Measuring uncertainty in the Local Authority Population Estimates

Download Report

Transcript Measuring uncertainty in the Local Authority Population Estimates

Measuring Uncertainty in
Population Estimates
at Local Authority Level
Ruth Fulton, Bex Newell, Dorothee Schneider
1
Outline
• Project aim
• Overall method
• Method internal migration
• Method international migration
• Outputs
2
Project aim
Improve understanding, measurement and
reporting of the quality of population estimates at
LA level
• Obtain overall quality measures for annual
population estimates at LA level
3
Mid-Year Population Estimates
• Cohort component method
Pop.(t) = pop.(t-1) + births
– deaths
+ internal net migration
+ international net migration
• Determining associated uncertainty is complex
Mixed sources: Census, administrative sources, surveys
Different estimation methods
4
Measuring uncertainty: Overall method
- Components with biggest impact:
2001 Census-based estimate
Internal migration
International migration
- Estimate distribution of error for component
- Combine error estimates into overall quality
measure for MYE at LA level
Error (t) = error (t-1)
+ error (net internal migration)
+ error (net international migration)
5
Internal migration
• Estimates based on GP registration data
• Sources of uncertainty in estimates related to:
• Migrants missing from GP register
• Time lags between moving and re-registration
• Double counting of school boarders
6
Method for internal migration
• Benchmark approach
• Uses adjusted 2001 Census data as benchmark
• Applies model from 2001 to subsequent years
• Limitation – does not cover all quality issues
7
Method for internal migration (ctd.)
• Movers in Census: those with other address
one year ago
• Movers in PRDS: those with different
addresses in two downloads
Census data adjusted to be as similar to PRDS data
as possible
• Compare observed number of migrants to a
‘true’ number of migrants
• Error represented by scaling factor of truth
(Census)/PRDS
8
Age pattern
Mean log scaling factors for inflows by age and sex
0.4
0.3
Mean lsf
0.2
0.1
0.0
-0.1
-0.2
Males
-0.3
Females
-0.4
0
10
20
30
40
50
60
70
80
Age
• log(Census/PRDS)
• shows double counting of school boarders
• shows undercount of young male migrants
9
Geographical variation
- Scaling factors vary by
area
Mean log(Scaling Factors)
Inflows
- Undercount in urban
areas or areas with high
proportion of students
- Cluster analysis
10
Model
• Fit model to log of scaling factors of groups of LAs
• Obtain predicted values and residuals
 Error measure is obtained by simulating from this
distribution
.5
0
-.5
Mean predicted log(sf)
1
Mean predicted log scaling factors, Inflows male
0
20
40
60
age
group 1
group 3
group 2
group 4
11
Distribution of estimated inflows
example LA
0
5.0e-04
.001
Density
.0015
.002
green: PRDS flow, red: Census (observed truth)
6000
6500
7000
estimated 'true' flow
7500
8000
12
International migration
• Focuses on intentions-based IPS estimates
• Multi-stage approach to distribute to national estimates
to lower levels of geography
National
IPS direct estimate
Regional
Calibrate to Labour Force Survey (LFS)
3 year average
Intermediate (NMGi)
Distribute using IPS 3 year average
Local Authority (LA)
Distribute using immigration model
13
International migration (ctd)
• Produce error distribution for statistical error
Bootstrapping approach
Resampling IPS
Resampling LFS (regional level)
Reproduce estimation method with new samples
14
Outputs
Outputs
• Composite quality measure will be derived from the
overall error distribution
• LAs will be banded based on this measure
15
Questions?
Contact
[email protected]
[email protected]
16