{"id":744,"date":"2016-06-06T10:27:14","date_gmt":"2016-06-06T14:27:14","guid":{"rendered":"https:\/\/health.uconn.edu\/health-disparities\/?page_id=744"},"modified":"2021-11-22T15:52:14","modified_gmt":"2021-11-22T20:52:14","slug":"methodological-statistical-services","status":"publish","type":"page","link":"https:\/\/health.uconn.edu\/health-disparities\/methodological-statistical-services\/","title":{"rendered":"Methodological and Statistical Services"},"content":{"rendered":"<div id=\"pl-744\"  class=\"panel-layout\" ><div id=\"pg-744-0\"  class=\"panel-grid panel-no-style\" ><div id=\"pgc-744-0-0\"  class=\"panel-grid-cell\" ><div id=\"panel-744-0-0-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"0\" ><div class=\"textwidget\"><p><figure id=\"attachment_773\" aria-describedby=\"caption-attachment-773\" style=\"width: 300px\" class=\"wp-caption alignright\"><a href=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/services_fig1.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-773 size-medium lazyload\" data-src=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/services_fig1-300x278.jpg\" alt=\"Racial and ethnic disparities in birth outcomes: a life-course perspective\" width=\"300\" height=\"278\" data-srcset=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/260\/2016\/06\/services_fig1-300x278.jpg 300w, https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/260\/2016\/06\/services_fig1.jpg 400w\" data-sizes=\"(max-width: 300px) 100vw, 300px\" src=\"data:image\/gif;base64,R0lGODlhAQABAAAAACH5BAEKAAEALAAAAAABAAEAAAICTAEAOw==\" style=\"--smush-placeholder-width: 300px; --smush-placeholder-aspect-ratio: 300\/278;\" \/><noscript><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-773 size-medium\" src=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/services_fig1-300x278.jpg\" alt=\"Racial and ethnic disparities in birth outcomes: a life-course perspective\" width=\"300\" height=\"278\" srcset=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/260\/2016\/06\/services_fig1-300x278.jpg 300w, https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/260\/2016\/06\/services_fig1.jpg 400w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/noscript><\/a><figcaption id=\"caption-attachment-773\" class=\"wp-caption-text\">Lu, M. C., &amp; Halfon, N. (2003). Racial and ethnic disparities in birth outcomes: a life-course perspective. Maternal &amp; Child Health Journal, 7(1), 13-30.<\/figcaption><\/figure><\/p>\n<p>Health Disparities (HD) are notoriously <a href=\"http:\/\/jech.bmj.com\/content\/59\/8\/700.short\" class=\"broken_link\">hard to identify<\/a> reliably; moreover finding what causes them, and hence how to reduce and\u00a0eliminate them, is especially difficult, but <a href=\"https:\/\/www.google.com\/url?sa=t&amp;rct=j&amp;q=&amp;esrc=s&amp;source=web&amp;cd=1&amp;cad=rja&amp;uact=8&amp;ved=0ahUKEwj2kOaSlJbNAhXEQD4KHRqXBCYQFgglMAA&amp;url=http%3A%2F%2Fdev1.education.uconn.edu%2Fm3c%2Fassets%2FFile%2FCausal%2520modeling%2520approaches%2520to%2520answer%2520research%2520questions%2520about%2520health%2520disparities%2520-%2520Coman%2520Fifield%2520Villagra%2520Shipley.pdf&amp;usg=AFQjCNFz214E_tMn8SKH5XZS2hV8y4le4w&amp;sig2=5JFNoZnzXUcJ8p6GYfh0EQ\">models exist<\/a> (see the <em>Framework for Health<\/em> equity below, the birth outcomes illustration, and other <a href=\"http:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC3740124\/\">conceptual<\/a> and <a href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15481431\">practical<\/a> models).