A class representing a DGLM
Construct a DGLM with Beta distributed observations, with variance < mean (1 - mean)
A beta distribution parameterised by the mean and variance
A beta distribution parameterised by the mean and variance
the mean of the resulting beta distribution
the variance of the beta distribution
a beta distribution
Forecast a DLM from a particle cloud representing the latent state at the end of the observations
Forecast a DLM from a particle cloud representing the latent state at the end of the observations
the model
the particle cloud representing the latent state
the initial time to start the forecast from
the parameters of the model
the time, mean observation and variance of the observation
Logistic function to transform the number onto a range between 0 and upper
Logistic function to transform the number onto a range between 0 and upper
the upper limit of the logistic function
the number to be transformed
a number between 0 and upper
Calculate the mean and covariance of a sequence of DenseVectors
Calculate the mean and variance of an observation at tim t given a particle cloud representing the latent-state at time t and the model specification
Calculate the mean and variance of an observation at tim t given a particle cloud representing the latent-state at time t and the model specification
a DGLM specification
the particle cloud representing the latent state at time t
the observation noise variance
mean and variance of observation
Construct a DGLM with Poisson distributed observations
Simulate a single step of a DGLM model
Simulate from a dlm model at regular time intervals
Define a DGLM with Student's t observation errors