Re-style code and enforce 80 character line limit

diff --git a/R/ID.R b/R/ID.R
index 0e3cc35bafb58e0e959f51b7acdb527f125295b4..7e8a04d46796b4cacb74675b8525b3590ac11eec 100644 (file)
--- a/R/ID.R
+++ b/R/ID.R
@@ -1,48 +1,46 @@
 #' ID method
 #'
 #' ID method
 #'

-#' This function implements a least squares estimation method of R0 due to Fisman et al. (PloS One, 2013).
-#' See details for implementation notes.
+#' This function implements a least squares estimation method of R0 due to
+#' Fisman et al. (PloS One, 2013). See details for implementation notes.

 #'
 #'

-#' The method is based on a straightforward incidence decay model. The estimate of R0 is the value which
-#' minimizes the sum of squares between observed case counts and cases counts 'expected' under the model.
+#' The method is based on a straightforward incidence decay model. The estimate
+#' of R0 is the value which minimizes the sum of squares between observed case
+#' counts and cases counts 'expected' under the model.

 #'
 #'

-#' This method is based on an approximation of the SIR model, which is most valid at the beginning of an epidemic.
-#' The method assumes that the mean of the serial distribution (sometimes called the serial interval) is known.
-#' The final estimate can be quite sensitive to this value, so sensitivity testing is strongly recommended.
-#' Users should be careful about units of time (e.g., are counts observed daily or weekly?) when implementing.
+#' This method is based on an approximation of the SIR model, which is most
+#' valid at the beginning of an epidemic. The method assumes that the mean of
+#' the serial distribution (sometimes called the serial interval) is known. The
+#' final estimate can be quite sensitive to this value, so sensitivity testing
+#' is strongly recommended. Users should be careful about units of time (e.g.,
+#' are counts observed daily or weekly?) when implementing.

 #'
 #' @param NT Vector of case counts.
 #'
 #' @param NT Vector of case counts.

-#' @param mu Mean of the serial distribution. This needs to match case counts in time units. For example, if case counts
-#'           are weekly and the serial distribution has a mean of seven days, then \code{mu} should be set to one If case
-#'           counts are daily and the serial distribution has a mean of seven days, then \code{mu} should be set to seven.
+#' @param mu Mean of the serial distribution. This needs to match case counts
+#'           in time units. For example, if case counts are weekly and the
+#'           serial distribution has a mean of seven days, then \code{mu} should
+#'           be set to one. If case counts are daily and the serial distribution
+#'           has a mean of seven days, then \code{mu} should be set to seven.

 #'
 #' @return \code{ID} returns a single value, the estimate of R0.
 #'
 #' @examples
 #'
 #' @return \code{ID} returns a single value, the estimate of R0.
 #'
 #' @examples

-#' ## ===================================================== ##
-#' ## Illustrate on weekly data                             ##
-#' ## ===================================================== ##
-#'
+#' # Weekly data:

 #' NT <- c(1, 4, 10, 5, 3, 4, 19, 3, 3, 14, 4)
 #' NT <- c(1, 4, 10, 5, 3, 4, 19, 3, 3, 14, 4)

-#' ## obtain Rhat when serial distribution has mean of five days
-#' ID(NT=NT, mu=5/7)
-#' ## obtain Rhat when serial distribution has mean of three days
-#' ID(NT=NT, mu=3/7)

 #'
 #'

-#' ## ========================================================= ##
-#' ## Compute Rhat using only the first five weeks of data      ##
-#' ## ========================================================= ##
+#' # Obtain R0 when the serial distribution has a mean of five days.
+#' ID(NT, mu = 5 / 7)

 #'
 #'

-#' ID(NT=NT[1:5], mu=5/7) # serial distribution has mean of five days
+#' # Obtain R0 when the serial distribution has a mean of three days.
+#' ID(NT, mu = 3 / 7)

 #'
 #' @export
 ID <- function(NT, mu) {
 #'
 #' @export
 ID <- function(NT, mu) {

-    NT <- as.numeric(NT)
-    TT <- length(NT)
-    s <- (1:TT) / mu
-    y <- log(NT) / s
+  NT <- as.numeric(NT)
+  TT <- length(NT)
+  s <- (1:TT) / mu
+  y <- log(NT) / s

 
 

-    R0_ID <- exp(sum(y) / TT)
+  R0_ID <- exp(sum(y) / TT)

 
 

-    return(R0_ID)
+  return(R0_ID)

 }
 }

diff --git a/R/IDEA.R b/R/IDEA.R
index 854acd7af108903da248048d34ee6ae20de3a81d..53fa653d11672af3d212a4b06dbbcd980437f141 100644 (file)
--- a/R/IDEA.R
+++ b/R/IDEA.R
@@ -1,58 +1,56 @@
 #' IDEA method
 #'
 #' IDEA method
 #'

-#' This function implements a least squares estimation method of R0 due to Fisman et al. (PloS One, 2013).
-#' See details for implementation notes.
+#' This function implements a least squares estimation method of R0 due to
+#' Fisman et al. (PloS One, 2013). See details for implementation notes.

