[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-533615-105":59,"doc-detail-533615-en":122},{"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":115,"head_meta":117,"extra_data":119,"updated_unix":121},105,"en","comparing-regression-coefficients-across-subsamples-a-study-of-the-statistical-test","Comparing Regression Coefficients Across Subsamples - A Study of the Statistical Test","","The paper examines whether regression relationships remain stable across different subsamples under varying conditions, addressing frequent misunderstandings in the statistical procedures used to compare estimated regression coefficients. It details appropriate statistical tests and the assumptions behind them, illustrating with examples how applying incorrect formulas can produce mistaken conclusions. The discussion covers models with one predictor and compares slopes across two subsamples, highlighting when standard normal, t, or Fisher-derived forms are valid.",{"@graph":69,"@context":114},[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/comparing-regression-coefficients-across-subsamples-a-study-of-the-statistical-test/533615/",{"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/comparing-regression-coefficients-across-subsamples-a-study-of-the-statistical-test/533615.png","ImageObject",300,407,{"name":92,"@type":93},"dawugda","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-10-10",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108],{"name":109,"@type":110,"acceptedAnswer":111},"How does the paper test equality of slopes across two subsamples?","Question",{"text":112,"@type":113},"It considers a simple linear regression with one predictor for two subsamples and sets a null hypothesis that the slopes are equal. Under normality and depending on sample size and assumptions like homoscedasticity, it derives appropriate test statistics such as an asymptotic normal approximation or a t/Fisher-derived form.","Answer","https://schema.org",{"og:url":83,"og:type":116,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":118,"canonical":83},"index,follow",{"doc_id":120,"site_id":62},533615,1792164724,{"code":4,"msg":5,"data":123},{"doc_id":120,"user_id":124,"nickname":92,"user_avatar":125,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":126,"file_id":127,"file_url":128,"file_type":129,"file_size":130,"view_count":14,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":131,"language":132,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":133,"faqs":134,"seo_title":135,"seo_description":67,"update_tm":136,"read_time":137,"preview_page_count":19,"preview_urls":138},3985747870947,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","The comparison of regression coefficients across subsamples is relevant tomany studies.Often,the same regression model is fitted to several subsamplesand the question arises whether the effect of some of the explanatory variables,as expressed by the linear model,is the same for all subsamples.Becausethere are sometimes misunderstandings as to the statistical procedure whichought to be applied and consequently,wrong formulae are sometimes adoptedby researchers.The purpose of this article is to describe in detail the relevantstatistical procedures,together with the assumptions underlying the statisticaltests.Some examples are quoted,in which wrong formulae were applied.It isdemonstrated how the adoption of the wrong formulae might lead to mis-taken conclusions.  \n# Comparing Regression CoefficientsAcross SubsamplesA Study of the Statistical Test\n\nAYALA COHEN  \nTechnion  \nHaifa,Israel  \ninear regression models are commonly used to representrelationships among variables.Often,the question arisesas to whether the relationship as expressed by the linear modelremains stable under some varying conditions.For example,Turner and Martinez(1977)fitted a linear model to predictoccupational attainment.They fitted the same structural modelfor men at two levels of education;then they compared thefitted regression coefficients across the two subsamples.  \nThe problem of comparing estimated regression coefficientsamong subsamples is confronted not only by sociologists.Ineconomics,when a linear regression model is fitted to describeeconomic relationships,it might be of interest to examinewhether the same relationships hold for different time periodsor for different economic units.For example,are the price  \n78 SOCIOLOGICAL METHODS&RESEARCH  \nelasticities the same for one or more products when differenttime periods are compared?  \nIn psychology,regression models are used to predict abilityof students.The question then arises whether the regressionslopes,for certain items in the test,are the same across differentsocioeconomic classes.  \nUnfortunately,there are misunderstandings as to the statis-tical procedure that ought to be applied to compare regressioncoefficients.Even though the wrong usage of a statistical for-mula does not necessarily lead to the wrong conclusion,we feelthat it is important to clarify the right procedure.When a wrongformula is quoted in an article,it might mislead others,whothen adopt the procedure and might obtain mistaken results.  \nThe purpose of this article is to describe the statistical testthat ought to be used for comparing regression coefficients.We quote some examples in which wrong formulae were used,and we demonstrate how the wrong formulae could lead towrong conclusions.  \n## COMPARISON OF THE SLOPES INSIMPLE LINEAR REGRESSIONACROSS TWO SUBSAMPLES\n\nWe first consider the simple case of a linear regression withone predictor.For N bivariate observations(xi,yi),i=1,...,N,it is assumed that  \n[1]  \ny;=α+βx:+ei  \nwhere the es are uncorrelated errors with zero expectation andvariance o².Let b denote the least squares estimate of β.It iswell known that the variance of b is  \n[2]  \nwhere  \nThe unbiased estimator of o²is  \n[3]  \nwhereý;is the ith predicted value  \nCombining equations 2 and 3 we obtain the estimate for Var(b)  \n[4]  \nFor simplicity we rewrite equation 4 as  \n[5]  \nNow consider drawing independent bivariate samples fromtwo subpopulations.Denote by N₁,N₂the respective samplesizes.For each subsample we fit a separate linear model(equa-tion 1).Letdenote the error variances in the two regres-sions and let b₁,b2 be the least squares estimates of the slopes.The null hypothesis that is tested is that the slopes are the samein the two subpopulations:  \nH⁰:β(1)=β(2)  \nwhere β(j)denotes the slope in thejth subpopulation(j=1,2).  \n80 SOCIOLOGICAL METHODS&RESEARCH  \nUnder the normality assumption,which is usually made inthe inference of regression data,and under H⁰,  \n[6]  \nThe statistics in equation 6 include Var(b₁)","cbCaivt8vH59GHVa","https://ap.wps.com/l/cbCaivt8vH59GHVa","pdf",1093621,18,"English","# Comparing Regression Coefficients Across Subsamples\n## A Study of the Statistical Test\n## Comparison of the Slopes in Simple Linear Regression Across Two Subsamples","[{\"question\":\"How does the paper test equality of slopes across two subsamples?\",\"answer\":\"It considers a simple linear regression with one predictor for two subsamples and sets a null hypothesis that the slopes are equal. Under normality and depending on sample size and assumptions like homoscedasticity, it derives appropriate test statistics such as an asymptotic normal approximation or a t/Fisher-derived form.\"}]","Comparing Regression Coefficients Across Subsamples - A Study of the Statistical Test | PDF",1791593237,45,[139,143,147,151],{"page_no":8,"url":140,"width":141,"height":142},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/14033207aa4ca76df2b7872b332cff07.webp",983,1415,{"page_no":14,"url":144,"width":145,"height":146},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/fcf0f368232492133a83f041d2a0635e.webp",982,1414,{"page_no":81,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/6fe6967fd03c9fd4db92c6c1d70704d2.webp",981,1412,{"page_no":19,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/50d351496ad89ece909a0d94ce5a9fda.webp",980,1411]