Last updated on 2023-12-03 07:51:50 CET.
| Flavor | Version | Tinstall | Tcheck | Ttotal | Status | Flags |
|---|---|---|---|---|---|---|
| r-devel-linux-x86_64-debian-clang | 2.0 | 12.49 | 89.61 | 102.10 | NOTE | |
| r-devel-linux-x86_64-debian-gcc | 2.0 | 11.02 | 67.42 | 78.44 | NOTE | |
| r-devel-linux-x86_64-fedora-clang | 2.0 | 130.60 | OK | |||
| r-devel-linux-x86_64-fedora-gcc | 2.0 | 124.49 | OK | |||
| r-devel-windows-x86_64 | 2.0 | 12.00 | 86.00 | 98.00 | OK | |
| r-patched-linux-x86_64 | 2.0 | 15.21 | 85.98 | 101.19 | OK | |
| r-release-linux-x86_64 | 2.0 | 12.79 | 86.94 | 99.73 | OK | |
| r-release-macos-arm64 | 2.0 | 36.00 | OK | |||
| r-release-macos-x86_64 | 2.0 | 59.00 | OK | |||
| r-release-windows-x86_64 | 2.0 | 18.00 | 102.00 | 120.00 | OK | |
| r-oldrel-macos-arm64 | 2.0 | 40.00 | OK | |||
| r-oldrel-macos-x86_64 | 2.0 | 52.00 | OK | |||
| r-oldrel-windows-x86_64 | 2.0 | 16.00 | 102.00 | 118.00 | OK |
Version: 2.0
Check: Rd files
Result: NOTE
checkRd: (-1) about.lvs.Rd:25: Lost braces; missing escapes or markup?
25 | At the moment, several correlation structures are permitted. Let \eqn{D_{ij}} denote the distance between site \eqn{i} and {j} i.e., entry \eqn{(i,j)} in \code{distmat}. Also, let \eqn{(\vartheta_1,\vartheta_2)} denote the two spatial covariance parameters (noting that the second parameter is not required for some of structures). Then we have: 1) \code{lv.type = "exponential"} such that \eqn{\Sigma_{ij} = \exp(-D_{ij}/\vartheta_1)}; 2) \code{lv.type = "squared.exponential"}, such that \eqn{\Sigma_{ij} = \exp(-D_{ij}/\vartheta_1^2)}; 3) \code{lv.type = "power.exponential"}, such that \eqn{\Sigma_{ij} = \exp(-(D_{ij}/\vartheta_1)^{\vartheta_2})} where \eqn{\vartheta_1 \in (0,2]} ; 4) \code{lv.type = "spherical"}, such that \eqn{(D_{ij} < \vartheta_1)*(1 - 1.5*D_{ij}/\vartheta_1 + 0.5*(D_{ij}/\vartheta_1)^3)}. We refer the reader to the \code{geoR} and the function \code{cov.spatial} for more, simple information on spatial covariance functions (Ribeiro Jr and Diggle, 2016).
| ^
checkRd: (-1) about.ranefs.Rd:31: Lost braces
31 | Perhaps not surprisingly, the way response-specific random intercepts are included is very similar to how row effects are included in the model. Specifically, the argument \code{ranef.ids} identifies the number of random intercepts to be included and how each observational unit maps to a cluster. \code{ranefs.ids} is a matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of random intercepts to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random intercept eqn{j}. Examples of its use are provided in the help file below.
| ^
checkRd: (-1) about.ssvs.Rd:32: Lost braces; missing escapes or markup?
32 | \item For elements taking positive integers {1,2,...}, SSVS is applied to each group of coefficients of the corresponding covariate in \eqn{\bm{X}}. That is, the fitted model will return a single posterior probability for this covariate, indicating whether this covariate should be included for all columns of the response matrix; see O'Hara and Sillanpaa (2009) and Tenan et al. (2014) among many others for an discussion of Bayesian variable selection methods.