 #'
 #'

-#' This method is closely related to that implemented in \code{ID}. The method is based on an incidence decay model.
-#' The estimate of R0 is the value which minimizes the sum of squares between observed case counts and cases counts
+#' This method is closely related to that implemented in \code{ID}. The method
+#' is based on an incidence decay model. The estimate of R0 is the value which
+#' minimizes the sum of squares between observed case counts and cases counts

 #' expected under the model.
 #'
 #' expected under the model.
 #'

-#' This method is based on an approximation of the SIR model, which is most valid at the beginning of an epidemic.
-#' The method assumes that the mean of the serial distribution (sometimes called the serial interval) is known.
-#' The final estimate can be quite sensitive to this value, so sensitivity testing is strongly recommended.
-#' Users should be careful about units of time (e.g., are counts observed daily or weekly?) when implementing.
+#' This method is based on an approximation of the SIR model, which is most
+#' valid at the beginning of an epidemic. The method assumes that the mean of
+#' the serial distribution (sometimes called the serial interval) is known. The
+#' final estimate can be quite sensitive to this value, so sensitivity testing
+#' is strongly recommended. Users should be careful about units of time (e.g.,
+#' are counts observed daily or weekly?) when implementing.

 #'
 #' @param NT Vector of case counts.
 #'
 #' @param NT Vector of case counts.

-#' @param mu Mean of the serial distribution. This needs to match case counts in time units. For example, if case counts
-#'           are weekly and the serial distribution has a mean of seven days, then \code{mu} should be set to one. If case
-#'           counts are daily and the serial distribution has a mean of seven days, then \code{mu} should be set to seven.
+#' @param mu Mean of the serial distribution. This needs to match case counts in
+#'           time units. For example, if case counts are weekly and the serial
+#'           distribution has a mean of seven days, then \code{mu} should be set
+#'           to one. If case counts are daily and the serial distribution has a
+#'           mean of seven days, then \code{mu} should be set to seven.

 #'
 #' @return \code{IDEA} returns a single value, the estimate of R0.
 #'
 #' @examples
 #'
 #' @return \code{IDEA} returns a single value, the estimate of R0.
 #'
 #' @examples

-#' ## ===================================================== ##
-#' ## Illustrate on weekly data                             ##
-#' ## ===================================================== ##
-#'
+#' # Weekly data.

 #' NT <- c(1, 4, 10, 5, 3, 4, 19, 3, 3, 14, 4)
 #' NT <- c(1, 4, 10, 5, 3, 4, 19, 3, 3, 14, 4)

-#' ## obtain Rhat when serial distribution has mean of five days
-#' IDEA(NT=NT, mu=5/7)
-#' ## obtain Rhat when serial distribution has mean of three days
-#' IDEA(NT=NT, mu=3/7)

 #'
 #'

-#' ## ========================================================= ##
-#' ## Compute Rhat using only the first five weeks of data      ##
-#' ## ========================================================= ##
+#' # Obtain R0 when the serial distribution has a mean of five days.
+#' IDEA(NT, mu = 5 / 7)

 #'
 #'

-#' IDEA(NT=NT[1:5], mu=5/7) # serial distribution has mean of five days
+#' # Obtain R0 when the serial distribution has a mean of three days.
+#' IDEA(NT, mu = 3 / 7)

 #'
 #' @export
 IDEA <- function(NT, mu) {
 #'
 #' @export
 IDEA <- function(NT, mu) {

-    if (length(NT) < 2)
-        print("Warning: length of NT should be at least two.")
-    else {
-        NT <- as.numeric(NT)
-        TT <- length(NT)
-        s <- (1:TT) / mu
+  if (length(NT) < 2)
+    print("Warning: length of NT should be at least two.")
+  else {
+    NT <- as.numeric(NT)
+    TT <- length(NT)
+    s <- (1:TT) / mu

 
 

-        y1 <- log(NT) / s
-        y2 <- s^2
-        y3 <- log(NT)
+    y1 <- log(NT) / s
+    y2 <- s^2
+    y3 <- log(NT)

 
 

-        IDEA1 <- sum(y2) * sum(y1) - sum(s) * sum(y3)
-        IDEA2 <- TT * sum(y2) - sum(s)^2
-        IDEA <- exp(IDEA1 / IDEA2)
+    IDEA1 <- sum(y2) * sum(y1) - sum(s) * sum(y3)
+    IDEA2 <- TT * sum(y2) - sum(s)^2
+    IDEA <- exp(IDEA1 / IDEA2)

 
 

-        return(IDEA)
-    }
+    return(IDEA)
+  }

 }
 }

diff --git a/R/WP.R b/R/WP.R
index c8178b7b168c462175bb5e4a320d78a98858c569..a6e53546d8d9b8ecbac1480822e404079cd6d130 100644 (file)
--- a/R/WP.R
+++ b/R/WP.R
@@ -1,98 +1,112 @@
 #' WP method
 #'
 #' WP method
 #'

-#' This function implements an R0 estimation due to White and Pagano (Statistics in Medicine, 2008).
-#' The method is based on maximum likelihood estimation in a Poisson transmission model.
-#' See details for important implementation notes.
+#' This function implements an R0 estimation due to White and Pagano (Statistics
+#' in Medicine, 2008). The method is based on maximum likelihood estimation in a
+#' Poisson transmission model. See details for important implementation notes.

