. Author manuscript; available in PMC: 2011 Dec 1.

Published in final edited form as: Genet Epidemiol. 2010 Dec;34(8):792–802. doi: 10.1002/gepi.20523

TABLE II.

Biases and RMSEs of risk parameters for the naive approach that ignores existence of the LD and the proposed method

		Naive approach		Proposed method
Parameter	True value	Bias	RMSE	Bias	RMSE
κ	−5.000	−0.060	0.024	−0.024	0.017
β _X	1.099	0.063	0.045	0.005	0.038
β _A1	0.693	−0.043	0.019	−0.007	0.013
β _A2	0.000	−0.046	0.022	0.002	0.014
β _AX1	0.693	0.169	0.064	0.005	0.028
β _AX2	0.693	0.113	0.049	0.005	0.026
P_{M_i}	0.250	<0.001	<0.001	<0.001	0.001
pr(X = 1)	0.500	0.002	0.001	<0.001	0.001

The results are based on 500 samples of 1,000 cases and 1,000 controls. Genotype is simulated at the two marker loci with P_{M_i} = 0.25, i = 1,2. The environmental covariate (X) is binary and measured with error with misclassification probabilities with misclassification probabilities being 0.20 for exposed and 0.25 for non-exposed subjects. Probability of disease is 0.0069 and is assumed to be known in the population. The data are simulated and analyzed under the additive effect model and the LD measure Δ_m₁m₂ = 0.02. RMSE, root mean-squared error.