<\/p>\n<p>The main reason is that simple group comparisons of a health outcome is not enough to conclude that HDs exist, and to what extent they do. Such group comparisons need to \u2018take into account\u2019 outside causal factors (like neighborhood, or socio-economic conditions) that \u2018partially explain\u2019 the raw difference we notice at first. We can provide <em>advice<\/em> on such matters, e.g.:<\/p>\n<ol>\n<li>How and why and what <a href=\"http:\/\/journals.lww.com\/epidem\/abstract\/2003\/05000\/quantifying_biases_in_causal_models__classical.9.aspx\">to \u2018control for\u2019<\/a> when deciding the extent of HDs is what we can provide assistance with, to researchers but also community stakeholders interested in <a href=\"http:\/\/journals.lww.com\/epidem\/Abstract\/2001\/03000\/Assessment_of_Structured_Socioeconomic_Effects_on.6.aspx\">extracting<\/a> and translating evidence, so that it can become actionable.<\/li>\n<li>How can one distinguish between: inequities\/differences\/disparities\/discrimination. There are ways to <a href=\"http:\/\/ftp.cs.ucla.edu\/pub\/stat_ser\/R273-U.pdf\">test for discrimination<\/a>, one involving assessing residual direct effects after explaining other mechanisms that may operate, or specific mediators like <a href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/20228874\">implicit prejudice<\/a>.<\/li>\n<li>How can make causal claims in the HD world:<\/li>\n<\/ol>\n<p style=\"padding-left: 30px\">3.1. Can race\/ethnicity \u2018<a href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/24887159\">cause\u2019 health outcomes<\/a>? Can gender cause them? It is debatable, but there are ways to handle this better\/worse.<\/p>\n<p style=\"padding-left: 30px\">3.2. What not to \u2018control for\u2019 when comparing groups: an intermediate outcome is problematic for example, <a href=\"http:\/\/journals.lww.com\/epidem\/abstract\/2003\/05000\/quantifying_biases_in_causal_models__classical.9.aspx\">others<\/a> even more problematic.<\/p>\n<p><figure id=\"attachment_774\" aria-describedby=\"caption-attachment-774\" style=\"width: 300px\" class=\"wp-caption alignright\"><a href=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/services_fig2.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-774 size-medium lazyload\" data-src=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/services_fig2-300x218.jpg\" alt=\"A Framework for Health Equity\" width=\"300\" height=\"218\" data-srcset=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/260\/2016\/06\/services_fig2-300x218.jpg 300w, https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/260\/2016\/06\/services_fig2.jpg 400w\" data-sizes=\"(max-width: 300px) 100vw, 300px\" src=\"data:image\/gif;base64,R0lGODlhAQABAAAAACH5BAEKAAEALAAAAAABAAEAAAICTAEAOw==\" style=\"--smush-placeholder-width: 300px; --smush-placeholder-aspect-ratio: 300\/218;\" \/><noscript><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-774 size-medium\" src=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/services_fig2-300x218.jpg\" alt=\"A Framework for Health Equity\" width=\"300\" height=\"218\" srcset=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/260\/2016\/06\/services_fig2-300x218.jpg 300w, https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/260\/2016\/06\/services_fig2.jpg 400w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/noscript><\/a><figcaption id=\"caption-attachment-774\" class=\"wp-caption-text\">Tony Iton \u201cFramework for Health Equity\u201d, referenced in the text: Tackling Health Inequities Through Public Health Practice: Theory to Action. Edited by Richard Hofrichter and Rajiv Bhatia. Based on a project by the National Association of County and City Health Officials. Oxford University Press, 2010 (page 380). Adapted by ACPHD from the Bay Area Regional Health Inequities Initiative, Summer 2008.