Preparing 0.2.0 submission

DESCRIPTION

@@ -21,7 +21,7 @@ License: MIT + file LICENSE
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.1
+RoxygenNote: 7.2.3
 Imports: 
     ggplot2,
     dplyr,

NEWS.md

@@ -1,4 +1,4 @@
-# POMADE 0.1.0.9999
+# POMADE 0.2.0
 
 * Corrected formula for expectation of tau-squared estimator in the CE-RVE model, in accordance with corrigendum.
 

R/data-documentation.R

@@ -1,8 +1,8 @@
-#' Co-teaching Dataset
+#' Co-Teaching Dataset
 #'
 #' Data from a meta-analysis on the effects of collaborative models
 #' of instruction on student achievement from Vembye, Weiss, and
-#' Bhat (In press/forthcoming).
+#' Bhat (2023).
 #'
 #' @format A tibble with 76 rows/studies and 9 variables
 #'\describe{
@@ -20,10 +20,10 @@
 #' @source Find background material on \href{https://osf.io/fby7w/}{Vembye's OSF page},
 #' and the preprint at <https://osf.io/preprints/metaarxiv/mq5v7/>.
 #'
-#' @references Vembye, M. H., Weiss, F., & Bhat, B. H. (In press/forthcoming). The Effects
+#' @references Vembye, M. H., Weiss, F., & Bhat, B. H. (2023). The Effects
 #' Co-Teaching and Related Collaborative Models of Instruction on
 #' Student Achievement: A Systematic Review and Meta-Analysis. \emph{Review of
-#' Educational Research}. Access to background material at <https://osf.io/fby7w/>.
+#' Educational Research}, \doi{10.3102/00346543231186588}
 #'
 
-"VWB22_pilot"
+"VWB23_pilot"

R/power_MADE.R

@@ -54,7 +54,7 @@
 #'    var_df = c("Model", "Satt", "RVE"),
 #'    alpha = .05,
 #'    seed = 10052510,
-#'    iterations =5
+#'    iterations = 5
 #'  )
 #'
 #' power

README.Rmd

@@ -25,7 +25,7 @@ knitr::opts_chunk$set(
 [![](http://cranlogs.r-pkg.org/badges/last-month/POMADE)](https://CRAN.R-project.org/package=POMADE)
 <!-- badges: end -->
 
-The POMADE package provides functions for conducting power analysis for tests based on the correlated-hierarchical effects (CHE; Pustejovsky & Tipton, 2021), multi-level meta-analysis (MLMA; Van den Noortgate et al., 2013), and correlated-effects (CE; Hedges et al., 2010) models for meta-analysis of dependent effect sizes, with the possibility to vary assumptions about the variance estimation and the estimation of the degrees of freedom. These approximations aim to replace Hedges & Pigott's (2001) previous power approximation based on the assumption of independence between effect sizes, which has been shown to work inadequately to predict power for models that handle dependent effect sizes (Vembye, Pustejovsky, & Pigott, 2022). The package also includes functions for creating graphical displays of power analysis results.
+The POMADE package provides functions for conducting power analysis for tests based on the correlated-hierarchical effects (CHE; Pustejovsky & Tipton, 2021), multi-level meta-analysis (MLMA; Van den Noortgate et al., 2013), and correlated-effects (CE; Hedges et al., 2010) models for meta-analysis of dependent effect sizes, with the possibility to vary assumptions about the variance estimation and the estimation of the degrees of freedom. These approximations aim to replace Hedges & Pigott's (2001) previous power approximation based on the assumption of independence between effect sizes, which has been shown to work inadequately to predict power for models that handle dependent effect sizes [(Vembye, Pustejovsky, & Pigott, 2022)](https://osf.io/6tp9y). The package also includes functions for creating graphical displays of power analysis results. Find more detail how to conduct reliable power analyses for meta-analysis in [Vembye, Pustejovsky, & Pigott (2024)](https://osf.io/preprints/metaarxiv/3x2en).
 
