Skip to main content
. 2016 Nov 12;5(12):649–655. doi: 10.1002/psp4.12148

Figure 1.

Figure 1

The response variable vector y is observed. There are k explanatory variables (covariates) { x1, …, xk} that are observed and a model is built that defines the relationship with parameters {θ1, …, θκ}. We see that there are also k′ latent variables with associated parameters. The model based on xk may fail to extrapolate beyond the current experiment due to the unforeseen influence of the latent variables.