I have a work-in-progress: MeasurementErrorModels.jl. It allows lag-covariance matrices for both the predictor noise and response noise. I’ve added a github gist which illustrates a spatial model example. I’m currently working on adding models that allow both noisy and noiseless predictors, and Fisher information derived confidence intervals. Currently I assume that the noise covariances are known, but I’m interested in implementing models where e.g. only the correlation structure is known too.