| ^
checkRd: (-1) boral.Rd:74: Lost braces
74 | \item{row.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of row effects to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random effect eqn{j}. This matrix is useful if one wants to specify more complicated row effect structures beyond a single, row effect unique to each row; please see details below as well as examples below. Whether these row effects are included as fixed or random effects is governed by \code{row.eff}. Defaults to \code{NULL}, so that if \code{row.eff = "none"} then the argument is ignored, otherwise if \code{row.eff = "fixed"} or \code{"random"}, then \cr \code{row.ids = matrix(1:nrow(y), ncol = 1)} i.e., a single, row effect unique to each row.}
| ^
checkRd: (-1) boral.Rd:76: Lost braces
76 | \item{ranef.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of random intercepts to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random intercept eqn{j}; please see \code{\link{about.ranefs}} for details. Defaults to \code{NULL}, in which case it is assumed no random intercepts are to be included in the model. If supplied, then response-specific random intercepts are assumed to come from a normal distribution with mean zero and unknown (response-specific) standard deviation.}
| ^
checkRd: (-1) boral.Rd:159: Lost braces; missing escapes or markup?
159 | where instead of measured covariates, we now have a vector of latent variables \eqn{\bm{u}_i} with \eqn{\bm{\theta}_j} being the response-specific coefficients relating to these latent variables. The response-specific intercept, beta_{0j}, accounts for differences between species prevalence, while the row effect, \eqn{alpha_i}, is included to account for differences in site total abundance (typically assuming a fixed effect, \code{row.eff = "fixed"}, although see Jamil and ter Braak, 2013, for a motivation for using random site effects), so that the ordination is then in terms of species composition. If \eqn{\alpha_i} is omitted from the model i.e., \code{row.eff = FALSE}, then the ordination will be in terms of relative species abundance. As mentioned previously, one reason for including fixed row effects is to account of any potential differences in sampling intensity between sites.
| ^
checkRd: (-1) calc.condlogLik.Rd:38: Lost braces
38 | \item{row.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of row effects to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random effect eqn{j}; please see the \code{\link{boral}} function for details. Defaults to \code{NULL}, so that if \code{row.coefs = NULL} then the argument is ignored, otherwise if \code{row.coefs} is supplied then \code{row.ids = matrix(1:nrow(y), ncol = 1)} i.e., a single, row effect unique to each row. An internal check is done to see \code{row.coefs} and \code{row.ids} are consistent in terms of arguments supplied.}
| ^
checkRd: (-1) calc.logLik.lv0.Rd:41: Lost braces
41 | \item{row.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of row effects to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random effect eqn{j}; please see \code{\link{boral}} for details. Defaults to \code{NULL}, so that if \code{row.params = NULL} then the argument is ignored, otherwise if \code{row.params} is supplied then \cr \code{row.ids = matrix(1:nrow(y), ncol = 1)} i.e., a single, row effect unique to each row. An internal check is done to see \code{row.params} and \code{row.ids} are consistent in terms of arguments supplied.}
| ^
checkRd: (-1) calc.marglogLik.Rd:41: Lost braces
41 | \item{row.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of row effects to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random effect eqn{j}; please see \code{\link{boral}} for details. Defaults to \code{NULL}, so that if \code{row.params = NULL} then the argument is ignored, otherwise if \code{row.params} is supplied then \cr \code{row.ids = matrix(1:nrow(y), ncol = 1)} i.e., a single, row effect unique to each row. An internal check is done to see \code{row.params} and \code{row.ids} are consistent in terms of arguments supplied.}
| ^
checkRd: (-1) calc.varpart.Rd:45: Lost braces
45 | If \code{groupX} is supplied, the variance due to the covariates is done based on subsets of the covariates (including the intercept) as identified by code{groupX}, and then rescaled correspondingly. This is useful if one was to, for example, quantify the proportion of variation in each response which is explained by each covariate.
