Spatial analysis of bladder, kidney, and pancreatic cancer on upper Cape Cod: an application of generalized additive models to case-control data

Table 3 Summary of kidney cancer models showing degree of smoothing and global test statistic

Analysis	Span^a	Cases/Controls^d	Deviance p-value^e	Figure #
Crude All Residences	0.95	54/1220	<0.001	--
Crude All Residences	0.90^b	54/1220	-----^f	4a
Adjusted All Residences	0.90	54/1220	<0.001	4b
Adjusted All Residences	0.40^c	54/1220	-----^f	4c
Adjusted All Residences	0.15^c	54/1220	-----^f	4d

Span is the percentage of data used for smoothing the model.
^a Optimal span obtained by using the Akaike's Information Criterion (AIC) unless otherwise noted.
^b Same span as for adjusted, all residences.
^c Local minimum span was used.
^d Number of residences contributed to the analysis by participant status.
^e Null hypothesis is that the map is flat.
^f The p-values were omitted because the maps were created using a non-optimal span.

ISSN: 1476-069X