. Author manuscript; available in PMC: 2010 Oct 12.

Published in final edited form as: Stat Med. 2009 May 15;28(11):1620–1635. doi: 10.1002/sim.3563

Table III.

Mean bias, MSE, correlation and SE for predicted values with two independent variables following a normal distribution.

Sample size, method	Mean bias	MSE	Correlation	SEE
$n = 300 (m_{1}^{*} = m_{2}^{†} = m_{3}^{‡} = 100)$ , New	0.0108	0.8046	0.9949	6.0496
$n = 300 (m_{1}^{*} = m_{2}^{†} = m_{3}^{‡} = 100)$ , SHR	14.1519	221.1321	0.9900	—
$n = 3000 (m_{1}^{*} = m_{2}^{†} = m_{3}^{‡} = 1000)$ , New	−0.0092	0.0723	0.9996	1.8656
$n = 3000 (m_{1}^{*} = m_{2}^{†} = m_{3}^{‡} = 1000)$ , SHR	14.0304	209.9250	0.9954	—

Note: Correlation is the mean correlation between observed and predicted values across simulations. SEE is the mean of standard error estimates for predicted values.

The sample size for a subset with only outcome Y and predictor X₁.

^†

The sample size for a subset with only outcome Y and predictor X₂.

^‡

The sample size for a subset with only predictors X₁ and X₂.