Page 158 - Contributed Paper Session (CPS) - Volume 3

CPS1979 Francisco N. de los R.
Voter turnout was generally high in the NLE of 2016 as indicated by an
average of 79% across the 86 areal units (Figure 1). The special province of
Cotabato City was outlying with a turnout of only 48%. There was a significant
positive spatial autocorrelation in voter turnout (Moran’s I = 0.22, p = 0.0067).
This indicates that areas with relatively higher voter turnout are spatially close.
A similar conclusion can be said of areas with relatively lower voter turnout.
There is suggestion of parity in voter participation across provinces as
evidenced by a dissimilarity index of D=0.15. The 95% confidence interval is
(0.113, 0.175) based on 10,000 bootstrap samples.
The hierarchical model had poor fit under the assumption of high spatial
variation scenario within clusters given the official election voter turnout data
(Table 1). Here, the standard deviation of residuals and Deviance Information
Criterion (DIC) are highest within tiers of MCMC sample. The width of the 95%
credible interval for the dissimilarity index, intercept term for the logit
expression, and are generally largest.
2
The hierarchical model had relatively better fit under the assumption of
moderate spatial variation scenario as compared to the model given a high
spatial variation assumption. In this scenario, the standard deviation of
residuals and Deviance Information Criterion (DIC) are lower within tiers of
MCMC sample. The width of the 95% credible interval for the dissimilarity
index, intercept term for the logit expression, and are tend to be
2
narrower. The hierarchical model showed best fit under low spatial variation
scenario within clusters given the official election turnout data. The 95%
confidence intervals are narrowest within each group of MCMC samples.
Residual variability is at its least and so is the DIC. Estimates seem to have
good precision at M=30,000 MCMC samples (50% burn-in). Here, the spatial
autocorrelation parameter can reasonably be expected to fall in the interval
(0.001, 0.181).
The dissimilarity indices generated across all scenarios are relatively small.
These values signify that variability in voter participation in indeed small across
provinces. There is generally high turnout nationwide with provincial rates
which are not far from this general average.

147 | I S I W S C 2 0 1 9