 #'
 #'

-#' This method is based on a Poisson transmission model, and hence may be most most valid at the beginning
-#' of an epidemic. In their model, the serial distribution is assumed to be discrete with a finite number
-#' of posible values. In this implementation, if \code{mu} is not {NA}, the serial distribution is taken to
-#' be a discretized version of a gamma distribution with mean \code{mu}, shape parameter one, and largest
-#' possible value based on parameter \code{tol}. When \code{mu} is \code{NA}, the function implements a
-#' grid search algorithm to find the maximum likelihood estimator over all possible gamma distributions
-#' with unknown mean and variance, restricting these to a prespecified grid (see \code{search} parameter).  
+#' This method is based on a Poisson transmission model, and hence may be most
+#' most valid at the beginning of an epidemic. In their model, the serial
+#' distribution is assumed to be discrete with a finite number of posible
+#' values. In this implementation, if \code{mu} is not {NA}, the serial
+#' distribution is taken to be a discretized version of a gamma distribution
+#' with mean \code{mu}, shape parameter one, and largest possible value based on
+#' parameter \code{tol}. When \code{mu} is \code{NA}, the function implements a
+#' grid search algorithm to find the maximum likelihood estimator over all
+#' possible gamma distributions with unknown mean and variance, restricting
+#' these to a prespecified grid (see \code{search} parameter).

 #'
 #'

-#' When the serial distribution is known (i.e., \code{mu} is not \code{NA}), sensitivity testing of \code{mu}
-#' is strongly recommended. If the serial distribution is unknown (i.e., \code{mu} is \code{NA}), the
-#' likelihood function can be flat near the maximum, resulting in numerical instability of the optimizer.
-#' When \code{mu} is \code{NA}, the implementation takes considerably longer to run. Users should be careful
-#' about units of time (e.g., are counts observed daily or weekly?) when implementing.  
+#' When the serial distribution is known (i.e., \code{mu} is not \code{NA}),
+#' sensitivity testing of \code{mu} is strongly recommended. If the serial
+#' distribution is unknown (i.e., \code{mu} is \code{NA}), the likelihood
+#' function can be flat near the maximum, resulting in numerical instability of
+#' the optimizer. When \code{mu} is \code{NA}, the implementation takes
+#' considerably longer to run. Users should be careful about units of time
+#' (e.g., are counts observed daily or weekly?) when implementing.

 #'
 #'

-#' The model developed in White and Pagano (2008) is discrete, and hence the serial distribution is finite 
-#' discrete. In our implementation, the input value \code{mu} is that of a continuous distribution. The
-#' algorithm discretizes this input when \code{mu} is not \code{NA}, and hence the mean of the serial
-#' distribution returned in the list \code{SD} will differ from \code{mu} somewhat. That is to say, if the
-#' user notices that the input \code{mu} and output mean of \code{SD} are different, this is to be expected,
+#' The model developed in White and Pagano (2008) is discrete, and hence the
+#' serial distribution is finite discrete. In our implementation, the input
+#' value \code{mu} is that of a continuous distribution. The algorithm
+#' discretizes this input when \code{mu} is not \code{NA}, and hence the mean of
+#' the serial distribution returned in the list \code{SD} will differ from
+#' \code{mu} somewhat. That is to say, if the user notices that the input
+#' \code{mu} and output mean of \code{SD} are different, this is to be expected,

 #' and is caused by the discretization.
 #'
 #' @param NT Vector of case counts.
 #' and is caused by the discretization.
 #'
 #' @param NT Vector of case counts.

-#' @param mu Mean of the serial distribution (needs to match case counts in time units; for example, if case
-#'           counts are weekly and the serial distribution has a mean of seven days, then \code{mu} should be
-#'           set to one). The default value of \code{mu} is set to \code{NA}.
-#' @param search List of default values for the grid search algorithm. The list includes three elements: the
-#'               first is \code{B}, which is the length of the grid in one dimension; the second is
-#'               \code{scale.max}, which is the largest possible value of the scale parameter; and the third
-#'               is \code{shape.max}, which is the largest possible value of the shape parameter. Defaults to
-#'               \code{B=100, scale.max=10, shape.max=10}. For both shape and scale, the smallest possible
-#'               value is 1/\code{B}.
-#' @param tol Cutoff value for cumulative distribution function of the pre-discretization gamma serial
-#'            distribution. Defaults to 0.999 (i.e. in the discretization, the maximum is chosen such that the
-#'            original gamma distribution has cumulative probability of no more than 0.999 at this maximum).
+#' @param mu Mean of the serial distribution (needs to match case counts in time
+#'           units; for example, if case counts are weekly and the serial
+#'           distribution has a mean of seven days, then \code{mu} should be set
+#'           to one). The default value of \code{mu} is set to \code{NA}.
+#' @param search List of default values for the grid search algorithm. The list
+#'               includes three elements: the first is \code{B}, which is the
+#'               length of the grid in one dimension; the second is
+#'               \code{scale.max}, which is the largest possible value of the
+#'               scale parameter; and the third is \code{shape.max}, which is
+#'               the largest possible value of the shape parameter. Defaults to
+#'               \code{B=100, scale.max=10, shape.max=10}. For both shape and
+#'               scale, the smallest possible value is 1/\code{B}.
+#' @param tol Cutoff value for cumulative distribution function of the
+#'            pre-discretization gamma serial distribution. Defaults to 0.999
+#'            (i.e. in the discretization, the maximum is chosen such that the
+#'            original gamma distribution has cumulative probability of no more
+#'            than 0.999 at this maximum).

