Maximum Likelihood Estimation of Linear Model with t-distributed errors
This is an example for generic MLE.
Except for defining the negative log-likelihood method, all methods and results are generic. Gradients and Hessian and all resulting statistics are based on numerical differentiation.
Methods
| bsejac() | |
| bsejhj() | |
| covjac() | covariance of parameters based on loglike outer product of jacobian |
| covjhj() | |
| expandparams(params) | expand to full parameter array when some parameters are fixed |
| fit([start_params, method, maxiter, ...]) | Fit the model using maximum likelihood. |
| hessian(params) | Hessian of log-likelihood evaluated at params |
| hessv() | |
| information(params) | Fisher information matrix of model |
| initialize() | |
| jac(params, **kwds) | Jacobian/Gradient of log-likelihood evaluated at params for each observation. |
| jacv() | |
| loglike(params) | |
| loglikeobs(params) | |
| nloglike(params) | |
| nloglikeobs(params) | Loglikelihood of linear model with t distributed errors. |
| predict(params[, exog]) | After a model has been fit predict returns the fitted values. |
| reduceparams(params) | |
| score(params) | Gradient of log-likelihood evaluated at params |
Attributes
| endog_names | |
| exog_names |