Ipop: Moran's I adjusted for population size
|
|
|
|
|
Indications/Recommendations for use: Nearby areas tend to have similar disease rates when their populations and exposures are
alike. When rates in connected areas are similar Ipop will be large, when rates in connected areas are
different Ipop will be small (more).
|
|
Description: A test for spatial autocorrelation in disease
rates that accounts for geographic variation in population size. Ipop
is used to detect departures from spatial randomness, but, unlike
Moran's I, it accounts for differences in population size
across areas. If ignored, large differences in population size
decrease the ability of Moran's I to detect departures from
spatial randomness. This may cause one to fail to identify a true
cluster.
|
Test statistic:
Ipop is a spatial autocorrelation coefficient adjusted for the size of the population at risk.
Large values of Ipop indicate positive spatial autocorrelation; small value indicate negative spatial
autocorrelation.
|
|
Null Hypothesis:
Disease rates in connected areas are independent.
|
|
|
Alternative Hypothesis:
Disease rates in connected areas are not independent.
|
|
GeoMed Inputs:
A Ipop data file containing population sizes and disease rates, and a link file
assigning connection weights to locality pairs.
Ipop requires an Ipop data file, a link file and the number of runs.
|
GeoMed Outputs:
- Ipop, Ipop', E[Ipop]
- Variance and significance under randomization assumption, approximation, and simulation
- Plot of frequency distribution of Ipop obtained under simulation
|
|
Example Analysis
|
Reference:
Oden, Neal (1995). Adjusting Moran's I for Population Density,
Statistics in Medicine, 14, pp. 17-26.
|