 #'
 #'

-#' @return \code{WP} returns a list containing the following components:  \code{Rhat} is the estimate of R0,
-#'         and \code{SD} is either the discretized serial distribution (if \code{mu} is not \code{NA}), or the
-#'         estimated discretized serial distribution (if \code{mu} is \code{NA}). The list also returns the
-#'         variable \code{check}, which is equal to the number of non-unique maximum likelihood estimators.
-#'         The serial distribution \code{SD} is returned as a list made up of \code{supp} (the support of
-#'         the distribution) and \code{pmf} (the probability mass function).
+#' @return \code{WP} returns a list containing the following components:
+#'         \code{Rhat} is the estimate of R0, and \code{SD} is either the
+#'         discretized serial distribution (if \code{mu} is not \code{NA}), or
+#'         the estimated discretized serial distribution (if \code{mu} is
+#'         \code{NA}). The list also returns the variable \code{check}, which is
+#'         equal to the number of non-unique maximum likelihood estimators. The
+#'         serial distribution \code{SD} is returned as a list made up of
+#'         \code{supp} (the support of the distribution) and \code{pmf} (the
+#'         probability mass function).

 #'
 #' @examples
 #'
 #' @examples

-#' ## ===================================================== ##
-#' ## Illustrate on weekly data                             ##
-#' ## ===================================================== ##
-#'
+#' # Weekly data.

 #' NT <- c(1, 4, 10, 5, 3, 4, 19, 3, 3, 14, 4)
 #' NT <- c(1, 4, 10, 5, 3, 4, 19, 3, 3, 14, 4)

-#' ## obtain Rhat when serial distribution has mean of five days
-#' res1 <- WP(NT=NT, mu=5/7)
+#'
+#' # Obtain R0 when the serial distribution has a mean of five days.
+#' res1 <- WP(NT, mu = 5 / 7)

 #' res1$Rhat
 #' res1$Rhat

-#' ## obtain Rhat when serial distribution has mean of three days
-#' res2        <- WP(NT=NT, mu=3/7)
+#'
+#' # Obtain R0 when the serial distribution has a mean of three days.
+#' res2 <- WP(NT, mu = 3 / 7)

 #' res2$Rhat
 #' res2$Rhat

-#' ## obtain Rhat when serial distribution is unknown
-#' ## NOTE:  this implementation will take longer to run
-#' res3        <- WP(NT=NT)
+#'
+#' # Obtain R0 when the serial distribution is unknown.
+#' # NOTE: This implementation will take longer to run.
+#' res3 <- WP(NT)

 #' res3$Rhat
 #' res3$Rhat

-#' ## find mean of estimated serial distribution
+#'
+#' # Find the mean of the estimated serial distribution.

 #' serial <- res3$SD
 #' sum(serial$supp * serial$pmf)
 #'
 #' serial <- res3$SD
 #' sum(serial$supp * serial$pmf)
 #'

-#' ## ========================================================= ##
-#' ## Compute Rhat using only the first five weeks of data      ##
-#' ## ========================================================= ##
-#' 
-#' res4 <- WP(NT=NT[1:5], mu=5/7) # serial distribution has mean of five days
-#' res4$Rhat
-#'

 #' @importFrom stats pexp qexp
 #'
 #' @export
 #' @importFrom stats pexp qexp
 #'
 #' @export

-WP <- function(NT, mu=NA, search=list(B=100, shape.max=10, scale.max=10), tol=0.999) {
-    if (is.na(mu)) {
-        print("You have assumed that the serial distribution is unknown.")
-        res <- WP_unknown(NT=NT, B=search$B, shape.max=search$shape.max, scale.max=search$scale.max, tol=tol)
-        Rhat <- res$Rhat
-        p <- res$p
-        range.max <- res$range.max
-        JJ <- res$JJ
-    } else {
-        print("You have assumed that the serial distribution is known.")
-        range.max <- ceiling(qexp(tol, rate=1/mu))
-        p <- diff(pexp(0:range.max, 1/mu))
-        p <- p / sum(p)
-        res <- WP_known(NT=NT, p=p)
-        Rhat <- res
-        JJ <- NA
-    }
+WP <- function(NT, mu = NA,
+               search = list(B = 100, shape.max = 10, scale.max = 10),
+               tol = 0.999) {
+  if (is.na(mu)) {
+    print("You have assumed that the serial distribution is unknown.")
+    res <- WP_unknown(NT, B = search$B, shape.max = search$shape.max,
+                      scale.max = search$scale.max, tol = tol)
+    Rhat <- res$Rhat
+    p <- res$p
+    range.max <- res$range.max
+    JJ <- res$JJ
+  } else {
+    print("You have assumed that the serial distribution is known.")
+    range.max <- ceiling(qexp(tol, rate = 1 / mu))
+    p <- diff(pexp(0:range.max, 1 / mu))
+    p <- p / sum(p)
+    res <- WP_known(NT = NT, p = p)
+    Rhat <- res
+    JJ <- NA
+  }

 
 

-    return(list(Rhat=Rhat, check=length(JJ), SD=list(supp=1:range.max, pmf=p)))
+  return(list(Rhat = Rhat,
+              check = length(JJ),
+              SD = list(supp = 1:range.max, pmf = p)))

 }
 }

diff --git a/R/WP_internal.R b/R/WP_internal.R
index 54744b9a3012bce2682f6705be073b8a2cf6fef1..420d0c05b2a5479448ef235561c469131ec07354 100644 (file)
--- a/R/WP_internal.R
+++ b/R/WP_internal.R
@@ -1,7 +1,8 @@
 #' WP method background function WP_known
 #'
 #' WP method background function WP_known
 #'

-#' This is a background/internal function called by \code{WP}. It computes the maximum
-#' likelihood estimator of R0 assuming that the serial distribution is known and finite discrete.
+#' This is a background/internal function called by \code{WP}. It computes the
+#' maximum likelihood estimator of R0 assuming that the serial distribution is
+#' known and finite discrete.