 ## Installation
 
@@ -55,8 +55,8 @@ library(POMADE)
 library(dplyr)
 
 # Find more information about this dataset by executing the following command below
-# ?VWB22_pilot
-coteach_dat <- VWB22_pilot
+# ?VWB23_pilot
+coteach_dat <- VWB23_pilot
 #glimpse(coteach_dat)
 
 dat_kjsigma2j <- select(coteach_dat, kj, sigma2j = vg_ms_mean)
@@ -78,8 +78,8 @@ power_CHE_RVE_empirical <-
     seed = 10052510
   )
  
-power_CHE_RVE_empirical %>%
-  select(J, tau, omega, rho, power, mcse) %>%
+power_CHE_RVE_empirical  |> 
+  select(J, tau, omega, rho, power, mcse) |>
   head(10)
 
 ```
@@ -95,7 +95,6 @@ power_CHE_RVE_plot <-
   )
 
 power_CHE_RVE_plot
-
 ```
 
 ### Minimum detectable effect size (MDES)
@@ -119,10 +118,9 @@ mdes_CHE_RVE_empirical <-
     seed = 10052510
   )
 
-mdes_CHE_RVE_empirical %>%
-  select(J, tau, omega, rho, target_power, MDES) %>%
+mdes_CHE_RVE_empirical |>
+  select(J, tau, omega, rho, target_power, MDES) |>
   head(10)
-
 ```
 
 The MDES data can then be plotted across plausible scenarios.
@@ -160,22 +158,20 @@ min_studies_example <-
     seed = 10052510,
 )
 
-min_studies_example %>%
-  select(mu, tau, omega, rho, target_power, studies_needed) %>%
+min_studies_example |>
+  select(mu, tau, omega, rho, target_power, studies_needed) |>
   head(10)
-
 ```
 
 and plotted via
 
 ```{r, example3, message=FALSE, warning=FALSE, fig.width=8, fig.height=6}
 min_studies_plot <- 
-  min_studies_example %>%
-  filter(mu == 0.1) %>%
+  min_studies_example |>
+  filter(mu == 0.1) |>
   plot_MADE()
 
 min_studies_plot 
-  
 ```
 
 Alternatively, reviewers can investigate how the number of studies needed varies across various values of the effect size of practical concern.
@@ -187,7 +183,6 @@ min_studies_plot2 <-
   )
 
 min_studies_plot2
-
 ```
 
 ### Traffic light power plot
@@ -201,7 +196,6 @@ plot_MADE(
   expected_studies = c(45, 55),
   traffic_light_assumptions = c("unlikely", "likely", "expected", "expected", "likely")
 )
-
 ```
 
 ## Parallel processing
@@ -262,3 +256,6 @@ Pustejovsky, J. E., & Tipton E. (2021). Meta-analysis with robust variance estim
 Van den Noortgate, W., López-López, J., Marín-Martínez, F., & Sánchez-Meca, J. (2013). Three-level meta-analysis of dependent effect sizes. *Behavior Research Methods*, 45(2), 576–594. <https://doi.org/10.3758/s13428-012-0261-6>
 
 Vembye, M. H., Pustejovsky, J. E., & Pigott, T. D. (2022). Power approximations for overall average effects in meta-analysis with dependent effect sizes. *Journal of Educational and Behavioral Statistics*, 1–33. <https://doi.org/10.3102/10769986221127379>
+
+Vembye, M. H., Pustejovsky, J. E., & Pigott, T. D. (2024). Conducting Power Analysis for Meta-Analysis of Dependent Effect Sizes: Common Guidelines and an Introduction to the POMADE R package. <https://osf.io/preprints/metaarxiv/3x2en>
+

README.md

@@ -24,8 +24,11 @@ degrees of freedom. These approximations aim to replace Hedges &
 Pigott’s (2001) previous power approximation based on the assumption of
 independence between effect sizes, which has been shown to work
 inadequately to predict power for models that handle dependent effect
-sizes (Vembye, Pustejovsky, & Pigott, 2022). The package also includes
-functions for creating graphical displays of power analysis results.
+sizes [(Vembye, Pustejovsky, & Pigott, 2022)](https://osf.io/6tp9y). The
+package also includes functions for creating graphical displays of power
+analysis results. Find more detail how to conduct reliable power
+analyses for meta-analysis in [Vembye, Pustejovsky, & Pigott
+(2024)](https://osf.io/preprints/metaarxiv/3x2en).
 
