1.4.3

.Rbuildignore

@@ -1,5 +1,3 @@
-^renv$
-^renv\.lock$
 ..Rcheck
 ^.*\.Rproj$
 ^\.Rproj\.user$
@@ -14,9 +12,7 @@ LICENSE
 docs/
 vignettes/figs/
 ^vignettes/.*cache
-^CRAN-RELEASE$
 ^cran-comments\.md$
 ^CRAN-SUBMISSION$
 ^sticker$
-^development_packages\.R$
-^fit_models\.R$
+^doc$

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: fHMM
 Type: Package
 Title: Fitting Hidden Markov Models to Financial Data
-Version: 1.4.2
+Version: 1.4.3
 Authors@R: c(
     person(given = "Lennart",
            family = "Oelschl\U00E4ger",
@@ -11,12 +11,12 @@ Authors@R: c(
     person(given = "Timo", 
            family = "Adam", 
            role = "aut",
-           email = "ta59@st-andrews.ac.uk",
+           email = "timo.adam@uni-bielefeld.de",
            comment = c(ORCID = "0000-0001-9079-3259")),
     person(given = "Rouven", 
            family = "Michels",
            role = "aut",
-           email = "r.michels@uni-bielefeld.de",
+           email = "rouven.michels@tu-dortmund.de",
            comment = c(ORCID = "0000-0002-5433-6197")))
 Description: Fitting (hierarchical) hidden Markov models to financial data
     via maximum likelihood estimation. See Oelschläger, L. and Adam, T.
@@ -43,7 +43,7 @@ Imports:
     httr,
     jsonlite,
     MASS,
-    oeli (>= 0.3.0),
+    oeli (>= 0.7.6),
     padr,
     pracma,
     progress,
@@ -63,7 +63,7 @@ Suggests:
     testthat (>= 3.0.0),
     tseries
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3
 VignetteBuilder: knitr
 Config/testthat/edition: 3
 LazyData: true

NEWS.md

@@ -1,3 +1,11 @@
+# fHMM 1.4.3
+
+* Improved documentation of input types and input checks.
+
+* Small documentation fixes.
+
+* Removed renv.
+
 # fHMM 1.4.2
 
 * Let `download_data()` fail gracefully with an informative message if the Yahoo Finance resource is not available or has changed.
@@ -10,7 +18,7 @@
 
 * Removed stale import of `oeli::check_date()`.
 
-* Updated `download_data()` to confirm with new Yahoo Finance API.
+* Updated `download_data()` to work with the new Yahoo Finance API.
 
 # fHMM 1.4.0
 

R/compare_models.R

@@ -33,12 +33,14 @@ compare_models <- function(...) {
 
   ### check if models are of class "fHMM_model"
   for (i in seq_len(length(models))) {
-    if (!inherits(models[[i]],"fHMM_model")) {
-      stop(
-        paste0("Input '", model_names[i], "' is not of class 'fHMM_model'."),
-        call. = FALSE
-      )
-    }
+    oeli::input_check_response(
+      check = if (inherits(models[[i]], "fHMM_model")) {
+        TRUE
+      } else {
+        paste0("Input '", model_names[i], "' is not of class 'fHMM_model'.")
+      },
+      var_name = model_names[i]
+    )
   }
 
   ### check if data is the same for each model

R/compute_T_star.R

@@ -4,16 +4,16 @@
 #' This helper function computes lengths of fine-scale chunks in the 
 #' hierarchical case.
 #'
-#' @param horizon
+#' @param horizon \[`integer(2)`\]\cr
 #' The element \code{controls$horizon}, i.e., an integer vector of length 2,
 #' where the second entry can be \code{NA_integer_}.
-#' @param period
+#' @param period \[`character(1)`\]\cr
 #' The element \code{controls$period}, i.e. one of \code{"w"},
 #' \code{"m"}, \code{"q"}, or \code{"y"}.
-#' @param dates
+#' @param dates \[`NULL` | `character()`\]\cr
 #' A \code{character} vector of dates of empirical fine-scale data (if any).
 #' By default, \code{dates = NULL}.
-#' @param seed
+#' @param seed \[`NULL` | `integer(1)`\]\cr
 #' Set a seed for the simulation of flexible chunk lengths.
 #' By default, \code{seed = NULL} (i.e., no seed).
 #'

R/compute_ci.R

@@ -4,12 +4,13 @@
 #' This helper function computes confidence intervals for the estimates of an
 #' \code{\link{fHMM_model}} object using the inverse Fisher information.
 #'
-#' @param x
+#' @param x \[`fHMM_model`\]\cr
 #' An object of class \code{\link{fHMM_model}}.
 #'
-#' @param alpha
-#' A \code{numeric} between 0 and 1, the alpha level for the confidence interval.
-#' By default, \code{alpha = 0.05}, which computes a 95% confidence interval.
+#' @param alpha \[`numeric(1)`\]\cr
+#' The alpha level for the confidence interval. Must be between 0 and 1.
+#' By default, \code{alpha = 0.05}, which computes a 95 percent confidence
+#' interval.
 #'
 #' @return
 #' A \code{list} containing the following elements:
@@ -24,12 +25,25 @@
 compute_ci <- function(x, alpha = 0.05) {
 
