Small Area (e.g. County-level) Estimates. Concepts Considerable interest in small area estimates of uninsured (e.g. County level) Two estimation methods.

Slides:



Advertisements
Similar presentations
Behavioral Risk Factor Surveillance System
Advertisements

Considerations for Moving Forward Cindy Mann Executive Director Georgetown University Health Policy Institute Center for Children and Families Health Foundation.
Health Insurance Coverage and Access in Rural America Timothy D. McBride, PhD September 20, 2004.
APHA-2006: Session Choice of denominator to measure disparities in motor vehicle crash deaths of teens and young adults Christopher J. Mansfield,
Eligible Women and Participation in the Women’s Health Network Ellen M. Kramer ScD RD April 7, 2005.
Demographic Analysis of Henderson County Prepared by Jason Bremner for Children and Family Resource Center.
Oklahoma Regional Demographic Profiles Created from the U.S. Census Bureau’s American Community Survey ( Public Use Microdata Sample) June 2009.
What, Why and How: Modeling to Address Health Policy Questions Deborah Chollet Senior Fellow, Mathematica Policy Research The Robert Wood Johnson Foundation’s.
Concurrent Tobacco Use: A Study of Socio-demographic Correlates Nasir Mushtaq, MPH Laura A Beebe, PhD University of Oklahoma Health Sciences Center.
North Carolina Aging Demographics
Changing Demographics in Texas
Chapter 1 The Where, Why, and How of Data Collection
Texas: Demographic Characteristics and Trends Texas Association of Healthcare Interpreters and Translators August 19, 2011 Dallas, TX.
This research is funded in part through a U.S. Health Resources and Services Administration, State Planning Grant to the Hawaii State Department of Health.
The Effort to Develop Disability Questions for the Current Population Survey Terence M. McMenamin U.S. Bureau of Labor Statistics October 5, 2006.
Measures of Income, Poverty and Health Insurance Wesley Basel, U.S. Census Bureau Presented at the Walter Cronkite School of Journalism June 17, :00.
Bridging the Gaps: Dealing with Major Survey Changes in Data Set Harmonization Joint Statistical Meetings Minneapolis, MN August 9, 2005 Presented by:
This research is funded in part through a U.S. Health Resources and Services Administration, State Planning Grant to the Hawaii State Department of Health,
This research is funded in part through a U.S. Health Resources and Services Administration, State Planning Grant to the Hawaii State Department of Health.
Texas Demographic Characteristics and Trends Texas Association of Mutual Insurance Companies October 7, 2010 Round Rock, TX 1.
Enhancing Surveillance with the Colorado Child Health Survey Jodi Drisko, MSPH Jason Gannon Alyson Shupe, MSW, PhD Colorado Department of Public Health.
Health Insurance Coverage of California’s Working Latinos Howard Greenwald Suzanne O'Keefe Mark DiCamillo University of Southern California California.
Socio-Economic & Demographic Data Tools for Proactive Planning Robin Blakely-Armitage STATE OF NEW YORK CITIES: Creative Responses to Fiscal Stress March.
Demography and Aging. What is “demography”? Demography is the study of populations Counting and describing people Age, sex, income, marital status… Demographers.
1 A Tale of Two Cities A Statistical Analysis of Baltimore’s Mature Workers Presentation for September 2008 Board Meeting.
Turning Data into Action for Colorectal Cancer November 17, 2014 Jessica Shaffer, Director, Maine CDC Colorectal Cancer Control Program
Effects of Income Imputation on Traditional Poverty Estimates The views expressed here are the authors and do not represent the official positions.
Customer : contractor : December, 2012 Sociologic Research on Awareness of Industrial Property Protection Possibilities.
Colorado Children’s Health Insurance Status 2012 Update April 6, 2012 All Kids Covered.
A Profile of Health among Massachusetts Adults: Highlights from the Massachusetts Behavioral Risk Factor Surveillance System (BRFSS) Health Survey.
Using and Interpreting Data Community Health Assessment Unit Office of Epidemiology.
Liesl Eathington Iowa Community Indicators Program Iowa State University October 2014.
Women’s Health in Massachusetts Highlights from the Massachusetts Behavioral Risk Factor Surveillance System (BRFSS): Health Survey Program Bureau.
Exhibit 1. Uninsured Rates for Blacks and Hispanics Are One-and-a-Half to Two Times Higher Than for Whites (2013) Notes: Black and white refer to black.
Excess cost growth in Medicare, Medicaid, and all other health care spending Source: CBO, A Federal Perspective on Health Care Policy and Costs, 2008.