 #'
 #' @param NT Vector of case counts.
 #' @param p Discretized version of the serial distribution.
 #'
 #' @param NT Vector of case counts.
 #' @param p Discretized version of the serial distribution.


@@ -10,97 +11,106 @@
 #'
 #' @keywords internal
 WP_known <- function(NT, p) {
 #'
 #' @keywords internal
 WP_known <- function(NT, p) {

-    k <- length(p)
-    TT <- length(NT) - 1
-       mu_t <- rep(0, TT)
+  k <- length(p)
+  TT <- length(NT) - 1
+  mu_t <- rep(0, TT)

 
 

-    for (i in 1:TT) {
-        Nt <- NT[i:max(1, i-k+1)]
-        mu_t[i]        <- sum(p[1:min(k, i)] * Nt)
-    }
+  for (i in 1:TT) {
+    Nt <- NT[i:max(1, i - k + 1)]
+    mu_t[i] <- sum(p[1:min(k, i)] * Nt)
+  }

 
 

-    Rhat <- sum(NT[-1]) / sum(mu_t)
-       return(Rhat)
+  Rhat <- sum(NT[-1]) / sum(mu_t)
+  return(Rhat)

 }
 
 #' WP method background function WP_unknown
 #'
 }
 
 #' WP method background function WP_unknown
 #'

-#' This is a background/internal function called by \code{WP}. It computes the maximum likelihood estimator
-#' of R0 assuming that the serial distribution is unknown but comes from a discretized gamma distribution.
-#' The function then implements a simple grid search algorithm to obtain the maximum likelihood estimator
-#' of R0 as well as the gamma parameters.
+#' This is a background/internal function called by \code{WP}. It computes the
+#' maximum likelihood estimator of R0 assuming that the serial distribution is
+#' unknown but comes from a discretized gamma distribution. The function then
+#' implements a simple grid search algorithm to obtain the maximum likelihood
+#' estimator of R0 as well as the gamma parameters.

 #'
 #' @param NT Vector of case counts.
 #' @param B Length of grid for shape and scale (grid search parameter).
 #' @param shape.max Maximum shape value (grid \code{search} parameter).
 #' @param scale.max Maximum scale value (grid \code{search} parameter).
 #'
 #' @param NT Vector of case counts.
 #' @param B Length of grid for shape and scale (grid search parameter).
 #' @param shape.max Maximum shape value (grid \code{search} parameter).
 #' @param scale.max Maximum scale value (grid \code{search} parameter).

-#' @param tol cutoff value for cumulative distribution function of the serial distribution (defaults to 0.999).
+#' @param tol cutoff value for cumulative distribution function of the serial
+#'            distribution (defaults to 0.999).

 #'
 #'

-#' @return The function returns \code{Rhat}, the maximum likelihood estimator of R0, as well as the maximum
-#'         likelihood estimator of the discretized serial distribution given by \code{p} (the probability mass
-#'         function) and \code{range.max} (the distribution has support on the integers one to \code{range.max}).
-#'         The function also returns \code{resLL} (all values of the log-likelihood) at \code{shape} (grid for
-#'         shape parameter) and at \code{scale} (grid for scale parameter), as well as \code{resR0} (the full
-#'         vector of maximum likelihood estimators), \code{JJ} (the locations for the likelihood for these), and
-#'         \code{J0} (the location for the maximum likelihood estimator \code{Rhat}). If \code{JJ} and \code{J0}
-#'         are not the same, this means that the maximum likelihood estimator is not unique.
+#' @return The function returns \code{Rhat}, the maximum likelihood estimator of
+#'         R0, as well as the maximum likelihood estimator of the discretized
+#'         serial distribution given by \code{p} (the probability mass function)
+#'         and \code{range.max} (the distribution has support on the integers
+#'         one to \code{range.max}). The function also returns \code{resLL} (all
+#'         values of the log-likelihood) at \code{shape} (grid for shape
+#'         parameter) and at \code{scale} (grid for scale parameter), as well as
+#'         \code{resR0} (the full vector of maximum likelihood estimators),
+#'         \code{JJ} (the locations for the likelihood for these), and \code{J0}
+#'         (the location for the maximum likelihood estimator \code{Rhat}). If
+#'         \code{JJ} and \code{J0} are not the same, this means that the maximum
+#'         likelihood estimator is not unique.

 #'
 #' @importFrom stats pgamma qgamma
 #'
 #' @keywords internal
 #'
 #' @importFrom stats pgamma qgamma
 #'
 #' @keywords internal

-WP_unknown <- function(NT, B=100, shape.max=10, scale.max=10, tol=0.999) {
-       shape <- seq(0, shape.max, length.out=B+1)
-       scale <- seq(0, scale.max, length.out=B+1)
-       shape <- shape[-1]
-       scale <- scale[-1]
+WP_unknown <- function(NT, B = 100, shape.max = 10, scale.max = 10,
+                       tol = 0.999) {
+  shape <- seq(0, shape.max, length.out = B + 1)
+  scale <- seq(0, scale.max, length.out = B + 1)
+  shape <- shape[-1]
+  scale <- scale[-1]

 
 

-       resLL <- matrix(0,B,B)
-       resR0 <- matrix(0,B,B)
+  resLL <- matrix(0, B, B)
+  resR0 <- matrix(0, B, B)

 
 

