What is a good introduction to errors-in-variables models?

Question

I'm aware of this resource https://en.wikipedia.org/wiki/Errors-in-variables_models, but I don't put a lot of faith into wikipedia articles on stats, so I'm looking for some reliable references on the subject (ideally academic references). If it can help in suggesting me something, I'm already familiar with standard regression models, and a bit with mixed models.

Do you have any good recommendations? If it's just a chapter in a textbook, I'm interested as long as it covers the basics and (ideally) suggests further resources.

Ideally I'm looking for recent resources. I ask for recent resources because I'm afraid that too old resources might be outdated, or may miss important recent developments on the subject. However if you know great old resources I'm interested, but in this case it would be great to know what they possibly miss regarding recent developments. Cheers,

Answer 1

Not too long ago I spent quite some time looking into a lot of resources in this particular area, and the best resources I found (in descending order) were:

1. Measurement Error in Nonlinear Models by Carroll et al. (2006). Provides a very good introduction into the problems associated with measurement errors, and then covers likelihood-based and Bayesian solutions.
2. Measurement Error and Latent Variables in Econometrics by Wansbeek (2000). Points out the thematic overlap between errors-in-variables and proxy/latent variable constructs (if $X$ is measured with error as $X^\ast$, then one may consider the measurable $X^\ast$ to be a proxy of the latent (unmeasurable) $X$), but then focuses on econometrics-typical solutions like instrumental variable models
3. Measurement Error and Misclassification in Statistics and Epidemiology by Gustafson (2004). The shortest of the three, and from the way it is written it is best not to be read first, but rather after reading one of the other two. But it contains some very nice results not included in the others.