compute_expected_cases |
Compute expected cases |
compute_log_incidence |
Compute log likelihood of incidence model |
covid_delay_dist |
Delay distribution from COVID-19 pandemic. |
covid_new_york_city |
New York City data from the COVID-19 pandemic. |
data_check |
Input data check |
data_processing |
Data processing wrapper |
diff_trans |
Transpose of the 1st difference operator |
fit_incidence |
Fit incidence curve to reported data |
front_zero_pad |
Pad reported data with zeros in front |
incidence_to_df |
Export incidence model to data frame |
init_params |
Initialize spline parameters (beta) |
make_ar_extrap_samps |
Make AR samples for extrapolation past end point |
make_likelihood_matrix |
Make delay likelihood matrix |
make_spline_basis |
Create spline basis matrix |
marg_loglike_poisson |
Marginal log likelihood This function computes the marginal probability of Pr(reported | beta). Note that lnPmat must be zero padded enough (or censored) to match the length of reported cases vector. |
marg_loglike_poisson_fisher |
Marginal log likelihood Fisher information matrix |
marg_loglike_poisson_grad |
Marginal log likelihood gradient |
plot.incidence_spline_model |
Plot model from fit_incidence |
poisson_objective |
Poisson objective function |
poisson_objective_grad |
Poisson objective function gradient |
poisson_objective_post_cov_approx |
Compute Fisher information matrix for Poisson objective |
regfun |
Beta regularization function |
regfun_grad |
Beta regularization function gradient |
regfun_hess |
Beta regularization function Hessian |
sample_laplace_log_incidence_poisson |
Generate Laplace samples of incidence |
scan_spline_dof |
Scan spline degrees of freedom |
scan_spline_lam |
Scan spline regularization parameter |
spanish_flu |
Daily flu mortality from 1918 flu pandemic. |
spanish_flu_delay_dist |
Delay distribution from 1918 flu pandemic. |
train_and_validate |
Train and validate model on reported data |
train_val_split |
Split reported case data |