-    for (i in 1:B) {
-        for (j in 1:B) {
-            range.max <- ceiling(qgamma(tol, shape=shape[i], scale=scale[j]))
-            p <- diff(pgamma(0:range.max, shape=shape[i], scale=scale[j]))
-            p <- p / sum(p)
-            mle <- WP_known(NT, p)
-            resLL[i,j] <- computeLL(p, NT, mle)
-            resR0[i,j] <- mle
-        }
+  for (i in 1:B)
+    for (j in 1:B) {
+      range.max <- ceiling(qgamma(tol, shape = shape[i], scale = scale[j]))
+      p <- diff(pgamma(0:range.max, shape = shape[i], scale = scale[j]))
+      p <- p / sum(p)
+      mle <- WP_known(NT, p)
+      resLL[i, j] <- computeLL(p, NT, mle)
+      resR0[i, j] <- mle

     }
     }

-       
-    J0 <- which.max(resLL)
-    R0hat <- resR0[J0]
-    JJ <- which(resLL == resLL[J0], arr.ind=TRUE)
-    range.max <- ceiling(qgamma(tol, shape=shape[JJ[1]], scale=scale[JJ[2]]))
-    p <- diff(pgamma(0:range.max, shape=shape[JJ[1]], scale=scale[JJ[2]]))
-    p <- p / sum(p)
-       
-    return(list(Rhat=R0hat, J0=J0, ll=resLL, Rs=resR0, scale=scale, shape=shape, JJ=JJ, p=p, range.max=range.max))
+
+  J0 <- which.max(resLL)
+  R0hat <- resR0[J0]
+  JJ <- which(resLL == resLL[J0], arr.ind = TRUE)
+  range.max <- ceiling(qgamma(tol, shape = shape[JJ[1]], scale = scale[JJ[2]]))
+  p <- diff(pgamma(0:range.max, shape = shape[JJ[1]], scale = scale[JJ[2]]))
+  p <- p / sum(p)
+
+  return(list(Rhat = R0hat, J0 = J0, ll = resLL, Rs = resR0, scale = scale,
+              shape = shape, JJ = JJ, p = p, range.max = range.max))

 }
 
 #' WP method background function computeLL
 #'
 }
 
 #' WP method background function computeLL
 #'

-#' This is a background/internal function called by \code{WP}.  It computes the log-likelihood.
+#' This is a background/internal function called by \code{WP}. It computes the
+#' log-likelihood.

 #'
 #' @param NT Vector of case counts.
 #' @param p Discretized version of the serial distribution.
 #' @param R0 Basic reproductive ratio.
 #'
 #'
 #' @param NT Vector of case counts.
 #' @param p Discretized version of the serial distribution.
 #' @param R0 Basic reproductive ratio.
 #'

-#' @return This function returns the log-likelihood at the input variables and parameters.
+#' @return This function returns the log-likelihood at the input variables and
+#'         parameters.

 #'
 #' @keywords internal
 computeLL <- function(p, NT, R0) {
 #'
 #' @keywords internal
 computeLL <- function(p, NT, R0) {

-    k <- length(p)
-    TT <- length(NT) - 1
-    mu_t <- rep(0, TT)
+  k <- length(p)
+  TT <- length(NT) - 1
+  mu_t <- rep(0, TT)

 
 

-    for (i in 1:TT) {
-        Nt <- NT[i:max(1, i-k+1)]
-        mu_t[i]        <- sum(p[1:min(k, i)] * Nt)
-    }
+  for (i in 1:TT) {
+    Nt <- NT[i:max(1, i - k + 1)]
+    mu_t[i] <- sum(p[1:min(k, i)] * Nt)
+  }

 
 

-    mu_t <- R0 * mu_t
-    LL <- sum(NT[-1] * log(mu_t)) - sum(mu_t)
+  mu_t <- R0 * mu_t
+  LL <- sum(NT[-1] * log(mu_t)) - sum(mu_t)

 
 

-       return(LL)
+  return(LL)

 }
 }

diff --git a/R/seqB.R b/R/seqB.R
index 8685f390bc738f87b1133d14da9988193e97a36f..e51117f852f976216241c368112f04d2dac4ed5d 100644 (file)
--- a/R/seqB.R
+++ b/R/seqB.R
@@ -1,126 +1,129 @@
 #' seqB method
 #'
 #' seqB method
 #'

-#' This function implements a sequential Bayesian estimation method of R0 due to Bettencourt and Riberio (PloS One, 2008).
-#' See details for important implementation notes.
+#' This function implements a sequential Bayesian estimation method of R0 due to
+#' Bettencourt and Riberio (PloS One, 2008). See details for important
+#' implementation notes.

 #'
 #'

-#' The method sets a uniform prior distribution on R0 with possible values between zero and \code{kappa}, discretized to a fine grid.
-#' The distribution of R0 is then updated sequentially, with one update for each new case count observation.
-#' The final estimate of R0 is \code{Rhat}, the mean of the (last) posterior distribution.
-#' The prior distribution is the initial belief of the distribution of R0; which in this implementation is the uninformative uniform
-#' distribution with values between zero and \code{kappa}. Users can change the value of /code{kappa} only (i.e., the prior distribution
-#' cannot be changed from the uniform).  As more case counts are observed, the influence of the prior distribution should lessen on
-#' the final estimate \code{Rhat}.
+#' The method sets a uniform prior distribution on R0 with possible values
+#' between zero and \code{kappa}, discretized to a fine grid. The distribution
+#' of R0 is then updated sequentially, with one update for each new case count
+#' observation. The final estimate of R0 is \code{Rhat}, the mean of the (last)
+#' posterior distribution. The prior distribution is the initial belief of the
+#' distribution of R0, which is the uninformative uniform distribution with
+#' values between zero and \code{kappa}. Users can change the value of
+#' /code{kappa} only (i.e., the prior distribution cannot be changed from the
+#' uniform). As more case counts are observed, the influence of the prior
+#' distribution should lessen on the final estimate \code{Rhat}.

