fix docs, update repo status

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: walker
 Type: Package
 Title: Bayesian Generalized Linear Models with Time-Varying Coefficients
-Version: 1.0.7
+Version: 1.0.9
 Description: Efficient Bayesian generalized linear models with time-varying coefficients 
     as in Helske (2022, <doi:10.1016/j.softx.2022.101016>). Gaussian, Poisson, and binomial 
     observations are supported. The Markov chain Monte Carlo (MCMC) computations are done using 
@@ -23,11 +23,11 @@ Suggests:
     rmarkdown (>= 0.8.1),
     testthat
 Depends:
-    bayesplot,
     R (>= 3.4.0),
     Rcpp (>= 0.12.9),
     rstan (>= 2.26.0)
 Imports:
+    bayesplot,
     coda,
     dplyr,
     Hmisc,
@@ -49,8 +49,9 @@ LinkingTo:
 SystemRequirements: GNU make 
 Biarch: true
 VignetteBuilder: knitr
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1
 ByteCompile: true
 URL: https://github.com/helske/walker
 BugReports: https://github.com/helske/walker/issues
 Encoding: UTF-8
+Roxygen: list(markdown = TRUE)

R/fitted.R

@@ -1,14 +1,14 @@
 #' Extract Fitted Values of Walker Fit
 #'
-#' Returns fitted values (posterior means) from output of \code{walker} or \code{walker_glm}.
+#' Returns fitted values (posterior means) from output of `walker` or `walker_glm`.
 #' 
 #' @export
 #' @importFrom stats fitted sd
 #' @name fitted.walker_fit
-#' @param object Output of \code{walker} or \code{walker_glm}.
-#' @param summary If \code{TRUE} (default), return summary statistics. Otherwise returns samples.
+#' @param object Output of `walker` or `walker_glm`.
+#' @param summary If `TRUE` (default), return summary statistics. Otherwise returns samples.
 #' @param ... Ignored.
-#' @return If \code{summary=TRUE}, matrix containing summary statistics of fitted values. 
+#' @return If `summary=TRUE`, matrix containing summary statistics of fitted values. 
 #' Otherwise a matrix of samples.
 fitted.walker_fit <- function(object, summary = TRUE, ...) {
 
@@ -31,13 +31,13 @@ fitted.walker_fit <- function(object, summary = TRUE, ...) {
 
 #' Extract Coeffients of Walker Fit
 #'
-#' Returns the time-varying regression coefficients from output of \code{walker} or \code{walker_glm}.
+#' Returns the time-varying regression coefficients from output of `walker` or `walker_glm`.
 #' 
 #' @export
 #' @importFrom stats coef
 #' @name coef.walker_fit
-#' @param object Output of \code{walker} or \code{walker_glm}.
-#' @param summary If \code{TRUE} (default), return summary statistics. Otherwise returns samples.
+#' @param object Output of `walker` or `walker_glm`.
+#' @param summary If `TRUE` (default), return summary statistics. Otherwise returns samples.
 #' @param transform Optional vectorized function for transforming the coefficients (for example exp).
 #' @param ... Ignored.
 #' @return Time series containing coefficient values.
@@ -67,4 +67,4 @@ coef.walker_fit <- function(object, summary = TRUE, transform = identity,  ...)
   } else {
     coef_data  
   }
-}
+}

R/lfo.R

@@ -1,23 +1,23 @@
 #' Leave-Future-Out Cross-Validation
 #'
-#' Estimates the leave-future-out (LFO) information criterion for \code{walker} and \code{walker_glm} models.
+#' Estimates the leave-future-out (LFO) information criterion for `walker` and `walker_glm` models.
 #' 
 #' The LFO for non-Gaussian models is (currently) based on the corresponding Gaussian approximation and 
 #' not the importance sampling corrected true posterior. 
 #' 
 #' @export
 #' @importFrom loo psis pareto_k_values weights.importance_sampling
-#' @param object Output of \code{walker} or \code{walker_glm}.
+#' @param object Output of `walker` or `walker_glm`.
 #' @param L Positive integer defining how many observations should be used for the initial fit.
-#' @param exact If \code{TRUE}, computes exact 1-step predictions by re-estimating the model repeatedly. 
-#' If \code{FALSE} (default), uses approximate method based on Bürkner, Gabry and Vehtari (2020).
-#' @param verbose If \code{TRUE} (default), print the progress of the LFO computations to the console.
+#' @param exact If `TRUE`, computes exact 1-step predictions by re-estimating the model repeatedly. 
+#' If `FALSE` (default), uses approximate method based on Bürkner, Gabry and Vehtari (2020).
+#' @param verbose If `TRUE` (default), print the progress of the LFO computations to the console.
 #' @param k_thres Threshold for the pareto k estimate triggering refit. Default is 0.7. 
 #' @references Paul-Christian Bürkner, Jonah Gabry & Aki Vehtari (2020). 
 #' Approximate leave-future-out cross-validation for Bayesian time series models, 
 #' Journal of Statistical Computation and Simulation, 90:14, 2499-2523, DOI: 10.1080/00949655.2020.1783262.
-#' @return List with components \code{ELPD} (Expected log predictive density), \code{ELPDs} (observation-specific ELPDs),
-#' \code{ks} (Pareto k values in case of approximation was used), and \code{refits} (time points where model was re-estimated)
+#' @return List with components `ELPD` (Expected log predictive density), `ELPDs` (observation-specific ELPDs),
+#' `ks` (Pareto k values in case of approximation was used), and `refits` (time points where model was re-estimated)
 #' @examples 
 #' \dontrun{
 #' fit <- walker(Nile ~ -1 + 

R/plot_coefs.R

@@ -1,18 +1,18 @@
 #' Posterior predictive check for walker object
 #' 
 #' Plots sample quantiles from posterior predictive sample. 
-#' See \code{\link{ppc_ribbon}} for details.
+#' See [bayesplot::ppc_ribbon()] for details.
 #' 
 #' @importFrom dplyr group_by summarise
 #' @importFrom rlang .data
 #' @importFrom stats quantile time update.formula drop.terms
 #' @import ggplot2
 #' @import bayesplot
-#' @param object An output from \code{\link{walker}}.
+#' @param object An output from [walker()].
 #' @param level Level for intervals. Default is 0.05, leading to 90\% intervals.
-#' @param alpha Transparency level for \code{geom_ribbon}.
-#' @param transform Optional vectorized function for transforming the coefficients (for example \code{exp}).
-#' @param scales Should y-axis of the panels be \code{"fixed"} (default) or \code{"free"}?
+#' @param alpha Transparency level for [ggplot2::geom_ribbon()].
+#' @param transform Optional vectorized function for transforming the coefficients (for example `exp`).
+#' @param scales Should y-axis of the panels be `"fixed"` (default) or `"free"`?
 #' @param add_zero Logical, should a dashed line indicating a zero be included?
 #' @export
 plot_coefs <- function(object, level = 0.05, alpha = 0.33, transform = identity, scales = "fixed", add_zero = TRUE){
@@ -58,4 +58,4 @@ plot_coefs <- function(object, level = 0.05, alpha = 0.33, transform = identity,
     ) 
   if (add_zero) p <- p + geom_hline(yintercept = 0, linetype = "dashed")
   p
-}
+}

R/plot_fit.R

@@ -1,9 +1,9 @@
 #' Plot the fitted values and sample quantiles for a walker object
 #' 
-#' @param object An output from \code{\link{walker}} or \code{\link{walker_glm}}.
+#' @param object An output from [walker()] or [walker_glm()].
 #' @param level Level for intervals. Default is 0.05, leading to 90\% intervals.
-#' @param alpha Transparency level for \code{geom_ribbon}.
-#' @param ... Further arguments to \code{\link{ppc_ribbon}}.
+#' @param alpha Transparency level for [ggplot2::geom_ribbon()].
+#' @param ... Further arguments to [bayesplot::ppc_ribbon()].
 #' @export
 plot_fit <- function(object, level = 0.05, alpha = 0.33, ...){
 
@@ -18,4 +18,4 @@ plot_fit <- function(object, level = 0.05, alpha = 0.33, ...){
     x = as.numeric(time(object$y))[noNA], ...) + 
     theme(legend.position = "none") + 
     scale_x_continuous(name = "time")
-}
+}

R/plot_predict.R

@@ -1,16 +1,16 @@
 #' Prediction intervals for walker object
 #' 
 #' Plots sample quantiles and posterior means of the predictions 
-#' of the \code{predict.walker_fit} output.
+#' of the `predict.walker_fit` output.
 #' 
 #' @importFrom ggplot2 ggplot facet_wrap geom_ribbon geom_line 
 #' @importFrom bayesplot color_scheme_get theme_default
-#' @param object An output from \code{\link{predict.walker_fit}}.
-#' @param draw_obs Either \code{"response"}, \code{"mean"}, or \code{"none"}, 
-#' where \code{"mean"} is response variable divided by number of trials or exposures 
+#' @param object An output from [predict.walker_fit()].
+#' @param draw_obs Either `"response"`, `"mean"`, or `"none"`, 
+#' where `"mean"` is response variable divided by number of trials or exposures 
 #' in case of binomial/poisson models. 
 #' @param level Level for intervals. Default is 0.05, leading to 90\% intervals.
-#' @param alpha Transparency level for \code{\link{geom_ribbon}}.
+#' @param alpha Transparency level for [ggplot2::geom_ribbon()].
 #' @export
 #' @examples 
 #' set.seed(1)
@@ -104,4 +104,4 @@ plot_predict <- function(object, draw_obs = NULL, level = 0.05, alpha = 0.33){
       aes_(~x, ~y, alpha = 1), inherit.aes = FALSE)
   }
   p
-}
+}

