Worksheet Name

Male

Contents

Modelled, published and census† based health prevalence †† rates and healthy life expectancies by age and area for the periods 2010 to 2012 and 2013 to 2015*

Worksheet Name

Female

Contents

Modelled, published and census† based health prevalence †† rates and healthy life expectancies by age and area for the periods 2010 to 2012 and 2013 to 2015*

Worksheet name

Adjusted R Squared

Contents

Adjusted R Squared by sex, age and area for 2013 to 2015, for the 3 methods tested.

Notes

• Figures are not calculated for City of London or Isles of Scilly due to small numbers of deaths and populations.

• Figures are based on the number of deaths registered and mid-year population estimates, aggregated over 3 consecutive years.

• Figures are based on geographical boundaries as of May 2016.

• Figures for England, Wales, regions, counties and local authorities exclude deaths of non-residents.

• Scotland includes non-usual residents who die in Scotland and do not have an area of residence within Scotland and imputation is used to assign to geography of ‘residence’ (see section 1.3.1).

• Northern Ireland also includes non-usual residents whom are allocated to place of death - See for more details.

• Excludes residents of communal establishments except NHS housing and students in halls of residence where inclusion takes place at their parents’ address.

• Local areas for England are upper tier local authorities for healthy and disability-free life expectancy.

• Local areas in Wales are unitary authorities.

• Local areas in Scotland are council areas.

• Local areas in Northern Ireland* are local government districts.

• • Northern Ireland local area data only covers the period 2013 to 2015.

• † Census estimates only cover the period 2010 to 2012.

• †† Health prevalence represents the proportion of the population reporting their general health as either very good or good.

The adjusted R square term:

Similar to the R squared term, the adjusted R squared term measures the explanatory power of a regression model by measuring how well the data points fit the curve or equation predicted by a regression model. The adjusted R squared also takes into account the number of terms that have been added to the model to adjust the R square. It has a tendency to decrease if irrelevant terms have been added to the model and increase if more useful terms are added in. The adjusted R squared can sometimes be negative, if there are too many explanatory variables that weakly predict the model, given the amount of observations. The closer an adjusted R squared value is to 1, the more accurate explanatory power the model has.