 #'
 #'

-#' This method is based on an approximation of the SIR model, which is most valid at the beginning of an epidemic. The method assumes
-#' that the mean of the serial distribution (sometimes called the serial interval) is known. The final estimate can be quite sensitive
-#' to this value, so sensitivity testing is strongly recommended. Users should be careful about units of time (e.g., are counts observed
-#' daily or weekly?) when implementing.  
+#' This method is based on an approximation of the SIR model, which is most
+#' valid at the beginning of an epidemic. The method assumes that the mean of
+#' the serial distribution (sometimes called the serial interval) is known. The
+#' final estimate can be quite sensitive to this value, so sensitivity testing
+#' is strongly recommended. Users should be careful about units of time (e.g.,
+#' are counts observed daily or weekly?) when implementing.

 #'
 #'

-#' Our code has been modified to provide an estimate even if case counts equal to zero are present in some time intervals. This is done
-#' by grouping the counts over such periods of time. Without grouping, and in the presence of zero counts, no estimate can be provided.
+#' Our code has been modified to provide an estimate even if case counts equal
+#' to zero are present in some time intervals. This is done by grouping the
+#' counts over such periods of time. Without grouping, and in the presence of
+#' zero counts, no estimate can be provided.

 #'
 #' @param NT Vector of case counts.
 #'
 #' @param NT Vector of case counts.

-#' @param mu Mean of the serial distribution. This needs to match case counts in time units. For example, if case counts
-#'           are weekly and the serial distribution has a mean of seven days, then \code{mu} should be set to one. If case
-#'           counts are daily and the serial distribution has a mean of seven days, then \code{mu} should be set to seven.
-#' @param kappa Largest possible value of uniform prior (defaults to 20). This describes the prior belief on ranges of R0,
-#'              and should be set to a higher value if R0 is believed to be larger.  
+#' @param mu Mean of the serial distribution. This needs to match case counts in
+#'           time units. For example, if case counts are weekly and the serial
+#'           distribution has a mean of seven days, then \code{mu} should be set
+#'           to one. If case counts are daily and the serial distribution has a
+#'           mean of seven days, then \code{mu} should be set to seven.
+#' @param kappa Largest possible value of uniform prior (defaults to 20). This
+#'              describes the prior belief on ranges of R0, and should be set to
+#'              a higher value if R0 is believed to be larger.

 #'
 #'

-#' @return \code{secB} returns a list containing the following components: \code{Rhat} is the estimate of R0 (the posterior mean),
-#'         \code{posterior} is the posterior distribution of R0 from which alternate estimates can be obtained (see examples),
-#'         and \code{group} is an indicator variable (if \code{group=TRUE}, zero values of NT were input and grouping was done 
-#'         to obtain \code{Rhat}). The variable \code{posterior} is returned as a list made up of \code{supp} (the support of
-#'         the distribution) and \code{pmf} (the probability mass function).
+#' @return \code{seqB} returns a list containing the following components:
+#'         \code{Rhat} is the estimate of R0 (the posterior mean),
+#'         \code{posterior} is the posterior distribution of R0 from which
+#'         alternate estimates can be obtained (see examples), and \code{group}
+#'         is an indicator variable (if \code{group=TRUE}, zero values of NT
+#'         were input and grouping was done to obtain \code{Rhat}). The variable
+#'         \code{posterior} is returned as a list made up of \code{supp} (the
+#'         support of the distribution) and \code{pmf} (the probability mass
+#'         function).

 #'
 #' @examples
 #'
 #' @examples

-#' ## ===================================================== ##
-#' ## Illustrate on weekly data                             ##
-#' ## ===================================================== ##
-#'
+#' # Weekly data.

 #' NT <- c(1, 4, 10, 5, 3, 4, 19, 3, 3, 14, 4)
 #' NT <- c(1, 4, 10, 5, 3, 4, 19, 3, 3, 14, 4)

-#' ## obtain Rhat when serial distribution has mean of five days
-#' res1 <- seqB(NT=NT, mu=5/7)
+#'
+#' ## Obtain R0 when the serial distribution has a mean of five days.
+#' res1 <- seqB(NT, mu = 5 / 7)

 #' res1$Rhat
 #' res1$Rhat

-#' ## obtain Rhat when serial distribution has mean of three days
-#' res2        <- seqB(NT=NT, mu=3/7)
+#'
+#' ## Obtain R0 when the serial distribution has a mean of three days.
+#' res2 <- seqB(NT, mu = 3 / 7)

 #' res2$Rhat
 #'
 #' res2$Rhat
 #'

-#' ## ============================================================= ##
-#' ## Compute posterior mode instead of posterior mean and plot     ##
-#' ## ============================================================= ##
+#' # Compute posterior mode instead of posterior mean and plot.

