Implementation ofImplementation of Improvements to the Allocation Routine for HealthAllocation Routine for Health Insurance Coverage in the CPS ASECCPS ASECFederal Committee on Statistical MethodologyFederal Committee on Statistical Methodology Research ConferenceJanuary 10, 2012

Joanna Turner and Michel BoudreauxState Health Access Data Assistance Center (SHADAC)( )University of Minnesota, School of Public Health

Supported by a grant from The Robert Wood Johnson Foundation

AcknowledgementsAcknowledgements

• Thanks to the Health and Disability StatisticsThanks to the Health and Disability Statistics Branch, U.S. Census Bureau for their support of this work– Funded under contract #000000033114

• http://www.census.gov/hhes/www/hlthins/hlthins.html

www.shadac.org 2

OutlineOutline

• ContextContext

• BackgroundBackground

• Improvements to the allocation routine• Improvements to the allocation routine

• Historical trends from 1988 to 2011• Historical trends from 1988 to 2011

www.shadac.org 3

Importance of EstimatesImportance of Estimates

• SurveillanceSurveillance– Trends and correlates in coverage: Private coverage

decreasing as public coverage increases

• Policy Analysis– 1990: Medicaid expansions– 1997: Children’s Health Insurance Coverage (CHIP)

2010 US H lth R f Aff d bl C A t (ACA)– 2010: US Health Reform, Affordable Care Act (ACA)

www.shadac.org 4

Data NeedsData Needs

• Accurate estimates for a given yearAccurate estimates for a given year

• Consistent estimates over timeConsistent estimates over time

• Ability to study estimates by characteristics• Ability to study estimates by characteristics (i.e. age) and for individual states

www.shadac.org 5

Current Population Survey Annual Social d E i S l t (CPS ASEC)and Economic Supplement (CPS ASEC)

• CPS provides over 20 years of healthCPS provides over 20 years of health insurance coverage estimates

• CPS is a monthly labor force survey

• ASEC fielded in February to April – Additional questions on work, income, migration, andAdditional questions on work, income, migration, and

health insurance coverage

www.shadac.org 6

Current Population Survey Annual Social d E i S l t (CPS ASEC) (2)and Economic Supplement (CPS ASEC) (2)

• Health insurance coverage questions askHealth insurance coverage questions ask about coverage in the previous calendar year– For example, the 2011 ASEC asks about coverage

during 2010

f• All years in this presentation refer to the survey year, the year of the ASEC

www.shadac.org 7

Improvements to Health InsuranceImprovements to Health Insurance

• Census Bureau dedicated to improving theCensus Bureau dedicated to improving the quality of the health insurance estimates– 2000: Verification question – 2001: Separate CHIP question added – 2002: Sample expansion – 2005-2006: Correction to the assignment of private

coverage (1997-2004: approximation)2010: Assign Medicaid to uninsured foster children– 2010: Assign Medicaid to uninsured foster children

– 2010: Addition of premium costs and medical out-of-pocket information

www.shadac.org

– 2011: Improvements to missing data allocation 8

Background of AllocationBackground of Allocation

• Approximately 10% of monthly CPS sampleApproximately 10% of monthly CPS sample does not respond to ASEC– All data for these cases are imputed– Full Supplement Imputations (FSI)

• Additionally, 2-3% of respondents are missing data on health insurance items

www.shadac.org 9

Allocation MethodAllocation Method

• Hot deck randomly draws values for missingHot deck randomly draws values for missing cases (recipients) from similar non-missing records (donors)

• Donors are organized into matrices gconsisting of variables that define “similar”– For example age, marital status, work status