R/pp_check.R

@@ -3,12 +3,12 @@
 #' Plots sample quantiles from posterior predictive sample. 
 #' 
 #' @details 
-#' For other types of posterior predictive checks for example with \code{bayesplot}, 
-#' you can extract the variable \code{yrep} from the output, see examples.#' 
+#' For other types of posterior predictive checks for example with `bayesplot`, 
+#' you can extract the variable `yrep` from the output, see examples.
 #' 
 #' @importFrom bayesplot pp_check
-#' @param object An output from \code{\link{walker}}.
-#' @param ... Further parameters to \code{\link{ppc_ribbon}}.
+#' @param object An output from [walker()].
+#' @param ... Further parameters to [bayesplot::ppc_ribbon()].
 #' @export
 #' @examples 
 #' \dontrun{
@@ -34,4 +34,4 @@ pp_check.walker_fit <- function(object, ...){
     yrep = y_rep,
     x = as.numeric(time(object$y)),
     ...)
-}
+}

R/predict.R

@@ -1,22 +1,22 @@
 #' Predictions for walker object
 #' 
-#' Given the new covariate data and output from \code{walker}, 
+#' Given the new covariate data and output from `walker`, 
 #' obtain samples from posterior predictive distribution for future time points.
 #' 
 #' @importFrom stats deltat tsp
-#' @param object An output from \code{\link{walker}} or \code{\link{walker_glm}}.
-#' @param newdata A \code{data.frame} containing covariates used for prediction.
+#' @param object An output from [walker()] or [walker_glm()].
+#' @param newdata A `data.frame` containing covariates used for prediction.
 #' @param u For Poisson model, a vector of future exposures i.e. E(y) = u*exp(x*beta). 
 #' For binomial, a vector containing the number of trials for future time points. Defaults 1.
-#' @param type If \code{"response"} (default for Gaussian model), predictions are on the response level 
+#' @param type If `"response"` (default for Gaussian model), predictions are on the response level 
 #' (e.g., number of successes for Binomial case, and for Gaussian case the observational 
 #' level noise is added to the mean predictions).
-#' If \code{"mean"} (default for non-Gaussian case), predict means (e.g., success probabilities in Binomial case).
-#' If \code{"link"}, predictions for non-Gaussian models are returned before applying the inverse of the link-function.
+#' If `"mean"` (default for non-Gaussian case), predict means (e.g., success probabilities in Binomial case).
+#' If `"link"`, predictions for non-Gaussian models are returned before applying the inverse of the link-function.
 #' @param ... Ignored.
 #' @return A list containing samples from posterior predictive distribution.
 #' @method predict walker_fit
-#' @seealso \code{\link{plot_predict}} for example.
+#' @seealso [plot_predict()] for example.
 #' @export
 predict.walker_fit <- function(object, newdata, u, 
   type = ifelse(object$distribution == "gaussian", "response", "mean"), ...){
@@ -106,4 +106,4 @@ predict.walker_fit <- function(object, newdata, u,
       length = nrow(pred$y_new)), iter = 1:ncol(pred$y_new))
 
   pred
-}
+}

R/predict_counterfactual.R

@@ -1,22 +1,22 @@
 #' Predictions for walker object
 #' 
-#' Given the new covariate data and output from \code{walker}, 
+#' Given the new covariate data and output from `walker`, 
 #' obtain samples from posterior predictive distribution for counterfactual case,
 #' i.e. for past time points with different covariate values.
 #' 
 #' @importFrom stats deltat tsp rpois plogis rbinom
-#' @param object An output from \code{\link{walker}} or \code{\link{walker_glm}}.
-#' @param newdata A \code{data.frame} containing covariates used for prediction. 
+#' @param object An output from [walker()] or [walker_glm()].
+#' @param newdata A `data.frame` containing covariates used for prediction. 
 #' Should have equal number of rows as the original data
 #' @param u For Poisson model, a vector of exposures i.e. E(y) = u*exp(x*beta). 
 #' For binomial, a vector containing the number of trials. Defaults 1.
-#' @param summary If \code{TRUE} (default), return summary statistics. Otherwise returns samples.
-#' @param type If \code{"response"} (default for Gaussian model), predictions are on the response level 
+#' @param summary If `TRUE` (default), return summary statistics. Otherwise returns samples.
+#' @param type If `"response"` (default for Gaussian model), predictions are on the response level 
 #' (e.g., number of successes for Binomial case, and for Gaussian case the observational 
 #' level noise is added to the mean predictions).
-#' If \code{"mean"} (default for non-Gaussian case), predict means (e.g., success probabilities in Binomial case).
-#' If \code{"link"}, predictions for non-Gaussian models are returned before applying the inverse of the link-function.
-#' @return If \code{summary=TRUE}, time series containing summary statistics of predicted values. 
+#' If `"mean"` (default for non-Gaussian case), predict means (e.g., success probabilities in Binomial case).
+#' If `"link"`, predictions for non-Gaussian models are returned before applying the inverse of the link-function.
+#' @return If `summary=TRUE`, time series containing summary statistics of predicted values. 
 #' Otherwise a matrix of samples from predictive distribution.
 #' @export
 #' @examples 

