Adult Obesity: Model-based estimates using HSE

The NHS Information Centre for Health and Social Care commissioned the National Centre for Social Research (NatCen) to provide model-based estimates of adult obesity (as well as other lifestyle behaviours), using HSE, Census and other data.

  • Methodology: A statistical model was used to represent the relationships between obesity and area-level characteristics. The 2001 Census provided the main source of demographic and social covariate data. Other routine sources of data providing area-level characteristics for LAs included all age-all cause mortality, diversity index, life expectancy, emergency hospital admissions, hospital admissions attributable to alcohol, job seekers allowance claimant counts and educational attainment. The model outputs were applied in conjunction with covariate data (available for all LAs) to estimate the 'expected' prevalence given the characteristics of the area. An adjustment factor was applied to ensure that the model-based estimates for each LA corresponded with the 2003-2005 direct estimates at GOR/SHA level taken from the Health Survey for England data. A similar methodology was also used to derive estimates for PCOs.
  • Frequency of data: 2000-2002 (data out of press), 2003-2005
  • Most recent return: 2003 - 2005
  • Commissioned by: Department of Health (2000-2002); Information Centre (2003-2005)
  • Coverage: England: PCO, LA, MSOA
  • Caveats: These model-based healthy lifestyle indicators are subject to both sampling and non-sampling error. The use of statistical models for prediction involves making assumptions about relationships in the data. The model-based estimate generated for a particular area is the expected measure for that area based on its population characteristics - and so does not provide an estimate of the actual prevalence. As such, the estimates are unable to take account of any additional local factors that may impact on the true prevalence rate (e.g. local initiatives designed to reduce obesity). Users should also note that NatCen do not encourage any ranking of the MSOA estimates within larger areas such as LAs, PCOs, MSOAs, Primary Care Trusts or Strategic Health Authorities. The 2003-2005 estimates are NOT comparable with the 2000-2002 estimates. The model-based estimates have been produced solely for LAs and cannot be translated onto any other geographical boundary system (ie aggregated or averaged over any other spatial unit).