• Assumes missing is random within cells

www.shadac.org

– Maintains correlations within complete data

10

Background of InconsistenciesBackground of Inconsistencies

• Davern et al. (2007) discoveredDavern et al. (2007) discovered inconsistencies in the hot deck specification– Instrument allows any household member to be a

private plan dependent– Allocation routine assigned dependent coverage only

to nuclear family members of a policy holderto nuclear family members of a policy holder– Did not consider other coverage the respondent may

have had

www.shadac.org 11

Improvements to the Allocation R tiRoutine• Switch order with public coverage allocatedSwitch order with public coverage allocated

first, followed by private coverage• Include public coverage in the private p g p

coverage matrix• Remove nuclear family restrictiony

• Also, discovered and corrected a coding so, d sco e ed a d co ected a cod gerror that undercounted imputed direct purchase coverage for children

www.shadac.org 12

Results – 2009 Research FileResults 2009 Research File

Uninsured Estimates by Age and Imputation Routine

Old Routine New Routine

Uninsured Estimates by Age and Imputation Routine

Percent Count Percent CountAll Ages 15.4 46,340 14.9 44,832g , ,0 to 18 10.3 8,076 9.9 7,82019 to 64 20.3 37,617 19.7 36,38619 to 64 20.3 37,617 19.7 36,38665+ 1.7 646 1.7 627

www.shadac.org 13

Source: 2009 CPS ASEC Research File; analysis conducted by SHADAC

Detailed ResultsDetailed Results

• Available in “Modifications to the ImputationAvailable in Modifications to the Imputation Routine for Health Insurance in the CPS ASEC: Description and Evaluation,” Boudreaux and Turner, 2011, at http://www.census.gov/hhes/www/hlthins/dat

/ hlth/SHADAC dfa/revhlth/SHADAC.pdf

www.shadac.org 14

ImplementationImplementation

• Improvements and coding correctionImprovements and coding correction implemented with the 2011 ASEC

• Improvements and coding correction applied to the 2000-2010 ASEC’s – Supplants previous revised series

www.shadac.org 15

Historical ModificationsHistorical Modifications

• Census Bureau dedicated to improving theCensus Bureau dedicated to improving the quality of the health insurance estimates– 2000: Verification question – 2001: Separate CHIP question added – 2002: Sample expansion – 2005-2006: Correction to the assignment of private

coverage (1997-2004: approximation)2010: Assign Medicaid to uninsured foster children– 2010: Assign Medicaid to uninsured foster children

– 2010: Addition of premium costs and medical out-of-pocket information

www.shadac.org

– 2011: Improvements to missing data allocation 16

Comparisons Over Time by Data SeriesComparisons Over Time by Data Series

• RevisedRevised– New allocation routine and all prior modifications

• OriginalOriginal– Old allocation routine with 1997-2004 approximation

• SHADAC-Enhanced– Developed by SHADAC to harmonize the data over

time – Removes full supplement imputations and re-weights– Revised to include the new allocation routine

www.shadac.org 17

All AgesUninsured Time Series by Data Series

1617

All Ages15

1rc

ent

1314P

e12

1990 1995 2000 2005 2010Year

Revised OriginalEnhanced

18

Source: 1988-2011 CPS ASEC’s; analysis conducted by SHADAC

All AgesPrivate Coverage Time Series by Data Series

7476

All Ages70

72rc

ent

6668

Pe

646

1990 1995 2000 2005 2010Year

Revised OriginalEnhanced

19

Source: 1988-2011 CPS ASEC’s; analysis conducted by SHADAC

All APublic Coverage Time Series by Data Series

3031

All Ages27

2829

rcen

t25

262

Per

2324

1990 1995 2000 2005 2010Year

Revised OriginalEnhanced

20

Source: 1988-2011 CPS ASEC’s; analysis conducted by SHADAC

ConclusionsConclusions

• The new allocation routine improves theThe new allocation routine improves the quality of the CPS ASEC health insurance coverage estimates

• The data revisions create a consistent time series for 2000+ which is important for surveillance and policy analysis

• SHADAC-Enhanced recommended for pre-2000 l i f i t t ti i

www.shadac.org

2000 analysis for a consistent time series

21

Joanna TurnerState Health Access Data Assistance CenterState Health Access Data Assistance Center

University of Minnesota, Minneapolis, MN612-624-4802

turn0053@umn.edu

Sign up to receive our newsletter and updates at www shadac orgSign up to receive our newsletter and updates at www.shadac.org

facebook.com/shadac4states

22

@SHADAC