<\/figcaption><\/figure><\/p>\n<p style=\"padding-left: 30px\">3.3. Various matching methods exist that allow for true comparability; such matching may <a href=\"https:\/\/ije.oxfordjournals.org\/content\/31\/5\/1030.full\">induce at times relationships<\/a> between variables that are not manifest in the entire population.<\/p>\n<p style=\"padding-left: 30px\">3.4. Instead of having race\/ethnicity \u2018cause\u2019 health, one can compare populations in <a href=\"http:\/\/elischolar.library.yale.edu\/dayofdata\/2013\/Posters\/2\/\">simple<\/a> and <a href=\"http:\/\/www.stata-journal.com\/article.html?article=st0238\">complex<\/a> ways of causal relationships.<\/p>\n<ol start=\"4\">\n<li>How to apply a person\/<a href=\"http:\/\/www.cipci.org\/roundtable-emil-coman\" class=\"broken_link\">patient-centered view<\/a> to HDs: what can statistics tell us about Darnell\u2018s vs. Jake\u2019s vs. Jose\u2019s health outcomes, and how can this provide feedback to their health care providers.<\/li>\n<\/ol>\n<p style=\"padding-left: 30px\">3.4. A practical solution is to find completely identical Darnell and Jake and compare their patient experiences and outcomes.<\/p>\n<ol start=\"5\">\n<li>Measuring race and ethnicity are the pillars of HD answers, yet these are <a href=\"http:\/\/psycnet.apa.org\/psycinfo\/1997-43129-015\">difficult to measure<\/a> reliably, better solutions exist of course.<\/li>\n<li>We can specifically help with gathering, processing and analyzing health data to develop health disparities dashboards\/reports for health care providers of other stakeholders interested in this.<\/li>\n<\/ol>\n<p>\u00a0<\/p>\n<p>We list below some modeling resources (papers, software code for analyses, outputs) that refer to some of our prior work.<\/p>\n<h2>Helpful Tips and Supplementary Materials<\/h2>\n<\/div><\/div><\/div><\/div><div id=\"pg-744-1\"  class=\"panel-grid panel-no-style\" ><div id=\"pgc-744-1-0\"  class=\"panel-grid-cell\" ><div id=\"panel-744-1-0-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"1\" ><div class=\"modeling_text panel-widget-style panel-widget-style-for-744-1-0-0\" ><div class=\"textwidget\"><p><span class=\"badge\">1<\/span>\u00a0\u00a0Models and Outputs<br \/>Statistical power of alternative structural models for comparative effectiveness research: advantages of modeling unreliability.\u00a0<\/p>\n<p>Contact <a href=\"mailto:coman@uchc.edu\">coman@uchc.edu<\/a> for detailed appendix.<\/p>\n<\/div><\/div><\/div><\/div><div id=\"pgc-744-1-1\"  class=\"panel-grid-cell\" ><div id=\"panel-744-1-1-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"2\" ><div class=\"modeling_text panel-widget-style panel-widget-style-for-744-1-1-0\" ><div class=\"textwidget\"><p><span class=\"badge\">2<\/span>\u00a0\u00a0Mplus\u00a0Outputs\u00a0<br \/>\"<a href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/23276188\">Characteristics of initial and sustained female condom users among urban U.S. women<\/a>.\"\u00a0<\/p>\n<p>Contact <a href=\"mailto:coman@uchc.edu\">coman@uchc.edu<\/a> for detailed appendix.<\/p>\n<\/div><\/div><\/div><\/div><div id=\"pgc-744-1-2\"  class=\"panel-grid-cell\" ><div id=\"panel-744-1-2-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"3\" ><div class=\"modeling_text panel-widget-style panel-widget-style-for-744-1-2-0\" ><div class=\"textwidget\"><p><span class=\"badge\">3<\/span>\u00a0\u00a0Mplus Outputs <br \/>\"Ethnic differences of the mediating effects of anxiety and actual social support on the relation between stress and depression in community-dwelling older adults.