Signal frequency estimation (regression with sinusoidal mean) in PyMC3

[junpenglao]

I think you might find the discussions in this post helpful:

How to model sinusoids in white gaussian noise

I am trying to a handle on how to use a some of the theano math functions within a probability model. My first effort was to reconstruct the parameters of a single unknown sinusoid in white Gaussian noise, which is a very common introductory problem in astrostatistics. It also has the advantage of having a semi-analytical Bayesian solution as well as a myriad of alternative classical methods. If I am using normal likelihood function X_obs = pm.Normal('X_obs', mu=signal, sd=sigma, observed=X) …