Connecticut State Department of Public Health

Connecticut Population Datasets in SAS Format

 
Population estimates for multiple years (2000+) are available in a single dataset to provide a single resource for longitudinal analyses. All datasets were originally published by the National Center for Health Statistics. 
 

State and county population estimates by Age, Sex, Race and Hispanic Ethnicity (ASRH) are produced annually by the National Center for Health Statistics (NCHS). NCHS provides annual population estimates by race using broad, single-race categories. This is a simpler race classification format than the 31 single and multiple-race categories published by the U.S. Census for the decennial 2000 and 2010 datasets.  The 'bridged estimates' (PDF) provide rate denominators that can be used to calculate the race-specific rates used to monitor health indicators.

 

Note that the 2001-2009 figures are smoothed intercensal estimates. As described by the US Census, “Intercensal estimates are produced each decade by adjusting the existing time series of postcensal estimates for a decade to smooth the transition from one decennial census count to the next.  They differ from the postcensal estimates that are released annually because they rely on a formula that redistributes the difference between the April 1 postcensal estimate and April 1 census count for the end of the decade across the estimates for that decade.”

 

Aggregating years or demographic groups:

  • When combining multiple years of population estimates into a single estimate (such as a 5-year population estimate), be sure to properly sum the individual years by the ASRH categories to create an aggregated 5-year POP value.
  • When combining ages, sexes, races, or ethnicities (such as combining Black, American Indian, Asian, and Hispanic into a single group), be sure to properly sum the ASRH combinations to create an aggregated POP value that represents the new ASRH grouping.

Recommended Citation:  Citation information is included within each dataset.

 

 

State-level Datasets2 in SAS and Excel:

 

State_Age_Sex_Race_Ethn_2010-2019.zip

  • Age in single years (0-85+):  a1srh_state_icen0009_pcen1019
  • Age in 18 age groups (0-4,5-9,...,85+):  a18srh_state_icen0009_pcen1019
  • Age in 19 age groups (0, 1-4, 5-9,...,85+):  a19srh_state_icen0009_pcen1019
  • Formats for the age, sex, race, and Hispanic ethnicity variables:  nchs_asrh_formats.sas    
  • SAS program that can be used to create custom tabulations:  tabulate_asrh_series.sas  
 

County-level Datasets2 in SAS and Excel:

 

County_Age_Sex_Race_Ethn_2010-2019.zip

  • Age in single years (0-85+):  a1srh_cty_icen0009_pcen1019
  • Age in 18 age groups (0-4,5-9,...,85+):  a18srh_cty_icen0009_pcen1019
  • Age in 19 age groups (0, 1-4, 5-9,...,85+):  a19srh_cty_icen0009_pcen1019
  • Formats for the age, sex, race, and Hispanic ethnicity variables:  nchs_asrh_formats.sas
  • SAS program that can be used to create custom tabulations:  tabulate_asrh_series.sas    

Notes:

1 Ingram DD, Parker JD, Schenker N, Weed JA, Hamilton B, Arias E, Madans JH. United States Census 2000 population with bridged race categories. National Center for Health Statistics. Vital Health Stat 2(135). 2003. http://www.cdc.gov/nchs/data/series/sr_02/sr02_135.pdf

 

2 Annual estimates provided here by DPH use the version or ‘vintage’ originally published by NCHS for each year and thus are consistent with DPH published estimates. NCHS and the US Census periodically issue updates of state population estimates, but these modified figures will not match previously published DPH estimates. When necessary, the Connecticut DPH has made minor corrections to the published NCHS figures. These corrections are discussed in our town-level population estimate reports. Updates to the ASRH dataset due to corrections to previous years estimates are available via NCHS website, as are county-level estimates by ASRH and ASRH estimates by single year of age.

 

3 County level ASRH estimates that are consistent with the original state level figures are not available for 2000 and 2001. NCHS did not publish July 1, 2000 estimates or July 1, 2001 estimates at the county level when the original state level estimates were produced. County level estimates for 2000 and 2001 were produced at a later date, with the release of the 2002 estimates. However, these "vintage 2002" data include modified county level 2000 and 2001 estimates that differ from the official CT State Population estimates. Please see our technical notes for more information.

 

4 Changes in Estimates Methodology: The Vintage 2008 postcensal population estimates reflect three major improvements in the estimates methodology. Improvements include changes in 1) the estimation of net international migration, 2) the incorporation of accepted challenges and special censuses into the national population estimates, and 3) the imputation of the race and Hispanic origin for births. These methodology changes go beyond the extensive methodology changes implemented for the Vintage 2007 estimates. The net impact of the various methodologic changes is a downward shift of the Vintage 2008 postcensal population estimates when compared to those from the Vintage 2007 series; the Vintage 2007 postcensal estimates also reflected a downward shift when compared to the 2006 estimates.

 

See the Census' Documentation for the Population Estimates for more information.

 

5 Changes in Estimates Methodology Implemented for Vintage 2009:  The Vintage 2009 population estimates reflect four major improvements in the estimates methodology: 1) changes in the estimation of net international migration, 2) changes in the estimation of the distribution of deaths to people aged 70 and older by age, sex, race, and Hispanic origin, 3) changes in the estimation of domestic migration of the population age 65 years and older, and 4) changes in the estimation of the age distribution of migration to and from counties (4, 5). Adjustments for Hurricanes Katrina and Rita were accomplished using a different approach than used for Vintage 2006-Vintage 2008 (4,6). At the national level, the result of the various methodologic changes is an upward shift of the Vintage 2009 postcensal population estimates when compared to those from the Vintage 2008 series. At the State and county level, some race and age groups experienced substantial changes (comparison of July 1, 2008 estimates from the Vintage 2008 series with the July 1, 2008 and July 1, 2009 estimates from the Vintage 2009 series).