\"\u00a0<\/p>\n<p>Contact <a href=\"mailto:coman@uchc.edu\">coman@uchc.edu<\/a> for detailed appendix.<\/p>\n<\/div><\/div><\/div><\/div><\/div><div id=\"pg-744-2\"  class=\"panel-grid panel-no-style\" ><div id=\"pgc-744-2-0\"  class=\"panel-grid-cell\" ><div id=\"panel-744-2-0-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"4\" ><div class=\"modeling_text panel-widget-style panel-widget-style-for-744-2-0-0\" ><div class=\"textwidget\"><p><span class=\"badge\">4<\/span>\u00a0\u00a0Mplus\u00a0Outputs\u00a0<br \/>\"<a href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/22674637\">Comparisons of CES-D depression scoring methods in two older adult ethnic groups. The emergence of an ethnic-specific brief three-item CES-D scale<\/a>.\"\u00a0<\/p>\n<p>Contact <a href=\"mailto:coman@uchc.edu\">coman@uchc.edu<\/a> for detailed appendix.<\/p>\n<\/div><\/div><\/div><\/div><div id=\"pgc-744-2-1\"  class=\"panel-grid-cell\" ><div id=\"panel-744-2-1-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"5\" ><div class=\"modeling_text panel-widget-style panel-widget-style-for-744-2-1-0\" ><div class=\"textwidget\"><p><span class=\"badge\">5<\/span>\u00a0\u00a0AMOS Model and Data <br \/>\"The paired t-test as a simple latent change score model.\"<\/p>\n<p>Contact <a href=\"mailto:coman@uchc.edu\">coman@uchc.edu<\/a> for detailed appendix.<\/p>\n<\/div><\/div><\/div><\/div><div id=\"pgc-744-2-2\"  class=\"panel-grid-cell\" ><div id=\"panel-744-2-2-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"6\" ><div class=\"modeling_text panel-widget-style panel-widget-style-for-744-2-2-0\" ><div class=\"textwidget\"><p><span class=\"badge\">6<\/span>\u00a0 <a href=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/FC_Mixture.ppt\">Poster<\/a>\u00a0\u201cChallenges in assessing impact of an intervention to reduce HIV when comparison data is not available\u201d.<\/p>\n<\/div><\/div><\/div><\/div><\/div><div id=\"pg-744-3\"  class=\"panel-grid panel-no-style\" ><div id=\"pgc-744-3-0\"  class=\"panel-grid-cell\" ><div id=\"panel-744-3-0-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"7\" ><div class=\"modeling_text panel-widget-style panel-widget-style-for-744-3-0-0\" ><div class=\"textwidget\"><p><span class=\"badge\">7<\/span>\u00a0 <a href=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/LaymanLCS.pptx\">AMOS Model and Poster<\/a>\u00a0\u201cA layman\u2019s visual modeling introduction to latent change score analysis\u201d.<\/p>\n<\/div><\/div><\/div><\/div><div id=\"pgc-744-3-1\"  class=\"panel-grid-cell\" ><div id=\"panel-744-3-1-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"8\" ><div class=\"modeling_text panel-widget-style panel-widget-style-for-744-3-1-0\" ><div class=\"textwidget\"><p><span class=\"badge\">8<\/span>\u00a0 <a href=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/decoupling.pdf\">Mplus Outputs<\/a>\u00a0for the \u201c<a href=\"http:\/\/informahealthcare.com\/doi\/abs\/10.3109\/16066359.2014.892932\">Altering dynamic pathways to reduce substance use among youth: Changes achieved by dynamic coupling<\/a>\u201d paper.<\/p>\n<\/div><\/div><\/div><\/div><div id=\"pgc-744-3-2\"  class=\"panel-grid-cell\" ><div id=\"panel-744-3-2-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"9\" ><div class=\"modeling_text panel-widget-style panel-widget-style-for-744-3-2-0\" ><div class=\"textwidget\"><p><span class=\"badge\">9<\/span>\u00a0 <a href=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/Poster_CT-ASA_LatentVariables_20_by_30.pptx\">Poster Latent Variables<\/a>\u00a0<br \/>\u201cOn the uses, benefits and interpretive meanings of latent variables in Comparative Effectiveness (CE) research\u201d 12th annual <a href=\"http:\/\/www.amstat.org\/chapters\/Connecticut\/home\/index.htm\" class=\"broken_link\">CT - American Statistical Association mini-conference<\/a>.