[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-590290-105":59,"doc-detail-590290-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","enhancing-quantitative-analysis-in-social-sciences-with-large-language-models-llms-a-methodological-case-study-in-educational-research","Enhancing Quantitative Analysis in Social Sciences With Large Language Models (LLMs) - A Methodological Case Study in Educational Research","","Large Language Models (LLMs) offer new ways to support quantitative data analysis in social science research by integrating them into researchers’ workflows. The paper presents a methodological case study in educational research, replicating work on school program coherence and student achievement. It shows how LLMs can generate code for statistical tools such as Mplus and R and explains how results depend on researcher choices and concepts like context windows, training cut-off, temperature, zero- and few-shot learning, and Retrieval-Augmented Generation (RAG).",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/enhancing-quantitative-analysis-in-social-sciences-with-large-language-models-llms-a-methodological-case-study-in-educational-research/590290/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/enhancing-quantitative-analysis-in-social-sciences-with-large-language-models-llms-a-methodological-case-study-in-educational-research/590290.png","ImageObject",300,407,{"name":92,"@type":93},"Pentious","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-09","2026-10-15",true,{"@type":102,"interactionType":103,"userInteractionCount":29},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the paper’s main goal for using LLMs in social science research?","Question",{"text":112,"@type":113},"It explores how Large Language Models can assist quantitative data analysis and helps researchers integrate LLMs effectively into their research workflows.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the paper demonstrate the approach?",{"text":117,"@type":113},"It replicates a research paper in educational leadership on school program coherence and student achievement, using LLMs to generate code for statistical tools such as Mplus and R.",{"name":119,"@type":110,"acceptedAnswer":120},"Which factors can influence the quality of LLM-generated analytical code?",{"text":121,"@type":113},"Code quality can depend on how researchers understand and apply context windows, LLM training data and training cut-off, temperature, zero- and few-shot learning, and Retrieval-Augmented Generation (RAG).","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},590290,1792512438,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":29,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":4},1374404730887,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","AERA Open  \nJanuary-December 2025, Vol. 11, No. 1, pp. 1–18 DOI: 10. 1177/23328584251389621  \nArticle reuse guidelines: [sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)© The Author(s) 2025. [https://journals.sagepub.com/home/ero](https://journals.sagepub.com/home/ero)  \nEnhancing Quantitative Analysis in Social Sciences With Large Language Models (LLMs): A Methodological Case Study in Educational  \nResearch  \nJames Sebastian  \nCollege of Education & Human Development, University of Missouri-Columbia  \nJeong-Mi Moon  \nDepartment of Energy Engineering, Korea Institute of Energy Technology  \nEric Camburn  \nSchool of Education, Social Work and Psychological Sciences, University of Missouri-Kansas City  \nThis paper explores the potential of Large Language Models (LLMs) for assisting with quantitative data analysis in social science research. Specifically, it introduces key concepts to help researchers effectively integrate LLMs into their workflows.  \nFor this purpose, we replicate a research paper in educational leadership on the relationship between school program coherence and student achievement. By leveraging LLMs to generate code for statistical tools like Mplus and R, researchers can streamline their data analysis, potentially saving time and effort. The quality of analytical code generated by LLMs can be influenced by the researcher’s understanding and application of concepts like context windows, LLM training data and training cut-off, model parameter settings like temperature, zero-and few-shot learning, and Retrieval-Augmented Generation (RAG). By describing and demonstrating the applications of these concepts, we aim to equip researchers with a basic toolset to leverage LLMs effectively to assist with coding for quantitative analysis.  \nKeywords: Artificial Intelligence, Administration, Educational Policy, Case Studies, Research Methodology, Survey Research, Hierarchical Linear Modeling, Large Language Models (LLMs), quantitative analysis, Retrieval-Augmented Generation (RAG), zero-shot learning, few-shot learning  \nIntroduction  \nLarge language models (LLMs) demonstrate significant capabilities to assist researchers across disciplines with their data analysis by enhancing the efficiency of their workstreams. LLMs such as OpenAI’s ChatGPT, Anthropic’s Claude, Meta’s Llama, and Google’s Gemini and Gemma models have received a great deal of attention recently, as they show potential to achieve advances in multiple fields and applications (Bommasani et al., 2021; Bowman, 2023) . LLMs are artificial intelligence (AI) models designed to generate text by predicting the next token in a sentence (Brown et al., 2020) . A token refers to a small unit of data, such as parts of words, images, or videos, with each token representing about four characters in English (Kuzminykh, 2024) . These models are trained on vast datasets, enabling them to capture complex statistical patterns in human language (Radford et al., 2019). They are called “large models”  \nbecause they contain billions or even trillions of parameters and are trained on vast amounts of data (Brown et al., 2020; Radford et al., 2019), allowing them to generate text that is often indistinguishable from human writing (Bender et al., 2021; Chang et al., 2024) . LLMs have significantly transformed natural language processing (NLP) tasks such as translation, question-answering, and reading comprehension (Brown et al., 2020) . Further, an emerging Reasoning and Acting (ReAct) framework explores the potential of LLMs to implement complex, multi-step reasoning tasks (Yao et al., 2022) . LLMs have shown impressive performance in extracting data from previous studies and in conducting systematic reviews (Gartlehner et al., 2024; Riaz et al., 2024) . LLM applications have also been explored for programming code generation and code comprehension (Fang et al., 2024; Vaithilingam et al., 2022) and are widely used by programmers ","cbCaitmSDkgvIXkW","https://ap.wps.com/l/cbCaitmSDkgvIXkW","pdf",457179,18,"English","# Introduction\n## Background on LLM capabilities for research workflows\n# Methodological Case Study\n## Replicating an educational leadership research relationship\n## Using LLMs to generate statistical tool code (Mplus, R)\n## Factors affecting code quality\n## Concepts: context windows, training data, temperature, zero-/few-shot, RAG","[{\"question\":\"What is the paper’s main goal for using LLMs in social science research?\",\"answer\":\"It explores how Large Language Models can assist quantitative data analysis and helps researchers integrate LLMs effectively into their research workflows.\"},{\"question\":\"How does the paper demonstrate the approach?\",\"answer\":\"It replicates a research paper in educational leadership on school program coherence and student achievement, using LLMs to generate code for statistical tools such as Mplus and R.\"},{\"question\":\"Which factors can influence the quality of LLM-generated analytical code?\",\"answer\":\"Code quality can depend on how researchers understand and apply context windows, LLM training data and training cut-off, temperature, zero- and few-shot learning, and Retrieval-Augmented Generation (RAG).\"}]","Enhancing Quantitative Analysis in Social Sciences With Large Language Models (LLMs) - A Methodological Case Study in Educational Research | PDF",1792069257,45]