In the simulated dataset 3, each subject has 1 to 5 measurement values from the new method and 10 to 15 measurement values from the reference method. Compared to the reference method, the new method has differential bias of 3 and proportional bias of 0.9. Variance of the new method is larger than that for the reference method.
data3An object of class data.frame with 1250 rows and 3 columns.
@format A data frame with three variables:
ididentification number for subjects
y1values from the new measurement method
y2values from the reference measurement method
Dataset 3 was created based on the following equations: $$y_{1ij}=3+0.9x_{i}+\varepsilon_{1ij}, \varepsilon_{1ij} \mid x_i \sim N(0,(2+0.06x_i)^2)$$ $$y_{2ij}=x_i+\varepsilon_{2ij},\varepsilon_{2ij} \mid x_i\sim N(0,(1+0.01x_i)^2)$$ $$x_i\sim Uniform[10-40]$$
for \(i = 1, 2, \ldots, 100\), \(j=1,2,\ldots,n_{1i} / n_{2i}\) and the number of repeated measurements for each subject \(i\) from the new and reference method was \(n_{1i} \sim Uniform[1-5]\) and \(n_{2i} \sim Uniform[10-15]\) respectively.