 #'
 #'

-#' Rpost <-    res1$posterior
+#' Rpost <- res1$posterior

 #' loc <- which(Rpost$pmf == max(Rpost$pmf))
 #' loc <- which(Rpost$pmf == max(Rpost$pmf))

-#' Rpost$supp[loc] # posterior mode
-#' res1$Rhat # compare with posterior mean
+#' Rpost$supp[loc] # Posterior mode.
+#' res1$Rhat # Compare with the posterior mean.

 #'
 #'

-#' par(mfrow=c(2, 1), mar=c(2, 2, 1, 1))
-#' plot(Rpost$supp, Rpost$pmf, col="black", type="l", xlab="", ylab="")
-#' abline(h=1/(20/0.01+1), col="red")
-#' abline(v=res1$Rhat, col="blue")
-#' abline(v=Rpost$supp[loc], col="purple")
-#' legend("topright", legend=c("prior", "posterior", "posterior mean (Rhat)", "posterior mode"),
-#'        col=c("red", "black", "blue", "purple"), lty=1)
-#' plot(Rpost$supp, Rpost$pmf, col="black", type="l", xlim=c(0.5, 1.5), xlab="", ylab="")
-#' abline(h=1/(20/0.01+1), col="red")
-#' abline(v=res1$Rhat, col="blue")
-#' abline(v=Rpost$supp[loc], col="purple")
-#' legend("topright", legend=c("prior", "posterior", "posterior mean (Rhat)", "posterior mode"),
-#'        col=c("red", "black", "blue", "purple"), lty=1)
+#' par(mfrow = c(2, 1), mar = c(2, 2, 1, 1))

 #'
 #'

-#' ## ========================================================= ##
-#' ## Compute Rhat using only the first five weeks of data      ##
-#' ## ========================================================= ##
-#' 
-#' res3 <- seqB(NT=NT[1:5], mu=5/7)    # serial distribution has mean of five days
-#' res3$Rhat
+#' plot(Rpost$supp, Rpost$pmf, col = "black", type = "l", xlab = "", ylab = "")
+#' abline(h = 1 / (20 / 0.01 + 1), col = "red")
+#' abline(v = res1$Rhat, col = "blue")
+#' abline(v = Rpost$supp[loc], col = "purple")
+#' legend("topright",
+#'   legend = c("Prior", "Posterior", "Posterior mean", "Posterior mode"),
+#'   col = c("red", "black", "blue", "purple"), lty = 1)

 #'
 #' @export
 #'
 #' @export

-seqB <- function(NT, mu, kappa=20) {   
-    if (length(NT) < 2)
-        print("Warning: length of NT should be at least two.")
-    else {
-        if (min(NT) > 0) {
-            times <- 1:length(NT)
-            tau <- diff(times)
-        }
-           group <- FALSE
-        if (min(NT) == 0) {
-            times <- which(NT > 0)
-            NT <- NT[times]
-            tau <- diff(times)
-            group <- TRUE
-        }
+seqB <- function(NT, mu, kappa = 20) {
+  if (length(NT) < 2) {
+    print("Warning: length of NT should be at least two.")
+  } else {
+    if (min(NT) > 0) {
+      times <- 1:length(NT)
+      tau <- diff(times)
+    }
+    group <- FALSE
+    if (min(NT) == 0) {
+      times <- which(NT > 0)
+      NT <- NT[times]
+      tau <- diff(times)
+      group <- TRUE
+    }

 
 

-        R <- seq(0, kappa, 0.01)
-        prior0 <- rep(1, kappa / 0.01 + 1)
-        prior0 <- prior0 / sum(prior0)
-        k <- length(NT) - 1
-        R0.post <- matrix(0, nrow=k, ncol=length(R))
-        prior <- prior0
-        posterior <- seq(0, length(prior0))
-        gamma <- 1 / mu
+    R <- seq(0, kappa, 0.01)
+    prior0 <- rep(1, kappa / 0.01 + 1)
+    prior0 <- prior0 / sum(prior0)
+    k <- length(NT) - 1
+    R0.post <- matrix(0, nrow = k, ncol = length(R))
+    prior <- prior0
+    posterior <- seq(0, length(prior0))
+    gamma <- 1 / mu

 
 

-        for (i in 1:k) {
-            mm1 <- NT[i]
-            mm2 <- NT[i+1]
-            lambda <- tau[i] * gamma * (R - 1)
-            lambda <- log(mm1) + lambda
-            loglik <- mm2 * lambda - exp(lambda)
-            maxll <- max(loglik)
-            const <- 0
+    for (i in 1:k) {
+      mm1 <- NT[i]
+      mm2 <- NT[i + 1]
+      lambda <- tau[i] * gamma * (R - 1)
+      lambda <- log(mm1) + lambda
+      loglik <- mm2 * lambda - exp(lambda)
+      maxll <- max(loglik)
+      const <- 0

 
 

-            if (maxll > 700)
-                const <- maxll - 700
+      if (maxll > 700)
+        const <- maxll - 700

 
 

-            loglik <- loglik-const
-            posterior <- exp(loglik) * prior
-            posterior <- posterior / sum(posterior)
-            prior <- posterior
-        }
+      loglik <- loglik - const
+      posterior <- exp(loglik) * prior
+      posterior <- posterior / sum(posterior)
+      prior <- posterior
+    }

 
 

-        Rhat <- sum(R * posterior)
+    Rhat <- sum(R * posterior)

 
 

-        return(list(Rhat=Rhat, posterior=list(supp=R, pmf=posterior), group=group))
-    }  
+    return(list(Rhat = Rhat,
+                posterior = list(supp = R, pmf = posterior),
+                group = group))
+  }

 }
 }