 ## Installation
 
@@ -58,8 +61,8 @@ library(POMADE)
 library(dplyr)
 
 # Find more information about this dataset by executing the following command below
-# ?VWB22_pilot
-coteach_dat <- VWB22_pilot
+# ?VWB23_pilot
+coteach_dat <- VWB23_pilot
 #glimpse(coteach_dat)
 
 dat_kjsigma2j <- select(coteach_dat, kj, sigma2j = vg_ms_mean)
@@ -81,8 +84,8 @@ power_CHE_RVE_empirical <-
     seed = 10052510
   )
 
-power_CHE_RVE_empirical %>%
-  select(J, tau, omega, rho, power, mcse) %>%
+power_CHE_RVE_empirical  |> 
+  select(J, tau, omega, rho, power, mcse) |>
   head(10)
 #> # A tibble: 10 × 6
 #>        J   tau omega   rho power    mcse
@@ -138,8 +141,8 @@ mdes_CHE_RVE_empirical <-
     seed = 10052510
   )
 
-mdes_CHE_RVE_empirical %>%
-  select(J, tau, omega, rho, target_power, MDES) %>%
+mdes_CHE_RVE_empirical |>
+  select(J, tau, omega, rho, target_power, MDES) |>
   head(10)
 #> # A tibble: 10 × 6
 #>        J   tau omega   rho target_power   MDES
@@ -196,8 +199,8 @@ min_studies_example <-
     seed = 10052510,
 )
 
-min_studies_example %>%
-  select(mu, tau, omega, rho, target_power, studies_needed) %>%
+min_studies_example |>
+  select(mu, tau, omega, rho, target_power, studies_needed) |>
   head(10)
 #> # A tibble: 10 × 6
 #>       mu   tau omega   rho target_power studies_needed
@@ -218,8 +221,8 @@ and plotted via
 
 ``` r
 min_studies_plot <- 
-  min_studies_example %>%
-  filter(mu == 0.1) %>%
+  min_studies_example |>
+  filter(mu == 0.1) |>
   plot_MADE()
 
 min_studies_plot 
@@ -286,7 +289,7 @@ system.time(
     )
 )
 #>    user  system elapsed 
-#>   35.40    0.25   35.81
+#>   33.38    0.58   34.30
 
 plan(multisession, workers = 2)
 
@@ -306,7 +309,7 @@ system.time(
     )
 )
 #>    user  system elapsed 
-#>    0.08    0.00   26.84
+#>    0.14    0.01   23.07
 
 identical(res_seq, res_par)
 #> [1] TRUE
@@ -336,3 +339,8 @@ Vembye, M. H., Pustejovsky, J. E., & Pigott, T. D. (2022). Power
 approximations for overall average effects in meta-analysis with
 dependent effect sizes. *Journal of Educational and Behavioral
 Statistics*, 1–33. <https://doi.org/10.3102/10769986221127379>
+
+Vembye, M. H., Pustejovsky, J. E., & Pigott, T. D. (2024). Conducting
+Power Analysis for Meta-Analysis of Dependent Effect Sizes: Common
+Guidelines and an Introduction to the POMADE R package.
+<https://osf.io/preprints/metaarxiv/3x2en>

_pkgdown.yml

@@ -27,4 +27,4 @@ reference:
   - title: "Datasets"
     desc: "Example datasets"
     contents:
-      - VWB22_pilot
+      - VWB23_pilot