<\/p>\n<\/div><\/div><\/div><\/div><\/div><div id=\"pg-744-4\"  class=\"panel-grid panel-no-style\" ><div id=\"pgc-744-4-0\"  class=\"panel-grid-cell\" ><div id=\"panel-744-4-0-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"10\" ><div class=\"modeling_text panel-widget-style panel-widget-style-for-744-4-0-0\" ><div class=\"textwidget\"><p><span class=\"badge\">10<\/span>\u00a0 <a href=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/CareCoord_2FinalCFAs.pdf\">MPlus CFA outputs<\/a>\u00a0<br \/>\u201cDevelopment and validation of the Medical Home Care Coordination Survey for assessing care coordination in the primary care setting from the patient and provider perspectives\u201d, <a href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/26113153\">NIH<\/a>,\u00a0<a href=\"http:\/\/www.biomedcentral.com\/1472-6963\/15\/226\">Free PDF<\/a>.<\/p>\n<\/div><\/div><\/div><\/div><div id=\"pgc-744-4-1\"  class=\"panel-grid-cell panel-grid-cell-mobile-last\" ><div id=\"panel-744-4-1-0\" class=\"so-panel widget widget_black-studio-tinymce widget_black_studio_tinymce panel-first-child panel-last-child\" data-index=\"11\" ><div class=\"modeling_text panel-widget-style panel-widget-style-for-744-4-1-0\" ><div class=\"textwidget\"><p><span class=\"badge\">11<\/span>\u00a0 <a href=\"https:\/\/health.uconn.edu\/health-disparities\/wp-content\/uploads\/sites\/53\/2016\/06\/LVMeanings_Outputs.docx\">Online appendix<\/a>\u00a0(syntaxes and outputs)<\/p>\n<p>The utility of well-designed graphical displays for statistical analyses.<\/p>\n<p>The omnipresence of latent variables in statistics.<\/p>\n<\/div><\/div><\/div><\/div><div id=\"pgc-744-4-2\"  class=\"panel-grid-cell panel-grid-cell-empty\" ><\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"<p>Health Disparities (HD) are notoriously hard to identify reliably; moreover finding what causes them, and hence how to reduce and\u00a0eliminate them, is especially difficult, but models exist (see the Framework for Health equity below, the birth outcomes illustration, and other conceptual and practical models).The main reason is that simple group comparisons of a health outcome [&hellip;]<\/p>\n","protected":false},"author":5,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"footnotes":""},"acf":[],"publishpress_future_action":{"enabled":false,"date":"2026-04-23 05:04:00","action":"change-status","newStatus":"draft","terms":[],"taxonomy":""},"_links":{"self":[{"href":"https:\/\/health.uconn.edu\/health-disparities\/wp-json\/wp\/v2\/pages\/744"}],"collection":[{"href":"https:\/\/health.uconn.edu\/health-disparities\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/health.uconn.edu\/health-disparities\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/health.uconn.edu\/health-disparities\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/health.uconn.edu\/health-disparities\/wp-json\/wp\/v2\/comments?post=744"}],"version-history":[{"count":42,"href":"https:\/\/health.uconn.edu\/health-disparities\/wp-json\/wp\/v2\/pages\/744\/revisions"}],"predecessor-version":[{"id":4617,"href":"https:\/\/health.uconn.edu\/health-disparities\/wp-json\/wp\/v2\/pages\/744\/revisions\/4617"}],"wp:attachment":[{"href":"https:\/\/health.uconn.edu\/health-disparities\/wp-json\/wp\/v2\/media?parent=744"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}