend the modeling framework to more spatially diverse regions such as Michigan, where conventional assumptions about spatial scale and practice effects may not apply. In addition, the researcher will support the future development of a software tool for lenders and insurers to assess risk-reduction benefits of conservation practices. Our contributions will emphasize accessibility and interpretability for stakeholders unfamiliar with statistical modeling.Complementing this agricultural research, the researcher is also contributing to an NSF-funded project investigating the philosophical (ontological, epistemological, and axiological) commitments of U.S. scientists. This interdisciplinary effort includes philosopher, sociologist, and anthropologist collaborators, and involves a standardized survey administered to a stratified random sample of 4,113 tenure-system faculty at 83 Carnegie R1 institutions. The researcher has been involved in survey design, sampling frame development, and statistical analysis using latent variable structural equation modeling (SEM), further deepening expertise in measuring scientific disciplinarity.Together, these research experiences demonstrate the researcher’s capacity to develop and apply rigorous statistical tools across domains. By integrating Bayesian inference, agricultural economics, and structural equation modeling in the social sciences, the work aims to support agricultural resilience, inform public policy, and contribute to broader societal and environmental well-being.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."],"dc:format":["application/pdf","1 online resource (279 p.) : ill."],"dc:identifier":["etd:52598","local:Pizzo_grad.msu_0128D_21561","https://doi.org/doi:10.25335/rcac-av06"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["Attribution-NonCommercial-NoDerivatives 4.0 International"],"dc:subject":["Statistics","Agriculture economics","Sociology","Agriculture--Economic aspects"],"dc:title":["HARNESSING THE POWER OF APPLIED STATISTICS TO CONTRIBUTE TO SCIENTIFIC KNOWLEDGE PRODUCTION"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:59:09Z"}