From 1b19fb428273629b5d055775e28722bc680e7e57 Mon Sep 17 00:00:00 2001 From: Daniel Date: Sun, 27 Oct 2024 17:06:10 +0100 Subject: [PATCH] docs --- R/1_model_parameters.R | 18 ++++++++++-------- man/compare_parameters.Rd | 18 ++++++++++-------- man/model_parameters.averaging.Rd | 18 ++++++++++-------- man/model_parameters.cgam.Rd | 18 ++++++++++-------- man/model_parameters.default.Rd | 18 ++++++++++-------- man/model_parameters.glht.Rd | 18 ++++++++++-------- man/model_parameters.merMod.Rd | 18 ++++++++++-------- man/model_parameters.mira.Rd | 18 ++++++++++-------- man/model_parameters.mlm.Rd | 18 ++++++++++-------- man/model_parameters.rma.Rd | 18 ++++++++++-------- man/model_parameters.stanreg.Rd | 18 ++++++++++-------- man/model_parameters.zcpglm.Rd | 18 ++++++++++-------- man/p_function.Rd | 18 ++++++++++-------- man/pool_parameters.Rd | 18 ++++++++++-------- 14 files changed, 140 insertions(+), 112 deletions(-) diff --git a/R/1_model_parameters.R b/R/1_model_parameters.R index 769656f54..458c49600 100644 --- a/R/1_model_parameters.R +++ b/R/1_model_parameters.R @@ -446,14 +446,16 @@ parameters <- model_parameters #' coefficients (and related confidence intervals). This is typical for #' logistic regression, or more generally speaking, for models with log or #' logit links. It is also recommended to use `exponentiate = TRUE` for models -#' with log-transformed response values. **Note:** Delta-method standard -#' errors are also computed (by multiplying the standard errors by the -#' transformed coefficients). This is to mimic behaviour of other software -#' packages, such as Stata, but these standard errors poorly estimate -#' uncertainty for the transformed coefficient. The transformed confidence -#' interval more clearly captures this uncertainty. For `compare_parameters()`, -#' `exponentiate = "nongaussian"` will only exponentiate coefficients from -#' non-Gaussian families. +#' with log-transformed response values. For models with a log-transformed +#' response variable, when `exponentiate = TRUE`, a one-unit increase in the +#' predictor is associated with multiplying the outcome by that predictor's +#' coefficient. **Note:** Delta-method standard errors are also computed (by +#' multiplying the standard errors by the transformed coefficients). This is +#' to mimic behaviour of other software packages, such as Stata, but these +#' standard errors poorly estimate uncertainty for the transformed +#' coefficient. The transformed confidence interval more clearly captures this +#' uncertainty. For `compare_parameters()`, `exponentiate = "nongaussian"` +#' will only exponentiate coefficients from non-Gaussian families. #' @param p_adjust Character vector, if not `NULL`, indicates the method to #' adjust p-values. See [`stats::p.adjust()`] for details. Further #' possible adjustment methods are `"tukey"`, `"scheffe"`, diff --git a/man/compare_parameters.Rd b/man/compare_parameters.Rd index 1b313cd95..073e0ba54 100644 --- a/man/compare_parameters.Rd +++ b/man/compare_parameters.Rd @@ -83,14 +83,16 @@ standardized parameters only works when \code{standardize="refit"}. coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{ci_method}{Method for computing degrees of freedom for p-values and confidence intervals (CI). See documentation for related model class diff --git a/man/model_parameters.averaging.Rd b/man/model_parameters.averaging.Rd index fa91a77ee..39bbfe0f0 100644 --- a/man/model_parameters.averaging.Rd +++ b/man/model_parameters.averaging.Rd @@ -240,14 +240,16 @@ standardized parameters only works when \code{standardize="refit"}. coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{p_adjust}{Character vector, if not \code{NULL}, indicates the method to adjust p-values. See \code{\link[stats:p.adjust]{stats::p.adjust()}} for details. Further diff --git a/man/model_parameters.cgam.Rd b/man/model_parameters.cgam.Rd index e04cbeb3a..72ee6f30c 100644 --- a/man/model_parameters.cgam.Rd +++ b/man/model_parameters.cgam.Rd @@ -100,14 +100,16 @@ standardized parameters only works when \code{standardize="refit"}. coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{p_adjust}{Character vector, if not \code{NULL}, indicates the method to adjust p-values. See \code{\link[stats:p.adjust]{stats::p.adjust()}} for details. Further diff --git a/man/model_parameters.default.Rd b/man/model_parameters.default.Rd index e377fe27c..872270db0 100644 --- a/man/model_parameters.default.Rd +++ b/man/model_parameters.default.Rd @@ -110,14 +110,16 @@ standardized parameters only works when \code{standardize="refit"}. coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{p_adjust}{Character vector, if not \code{NULL}, indicates the method to adjust p-values. See \code{\link[stats:p.adjust]{stats::p.adjust()}} for details. Further diff --git a/man/model_parameters.glht.Rd b/man/model_parameters.glht.Rd index 55ded27eb..100a8052e 100644 --- a/man/model_parameters.glht.Rd +++ b/man/model_parameters.glht.Rd @@ -24,14 +24,16 @@ or of class \code{PMCMR}, \code{trendPMCMR} or \code{osrt} (\strong{PMCMRplus}). coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{keep}{Character containing a regular expression pattern that describes the parameters that should be included (for \code{keep}) or excluded diff --git a/man/model_parameters.merMod.Rd b/man/model_parameters.merMod.Rd index 5f34e5714..7f7147de7 100644 --- a/man/model_parameters.merMod.Rd +++ b/man/model_parameters.merMod.Rd @@ -249,14 +249,16 @@ are shown.} coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{p_adjust}{Character vector, if not \code{NULL}, indicates the method to adjust p-values. See \code{\link[stats:p.adjust]{stats::p.adjust()}} for details. Further diff --git a/man/model_parameters.mira.Rd b/man/model_parameters.mira.Rd index 5b379f152..785151ae2 100644 --- a/man/model_parameters.mira.Rd +++ b/man/model_parameters.mira.Rd @@ -36,14 +36,16 @@ coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{p_adjust}{Character vector, if not \code{NULL}, indicates the method to adjust p-values. See \code{\link[stats:p.adjust]{stats::p.adjust()}} for details. Further diff --git a/man/model_parameters.mlm.Rd b/man/model_parameters.mlm.Rd index ccc605b36..11b83a4f8 100644 --- a/man/model_parameters.mlm.Rd +++ b/man/model_parameters.mlm.Rd @@ -114,14 +114,16 @@ standardized parameters only works when \code{standardize="refit"}. coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{p_adjust}{Character vector, if not \code{NULL}, indicates the method to adjust p-values. See \code{\link[stats:p.adjust]{stats::p.adjust()}} for details. Further diff --git a/man/model_parameters.rma.Rd b/man/model_parameters.rma.Rd index 39d3d96dd..e388a84b8 100644 --- a/man/model_parameters.rma.Rd +++ b/man/model_parameters.rma.Rd @@ -51,14 +51,16 @@ standardized parameters only works when \code{standardize="refit"}. coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{include_studies}{Logical, if \code{TRUE} (default), includes parameters for all studies. Else, only parameters for overall-effects are shown.} diff --git a/man/model_parameters.stanreg.Rd b/man/model_parameters.stanreg.Rd index af4303bed..7ea0a94bc 100644 --- a/man/model_parameters.stanreg.Rd +++ b/man/model_parameters.stanreg.Rd @@ -183,14 +183,16 @@ Bayesian models. All arguments in \code{...} are passed to coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{effects}{Should results for fixed effects, random effects or both be returned? Only applies to mixed models. May be abbreviated.} diff --git a/man/model_parameters.zcpglm.Rd b/man/model_parameters.zcpglm.Rd index 4ed13d492..d7f14b755 100644 --- a/man/model_parameters.zcpglm.Rd +++ b/man/model_parameters.zcpglm.Rd @@ -74,14 +74,16 @@ standardized parameters only works when \code{standardize="refit"}. coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{p_adjust}{Character vector, if not \code{NULL}, indicates the method to adjust p-values. See \code{\link[stats:p.adjust]{stats::p.adjust()}} for details. Further diff --git a/man/p_function.Rd b/man/p_function.Rd index fa210dc77..fd82f9f6b 100644 --- a/man/p_function.Rd +++ b/man/p_function.Rd @@ -62,14 +62,16 @@ highlighted values should be named \code{"emph"}, e.g coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{effects}{Should parameters for fixed effects (\code{"fixed"}), random effects (\code{"random"}), or both (\code{"all"}) be returned? Only applies diff --git a/man/pool_parameters.Rd b/man/pool_parameters.Rd index 6b02889b0..7a848ef03 100644 --- a/man/pool_parameters.Rd +++ b/man/pool_parameters.Rd @@ -22,14 +22,16 @@ pool_parameters( coefficients (and related confidence intervals). This is typical for logistic regression, or more generally speaking, for models with log or logit links. It is also recommended to use \code{exponentiate = TRUE} for models -with log-transformed response values. \strong{Note:} Delta-method standard -errors are also computed (by multiplying the standard errors by the -transformed coefficients). This is to mimic behaviour of other software -packages, such as Stata, but these standard errors poorly estimate -uncertainty for the transformed coefficient. The transformed confidence -interval more clearly captures this uncertainty. For \code{compare_parameters()}, -\code{exponentiate = "nongaussian"} will only exponentiate coefficients from -non-Gaussian families.} +with log-transformed response values. For models with a log-transformed +response variable, when \code{exponentiate = TRUE}, a one-unit increase in the +predictor is associated with multiplying the outcome by that predictor's +coefficient. \strong{Note:} Delta-method standard errors are also computed (by +multiplying the standard errors by the transformed coefficients). This is +to mimic behaviour of other software packages, such as Stata, but these +standard errors poorly estimate uncertainty for the transformed +coefficient. The transformed confidence interval more clearly captures this +uncertainty. For \code{compare_parameters()}, \code{exponentiate = "nongaussian"} +will only exponentiate coefficients from non-Gaussian families.} \item{effects}{Should parameters for fixed effects (\code{"fixed"}), random effects (\code{"random"}), or both (\code{"all"}) be returned? Only applies