I have a series of human growth data that I wish to fit to a 3 parameter logarithmic growth curve:

s(i) = Beta0 + B1*T + B2*ln(t), where s is a length and t is an age.

The only problem is that this age is not a point estimate. Rather, I have an upper and lower boundary to an age distribution based on tooth development. The age estimation technique returns a lognormal age distribution with an upper and lower 95% PI. I'd like to account for this "estimation" in my model, as opposed to a just plugging in a biased mean point estimate in OLS. I'd like to do this in R, but I am struggling with the best way to model and/or 'maximize' this interval so as to return a fitted curve based on the interval values. I have thought through deconvulution, simulation, Bayesian techniques, ODR, and other maximizing techniques to find the parameters that best-fit the data.

Any suggestions on how to handle such "error" in an explanatory variable, when fitting data to a logarithmic (or any) model such as the one described above??


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.