   ### check inputs
-  if (!inherits(x,"fHMM_model")) {
-    stop("Input 'x' must be an 'fHMM_model' object.", call. = FALSE)
-  }
-  if (!is.numeric(alpha) || length(alpha) != 1 || alpha <= 0 || alpha >= 1) {
-    stop("Input 'alpha' must be a numeric between 0 and 1.", call. = FALSE)
-  }
+  oeli::input_check_response(
+    check = if (inherits(x, "fHMM_model")) {
+      TRUE
+    } else {
+      "Input 'x' must be an 'fHMM_model' object."
+    },
+    var_name = "x"
+  )
+  oeli::input_check_response(
+    check = if (
+      checkmate::test_number(alpha, lower = 0, upper = 1) &&
+        alpha > 0 && alpha < 1
+    ) {
+      TRUE
+    } else {
+      "Input 'alpha' must be a numeric between 0 and 1."
+    },
+    var_name = "alpha"
+  )
 
   ### compute confidence intervals using the inverse Hessian approach
   inverse_fisher <- x$inverse_fisher
@@ -41,7 +55,7 @@ compute_ci <- function(x, alpha = 0.05) {
   ### if negative variance, replace by NA_real_
   bad_inverse_fisher <- which(
     !vapply(
-      inverse_fisher, checkmate::test_number, logical(1), na.ok = FALSE, 
+      inverse_fisher, checkmate::test_number, logical(1), na.ok = FALSE,
       finite = TRUE, lower = 0
     )
   )

R/compute_residuals.R

@@ -4,9 +4,9 @@
 #' This function computes (pseudo-) residuals of an \code{\link{fHMM_model}} 
 #' object.
 #'
-#' @param x
+#' @param x \[`fHMM_model`\]\cr
 #' An object of class \code{\link{fHMM_model}}.
-#' @param verbose
+#' @param verbose \[`logical(1)`\]\cr
 #' Set to \code{TRUE} (default) to print progress messages.
 #'
 #' @return
@@ -20,13 +20,23 @@
 
 compute_residuals <- function(x, verbose = TRUE) {
 
-  ### check input
-  if (!inherits(x,"fHMM_model")) {
-    stop("'x' must be of class 'fHMM_model'.", call. = FALSE)
-  }
-  if (!isTRUE(verbose) && !isFALSE(verbose)) {
-    stop("'verbose' must be either TRUE or FALSE.", call. = FALSE)
-  }
+  ### check inputs
+  oeli::input_check_response(
+    check = if (inherits(x, "fHMM_model")) {
+      TRUE
+    } else {
+      "'x' must be of class 'fHMM_model'."
+    },
+    var_name = "x"
+  )
+  oeli::input_check_response(
+    check = if (checkmate::test_flag(verbose)) {
+      TRUE
+    } else {
+      "'verbose' must be either TRUE or FALSE."
+    },
+    var_name = "verbose"
+  )
   if (is.null(x$decoding)) {
     warning(
       paste(

R/data_and_models.R

@@ -113,7 +113,7 @@
 #' @description
 #' A pre-computed HMM on closing prices of the DAX from 2000 to 2022
 #' with two hidden states and normal state-dependent distributions for
-#' demonstration purpose.
+#' demonstration purposes.
 #'
 #' @usage data("dax_model_2n")
 #'
@@ -150,7 +150,7 @@
 #' @description
 #' A pre-computed HMM on closing prices of the DAX from 2000 to 2022
 #' with three hidden states and state-dependent t-distributions for
-#' demonstration purpose.
+#' demonstration purposes.
 #'
 #' @usage data("dax_model_3t")
 #'
@@ -193,7 +193,7 @@
 #' A pre-computed HHMM with monthly averaged closing prices of the
 #' DAX from 2010 to 2022 on the coarse scale, Volkswagen AG stock data on the 
 #' fine scale, two hidden fine-scale and coarse-scale states, respectively, and
-#' state-dependent t-distributions for demonstration purpose.
+#' state-dependent t-distributions for demonstration purposes.
 #'
 #' @usage data("dax_vw_model")
 #'
@@ -235,7 +235,7 @@
 #' @description
 #' A pre-computed HHMM with monthly unemployment rate in the US on the coarse
 #' scale using 3 states and S&P 500 index data on the fine scale using 2 states
-#' from 1970 to 2020 for demonstration purpose.
+#' from 1970 to 2020 for demonstration purposes.
 #'
 #' @usage data("unemp_spx_model_3_2")
 #'