Estimation of exposure to toxic releases using spatial interaction modeling

Table 5 OLS regression R-squared values by rural-urban code

Code	no term	contain.	buffer	Cutter	exp.	power
0	0.4971	0.4971	0.5682	0.5493	0.5100	0.4978
1	0.4113	0.4318	0.4795	0.4840	0.4119	0.4345
2	0.4654	0.4655	0.5143	0.5065	0.4655	0.4690
3	0.4618	0.4678	0.5216	0.5089	0.4621	0.4660
4	0.4815	0.4818	0.5514	0.5210	0.4828	0.4841
5	0.5886	0.5905	0.6753	0.6425	0.5899	0.5939
6	0.3990	0.3992	0.4562	0.4436	0.3997	0.3990
7	0.5231	0.5231	0.5882	0.5862	0.5234	0.5232
8	0.5555	0.5628	0.5829	0.5749	0.5560	0.5578
9	0.5741	0.5746	0.5892	0.5909	0.5748	0.5764

Results for multivariate ordinary least squares regression of age-adjusted lung cancer mortality versus covariates and risk estimates from releases of lung carcinogens and related compounds, separated by the county's 1993 rural-urban continuum code (see Table 6). Bold entries indicate which spatial interaction model performed best.

ISSN: 1476-072X