A presentation for the Women’s Institute for a Secure Retirement February 28, 2008 Barbara D. Bovbjerg Director Education, Workforce, and Income Security.
Assessing the Value of the NHIS for Studying Changes in State Health Coverage Policies: The Case of New York Sharon K. Long John A. Graves Stephen Zuckerman.
A Presentation of the Colorado Health Institute 303 E. 17 th Avenue, Suite 930 Denver, Colorado (Twitter)
Available Data on Alaska’s Uninsured December 2006 Health Planning & Systems Development Unit Office of the Commissioner Alaska Department of Health &
Using IPUMS.org Katie Genadek Minnesota Population Center University of Minnesota The IPUMS projects are funded by the National Science.
The Uninsured in Alameda County 2010 December 2010.
Community Health Needs Assessment Introduction and Overview Berwood Yost Franklin & Marshall College.
Introduction Biostatistics Analysis: Lecture 1 Definitions and Data Collection.
Veterans Using and Uninsured Veterans Not Using VA Health Care Karin Nelson, MD, MSHS Gordon A. Starkebaum, MD Gayle E. Reiber, PhD, MPH VA Puget Sound.
Health Profile of Massachusetts Adults In Selected Cities, 2008 Bureau of Health Statistics, Research, and Evaluation, Division of Research and Epidemiology,
Oklahoma Regional Demographic Profiles Created from the U.S. Census Bureau’s American Community Survey ( Public Use Microdata Sample) June 2009.
Health Insurance and the Uninsured in Kansas February 2008 Kansas Health Institute This chartpack may be used as a presentation in its entirety. Individual.
Things that May Affect the Estimates from the American Community Survey Updated February 2013.
Chap 7-1 A Course In Business Statistics, 4th © 2006 Prentice-Hall, Inc. A Course In Business Statistics 4 th Edition Chapter 7 Estimating Population Values.
American Community Survey (ACS) Product Types: Tables and Maps Samples Revised
2007 YOUTH RISK BEHAVIOR SURVEY DATA: DURHAM COUNTY AND COMPARISON LOCATIONS Youth Violence.
VerdierView Graph # 1 OVERVIEW Problems With State-Level Estimates in National Surveys of the Uninsured Statistically Enhancing the Current Population.
Incorporating Multiple Evidence Sources for the Assessment of Breast Cancer Policies and Practices J. Jackson-Thompson, Gentry White, Missouri Cancer Registry,
Chap 7-1 A Course In Business Statistics, 4th © 2006 Prentice-Hall, Inc. A Course In Business Statistics 4 th Edition Chapter 7 Estimating Population Values.
Economics and Statistics Administration U.S. CENSUS BUREAU U.S. Department of Commerce The Foreign-Born Population in New Mexico Size, Distribution, and.
U.S. DEPARTMENT OF HEALTH AND HUMAN SERVICES Centers for Disease Control and Prevention National Center for Health Statistics Occupational exposure to.
Presented at The 129th Annual Meeting of the American Public Health Association Atlanta, GA, October 21–25, 2001 Presented by Amanda A. Honeycutt Linda.
Project 2030 Supporters Blue Cross/Blue Shield of Montana Montana Agricultural Experiment Station Montana Area Agencies on Aging Association Montana Association.
1 The Mortality of China’s Oldest Old: Comparisons from the Healthy Longevity Survey (HLS) and the 2000 Census Daniel Goodkind International Programs.
Centers for Disease Control and Prevention National Center for Health Statistics Elizabeth Arias, Ph.D. Mortality Statistics Branch Division of Vital Statistics.
Estimating Wisconsin Asthma Prevalence Using Clinical Electronic Health Records and Public Health Data Carrie Tomasallo, PhD, MPH Wisconsin Division of.
Healthy Women: State Trends in Health and Mortality CD-ROM training Kate Brett Joanna Skilogianis Centers for Disease Control and Prevention National Center.
27a. Percentage of workers with health insurance, by source and industry, 2010 (Wage-and-salary workers) 86% 85% 82% 80% 90% 68% 89% 83% 95% 62%
Presented by: Khaleel S. Hussaini PhD Bureau Chief, Public Health Statistics Division of Public Health Preparedness Judy Bass Arizona’s BRFSS Coordinator.
Comparing New York and Massachusetts: Implications for Reform Elise Hubert United Hospital Fund June 9, 2006.
Improving Community Health through Planning and Partnerships Nelson Community Health Council.
Improving Community Health through Planning and Partnerships Albemarle and Charlottesville Community Health Council.
Yolo County Obesity Data Yolo County Childhood Nutrition and Fitness Forum September 18, 2004 Samrina Marshall, MD, MPH Assistant Health Officer, Yolo.
26a. Percentage of workers with health insurance, by source and industry, % 94.7% 92.9% 91.8% 91.0% 89.9% 89.2% 78.3% 73.4% 89.9%
Summary of Slide Content
Presentation transcript:

Small Area (e.g. County-level) Estimates

Concepts Considerable interest in small area estimates of uninsured (e.g. County level) Two estimation methods for an area: –Direct: measure rate from a sample of population of interest –Indirect: measure rate from a “superpopulation” and apply to smaller areas Direct is preferred, but expensive – necessary to have suitable number of respondents in each area (e.g., 100 counties).

Concepts Direct estimates, using CPS precision standards, would require surveying approximately 400,000 North Carolinians (4000 per county). Indirect approach: –Model probability of uninsured for state residents –Apply probability to county residents

Four out of six shapes (with known colors) are blue 4/6 = 83% Direct Estimation Indirect Estimation ? ?? ? ? We know that in similar rectangles, 75% of circles and 50% of triangles are blue. ? ? 2.25 circles and 2 triangles are blue: ( ) / 7 = 61% Comparison of Direct and Indirect ? ? ? ? ? ?

Methods 1. Use Current Population Survey data on North Carolina residents to estimate the probability of being uninsured in Allow the following to affect the probability of being uninsured: Age, gender, race/ethnicity, employment status, industry, income, education. 2. Apply observed probabilities to demographics of each county.

Methods Comparability with other estimates –In most results presented here, we combine last three years putting more weight on recent surveys. “One year” estimates less precise “Multiyear” estimates less responsive to trends –Eliminate all respondents age 65 or over. BRFSS, published by State Center for Health Statistics, has direct estimates on some counties. Different question wording precludes direct comparison. We are working on combining the two approaches to get better estimates. –Direct estimation, of course, still entails surveying a sample

Results Complete report –Available at Highlights: –Percentage 0-64 year olds without insurance varies from 15.9% (Wake) to 26.1% (Duplin) –Number of uninsured residents varies from 850 (Tyrrell) to 115,000 (Mecklenburg)

CPS (indirect) BRFSS (direct)

Summary Approximately percent of North Carolinians between the ages of 0 and 64 had no health insurance for the entirety of –Evidence of an increase over the past four years Considering the risk of being uninsured for a given characteristic may yield different policy conclusions than considering the characteristics of the uninsured –For example, unemployed are more likely to be uninsured, but relatively few uninsured are unemployed. Increases in statewide uninsured rate due somewhat to changes in demographic structure, but more due to changes in UI rates within demographic Statewide, evidence of higher uninsured rates in Eastern and Mountain Counties

For More Information Sheps Center for Health Services Research, UNC – –Click for county-level estimates –2003 estimates not posted yet, but soon Kaiser Family Foundation –Analysis of national trends – U.S. Census Bureau –Results of national surveys – Behavioral Risk Factor Surveillance System –North Carolina State Center for Health Statistics –