| ^
checkRd: (-1) create.life.Rd:86: Lost braces
86 | \item{row.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of row effects to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random effect eqn{j}; please see \code{\link{boral}} for details. Defaults to \code{NULL}, so that if \code{row.params = NULL} then the argument is ignored, otherwise if \code{row.params} is supplied then \cr \code{row.ids = matrix(1:nrow(y), ncol = 1)} i.e., a single, row effect unique to each row.}
| ^
checkRd: (-1) create.life.Rd:92: Lost braces
92 | \item{ranef.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of random intercepts to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random intercept eqn{j}; please see \code{\link{about.ranefs}} for details. Defaults to \code{NULL}, in which case it is assumed no random intercepts are to be included in the model. If supplied, then either one of \code{true.ranef} or \code{ranef.params} must also be supplied. If \code{true.ranef} is supplied, then these are used as the true random intercepts; if \code{ranef.params} is supplied, then response-specific random intercepts are generated from a normal distribution with mean zero and (response-specific) standard deviation based on the elements of \code{ranef.params}.}
| ^
checkRd: (-1) get.hpdintervals.Rd:26: Lost braces
26 | \item{row.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of row effects to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random effect eqn{j}; please see \code{\link{boral}} for details. Defaults to \code{NULL}, in which case iti assumed no random effects were included in the model.}
| ^
checkRd: (-1) get.hpdintervals.Rd:28: Lost braces
28 | \item{ranef.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of random intercepts to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random intercept eqn{j}; please see \code{\link{about.ranefs}} for details. Defaults to \code{NULL}, in which case it is assumed no random intercepts are to be included in the model. If supplied, then response-specific random intercepts are assumed to come from a normal distribution with mean zero and unknown (response-specific) standard deviation.}
| ^
checkRd: (-1) get.measures.Rd:33: Lost braces
33 | \item{row.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of row effects to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random effect eqn{j}; please see \code{\link{boral}} for details. Defaults to \code{NULL}, so that if \code{row.eff = "none"} then the argument is ignored, otherwise if \cr \code{row.eff = "fixed"} or \code{"random"}, \cr then \code{row.ids = matrix(1:nrow(y), ncol = 1)} i.e., a single, row effect unique to each row.}
| ^
checkRd: (-1) get.more.measures.Rd:34: Lost braces
34 | \item{row.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of row effects to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random effect eqn{j}; please see \code{\link{boral}} for details. Defaults to \code{NULL}, so that if \code{row.eff = "none"} then the argument is ignored, otherwise if \cr \code{row.eff = "fixed"} or \code{"random"}, \cr then \code{row.ids = matrix(1:nrow(y), ncol = 1)} i.e., a single, row effect unique to each row.}
| ^
checkRd: (-1) make.jagsboralmodel.Rd:56: Lost braces
56 | \item{row.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of row effects to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random effect eqn{j}; please see \code{\link{boral}} for details. Defaults to \code{NULL}, so that if \code{row.eff = "none"} then the argument is ignored, otherwise if \cr \code{row.eff = "fixed"} or \code{"random"}, \cr then \code{row.ids = matrix(1:nrow(y), ncol = 1)} i.e., a single, row effect unique to each row.}
| ^
checkRd: (-1) make.jagsboralmodel.Rd:58: Lost braces
58 | \item{ranef.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of random intercepts to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random intercept eqn{j}; please see \code{\link{about.ranefs}} for details. Defaults to \code{NULL}, in which case it is assumed no random intercepts are to be included in the model. If supplied, then response-specific random intercepts are assumed to come from a normal distribution with mean zero and unknown (response-specific) standard deviation.}
| ^
checkRd: (-1) make.jagsboralnullmodel.Rd:44: Lost braces
44 | \item{row.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of row effects to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random effect eqn{j}; please see \code{\link{boral}} for more details. for details. Defaults to \code{NULL}, so that if \code{row.eff = "none"} then the argument is ignored, otherwise if \cr \code{row.eff = "fixed"} or \code{"random"}, \cr then \code{row.ids = matrix(1:nrow(y), ncol = 1)} i.e., a single, row effect unique to each row.}
| ^
checkRd: (-1) make.jagsboralnullmodel.Rd:46: Lost braces
46 | \item{ranef.ids}{A matrix with the number of rows equal to the number of rows in the response matrix, and the number of columns equal to the number of random intercepts to be included in the model. Element \eqn{(i,j)} indicates the cluster ID of row \eqn{i} in the response matrix for random intercept eqn{j}; please see \code{\link{about.ranefs}} for details. Defaults to \code{NULL}, in which case it is assumed no random intercepts are to be included in the model. If supplied, then response-specific random intercepts are assumed to come from a normal distribution with mean zero and unknown (response-specific) standard deviation.}
| ^
checkRd: (-1) ranefsplot.Rd:23: Lost braces
23 | \item{ordered}{If set to \code{TRUE}, then the random intercept predictions in each caterpillar plot are plotted from smallest to largest. Defaults to \code{FALSE}, in which case the caterpillar plot is simply ordered as per the rows of object{object$ranef.ids}.}
| ^
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc