Resolve merge conflicts by choosing files being merged in

README.Rmd

@@ -44,7 +44,7 @@ pak::pak("Gilead-BioStats/graphicalMCP@dev")
   - see `vignette("closed-testing")` for graphical multiple comparison procedures based on the closure principle
   - see `vignette("graph-examples")` for common multiple comparison procedures illustrated using `graphicalMCP`
   - see `vignette("generate-closure")` for rationales to generate the closure and the weighting strategy of a graph
-  - see `vignette("comparison")` for comparisons to other R packages
+  - see `vignette("comparisons")` for comparisons to other R packages
 
 ## Related work
 
@@ -74,4 +74,3 @@ Along with the authors and contributors, thanks to the following people for thei
 Frank Bretz, Willi Maurer, Ekkehard Glimm, Nan Chen, Jeremy Wildfire, Spencer Childress, Colleen McLaughlin, Matt Roumaya, Chelsea Dickens, and Ron Yu
 
 We owe a debt of gratitude to the authors of [gMCP](https://cran.r-project.org/package=gMCP) for their pioneering work, without which this package would not be nearly as extensive as it is.
-

README.md

@@ -43,7 +43,7 @@ pak::pak("Gilead-BioStats/graphicalMCP@dev")
     procedures illustrated using `graphicalMCP`
   - see `vignette("generate-closure")` for rationales to generate the
     closure and the weighting strategy of a graph
-  - see `vignette("comparison")` for comparisons to other R packages
+  - see `vignette("comparisons")` for comparisons to other R packages
 
 ## Related work
 

misc/example_3.R

@@ -59,11 +59,7 @@ cbind(gw, cJ)
 # calculation above
 p_vals <- c(.01, .02, .005, .5)
 
-<<<<<<< HEAD
 gMCP(as_graphMCP(g), p_vals, alpha = alpha, correlation = corr,
-=======
-gMCP(as_gmcp_graph(g), p_vals, alpha = alpha, correlation = test_corr,
->>>>>>> test-specification
      test = "parametric")@rejected
 graph_test_closure(g, p_vals, alpha = alpha, test_corr = test_corr,
            tests = list(parametric = list(1:4)))$hypotheses_rejected

misc/vignettes/performance.Rmd

@@ -279,11 +279,7 @@ if (file.exists(here("vignettes/data/df_benchmarks_seqtest.rds"))) {
         `graphicalMCP shortcut (R)` = graph_test_shortcut(rando, p),
         `lrstat Bonferroni (C++)` = fadjpbon(hyp, trn, p) <= .025,
         `gMCP closure parametric (R)` =
-<<<<<<< HEAD:misc/vignettes/performance.Rmd
           gMCP(as_graphMCP(rando), p, alpha = .025, corr = diag(size)),
-=======
-          gMCP(as_gmcp_graph(rando), p, alpha = .025, test_corr = diag(size)),
->>>>>>> test-specification:vignettes/performance.Rmd
         `graphicalMCP closure parametric (R)` =
           graph_test_closure(rando, p, test_corr = diag(size)),
         `lrstat Simes (C++)` =

vignettes/generate-closure.Rmd

@@ -74,7 +74,7 @@ $m$ is the number of hypotheses.
 
 ## Comparing different approaches to calculating weighting strategies
 
-To benchmark against existing approaches to calculating weighting strategies, we compare the following approaches: `gMCP::generateWeights()` [@rohmeyer-2020-gmcp], `lrstat::fwgtmat()` [lu-2016-graphical], Approach 1 (graphicalMCP simple) and Approach 2 (graphicalMCP parent-child). Random graphs are generated for the numbers of hypotheses of 4, 8, 12, and 16. Computing time (in median log-10 milliseconds) is plotted below. We can see that [gMCP::generateWeights()] is the slowest and [lrstat::fwgtmat()] is the fastest. Approach 2 (graphicalMCP parent-child) is faster than Approach 1 (graphicalMCP simple). Note that [lrstat::fwgtmat()] implements the calculation using C++, which is known to be faster than R. But it is less stable than other approaches, e.g., giving errors more often than others. Given that the computing time of R-based approaches is acceptable, adding Rcpp dependency is not considered in `graphicalMCP`. For these considerations, we implement Approach 2 in [graphicalMCP::graph_generate_weights()].
+To benchmark against existing approaches to calculating weighting strategies, we compare the following approaches: `gMCP::generateWeights()` [@rohmeyer-2020-gmcp], `lrstat::fwgtmat()` [@lu-2016-graphical], Approach 1 (graphicalMCP simple) and Approach 2 (graphicalMCP parent-child). Random graphs are generated for the numbers of hypotheses of 4, 8, 12, and 16. Computing time (in median log-10 milliseconds) is plotted below. We can see that `gMCP::generateWeights()` is the slowest and `lrstat::fwgtmat()` is the fastest. Approach 2 (graphicalMCP parent-child) is faster than Approach 1 (graphicalMCP simple). Note that `lrstat::fwgtmat()` implements the calculation using C++, which is known to be faster than R. But it is less stable than other approaches, e.g., giving errors more often than others. Given that the computing time of R-based approaches is acceptable, adding Rcpp dependency is not considered in `graphicalMCP`. For these considerations, we implement Approach 2 in `graphicalMCP::graph_generate_weights()`.
 
 ![](img/gw-benchmarks-plot.png)