This function computes the log-likelihood for a given set of parameters for different models. The models "M0", "M1", "M2" involve gamma and lambda terms, while models "M3" and "M4" involve only lambda. The function calculates the log-likelihood based on the observed data.
Usage
init.log.likelihood(
params = rep(1, 5),
model,
type1,
data1 = sim_dat$diff_Y_t[, 1],
t = t,
u = NULL
)Arguments
- params
A numeric vector containing initial values for the parameters. The vector should be of length 5 for models "M0", "M1", "M2", or length 3 for models "M3" and "M4".
- model
A character string specifying the model type. Must be one of "M0", "M1", "M2", "M3", or "M4".
- type1
A string specifying the type of distribution or model for the lambda calculation.
- data1
A numeric vector containing the observed data for a single product (response variable).
- t
A numeric vector of time or other covariates used in the lambda function.
- u
A numeric vector of additional covariates for the lambda function (can be NULL for some models).