R/print_fit.R

@@ -3,8 +3,8 @@
 #' Prints the summary information of time-invariant model parameters. In case of non-Gaussian models, 
 #' results based on approximate model are returned with a warning.
 #' 
-#' @param x An output from \code{\link{walker}} or \code{\link{walker_glm}}.
-#' @param ... Additional arguments to \code{\link{print.stanfit}}.
+#' @param x An output from [walker()] or [walker_glm()].
+#' @param ... Additional arguments to [rstan::print.stanfit()].
 #' @method print walker_fit
 #' @export
 print.walker_fit <- function(x, ...) {
@@ -17,11 +17,11 @@ print.walker_fit <- function(x, ...) {
 #' 
 #' Creates a data.frame object from the output of walker fit.
 #' 
-#' @param x An output from \code{\link{walker}} or \code{\link{walker_glm}}.
-#' @param row.names \code{NULL} (default) or a character vector giving the row names 
+#' @param x An output from [walker()] or [walker_glm()].
+#' @param row.names `NULL` (default) or a character vector giving the row names 
 #' for the data frame.
-#' @param optional Ignored (part of generic \code{as.data.frame} signature).
-#' @param type Either \code{tiv} (time-invariant parameters) or \code{tv} (time-varying coefficients).
+#' @param optional Ignored (part of generic `as.data.frame` signature).
+#' @param type Either `tiv` (time-invariant parameters) or `tv` (time-varying coefficients).
 #' @param ... Ignored.
 #' @method as.data.frame walker_fit
 #' @export
@@ -75,8 +75,8 @@ as.data.frame.walker_fit <- function(x, row.names = NULL, optional = FALSE,  typ
 #' 
 #' Return summary information of time-invariant model parameters.
 #' 
-#' @param object An output from \code{\link{walker}} or \code{\link{walker_glm}}.
-#' @param type Either \code{tiv} (time-invariant parameters, the default) or \code{tv} (time-varying coefficients).
+#' @param object An output from [walker()] or [walker_glm()].
+#' @param type Either `tiv` (time-invariant parameters, the default) or `tv` (time-varying coefficients).
 #' @param ... Ignored.
 #' @importFrom Hmisc wtd.mean wtd.var wtd.quantile
 #' @importFrom coda spectrum0.ar

R/rw.R

@@ -1,6 +1,6 @@
 #' Construct a first-order random walk component 
 #' 
-#' Auxiliary function used inside of the formula of \code{walker}.
+#' Auxiliary function used inside of the formula of `walker`.
 #' 
 #' @export
 #' @param formula Formula for RW1 part of the model. Only right-hand-side is used. 
@@ -42,7 +42,7 @@ rw1 <- function(formula, data, beta, sigma = c(2, 0.0001), gamma = NULL) {
 }
 #' Construct a second-order random walk component 
 #' 
-#' Auxiliary function used inside of the formula of \code{walker}.
+#' Auxiliary function used inside of the formula of `walker`.
 #' 
 #' @export
 #' @param formula Formula for RW2 part of the model. Only right-hand-side is used. 
@@ -86,4 +86,4 @@ rw2 <- function(formula, data, beta, sigma = c(2, 0.0001), nu, gamma = NULL) {
   list(xreg = xreg, beta = beta, 
     sigma = sigma, nu = nu, gamma = gamma)
 
-}
+}

R/test_args.R

@@ -11,4 +11,4 @@ check_gamma <- function(x, name) {
     "defining the shape and rate for the Gamma prior the parameter ", name, ". "))
   if(!all(x > 0)) 
     stop(paste0("Both parameters of the Gamma prior for the parameter ", name, " should be positive. "))
-}
+}