Loading wiki pages...

Wiki Version:
<p>The following files are included:</p> <ul> <li><code>volume_SDT.R</code>: Calculate the volume of the polytopes representing the Block-Marschak inequalities. Also contains the code for the creating the matrix representing the Block-Marschak inequalities for the Swets (1959) data in which 5-AFC and 7-AFC are missing.</li> <li><code>statpower.R</code>: Calculate power of test for Block-Marschack inequalities with and without the monotonic-likelihood constraints.</li> <li><code>independence.R</code>: Calculate power for the multiplicative inequalities.</li> <li><code>swets_analysis.R</code>: Reanalysis of Swets (1959) data. Create corresponding figure.</li> <li><code>fig_rank_ROC_reanalysis.R</code>: yes-no ROC reconstruction using ranking and "answer-until-correct" data from Kellen and Klauer (2014), McAdoo and Gronlund (2016), and Chechile et al. (2012).</li> <li><code>analysis_exp1.R</code> to <code>analysis_exp4.R</code>: Analysis of the experiments 1 to 4. Requires the data in folder <code>data</code>. </li> <li><code>vertex_representations.pdf</code>: Contains the vertex representations of the Block-Marschak inequalities (as applied to $m$-AFC recognition) and the Block-Marschak inequalities together with monotonic likelihood.</li> <li><code>example_violations_BMI.R</code>: Contains the code that produces the two example sets of choice probabilities that violate the BMIs given in section "The Testability of the Block-Marschak Inequalities in Recognition Memory".</li> <li><code>asymmetry_examples.R</code>: Code that produces predictions for the Gaussian and double-exponential model in $m$-AFC and $m^*$-AFC task reported in section "Step 4: ROC Symmetry".</li> </ul> <p>To run the code, <code>R</code> is required with the following packages: - <a href="https://github.com/fnoorian/quadprogpp" rel="nofollow"><code>quadprogpp</code></a>: For fitting the Block-Marschack and the other inequalities, we need a function that solves quadratic equations with inequality constraints. <code>R</code> offers several such packages, see section 'Quadratic Optimization' on: <a href="https://cran.r-project.org/view=Optimization" rel="nofollow">https://cran.r-project.org/view=Optimization</a><br> Initially, we used the most popular package, <a href="https://cran.r-project.org/package=quadprog" rel="nofollow"><code>quadprog</code></a> for this purpose. However, in some cases the function got stuck. Consequently, we tried other packages. For example, we observed good, albeit slow, results with <a href="https://cran.r-project.org/package=Dykstra" rel="nofollow"><code>Dykstra</code></a>. So all results reported here should replicate with <code>Dykstra</code> as well. We finally settled on <code>quadprogpp</code> which is a new and fast implementation of <code>quadprog</code>, which currently is only available from <a href="https://github.com/fnoorian/quadprogpp" rel="nofollow">github</a>. It requires a C++ compiler (e.g., Rtools on Windows or Xtools on Mac) and can then be installed via <code>devtools</code>. The <code>tar.gz</code> of <code>quadprogpp</code> which we used can be found in folder <code>packages</code> - <a href="https://cran.r-project.org/package=tidyverse" rel="nofollow"><code>tidyverse</code></a>: Needed for the analysis of the experiments. - <a href="https://cran.r-project.org/package=jsonlite" rel="nofollow"><code>jsonlite</code></a>: For loading in the data of the experiments. - <a href="https://cran.r-project.org/package=MPTinR" rel="nofollow"><code>MPTinR</code></a>: For analysis of experiments 3 and 4.</p> <p>We have successfully executed the code with the following setup:</p> <pre class="highlight"><code>R version 3.5.1 (2018-07-02) Platform: x86_64-pc-linux-gnu (64-bit) Running under: Linux Mint 19 Matrix products: default BLAS: /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.7.1 LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.7.1 locale: [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C LC_TIME=en_US.UTF-8 [4] LC_COLLATE=en_US.UTF-8 LC_MONETARY=de_CH.UTF-8 LC_MESSAGES=en_US.UTF-8 [7] LC_PAPER=de_CH.UTF-8 LC_NAME=C LC_ADDRESS=C [10] LC_TELEPHONE=C LC_MEASUREMENT=de_CH.UTF-8 LC_IDENTIFICATION=C attached base packages: [1] stats graphics grDevices utils datasets methods base other attached packages: [1] bindrcpp_0.2.2 MPTinR_1.11.0 quadprogpp_1.1-0 Rcpp_0.12.18 [5] jsonlite_1.5 forcats_0.3.0 stringr_1.3.1 dplyr_0.7.6 [9] purrr_0.2.5 readr_1.1.1 tidyr_0.8.1 tibble_1.4.2 [13] ggplot2_3.0.0 tidyverse_1.2.1 loaded via a namespace (and not attached): [1] cellranger_1.1.0 pillar_1.3.0 compiler_3.5.1 plyr_1.8.4 [5] bindr_0.1.1 prettyunits_1.0.2 progress_1.2.0 tools_3.5.1 [9] lubridate_1.7.4 nlme_3.1-137 gtable_0.2.0 lattice_0.20-35 [13] pkgconfig_2.0.2 rlang_0.2.2 cli_1.0.0.9002 rstudioapi_0.7 [17] yaml_2.2.0 haven_1.1.2 withr_2.1.2 xml2_1.2.0 [21] httr_1.3.1 hms_0.4.2 grid_3.5.1 tidyselect_0.2.4 [25] glue_1.3.0 R6_2.2.2 fansi_0.3.0 readxl_1.1.0 [29] selectr_0.4-1 modelr_0.1.2 magrittr_1.5 backports_1.1.2 [33] scales_1.0.0 rvest_0.3.2 assertthat_0.2.0 colorspace_1.3-2 [37] numDeriv_2016.8-1 Brobdingnag_1.2-6 utf8_1.1.4 stringi_1.2.4 [41] lazyeval_0.2.1 munsell_0.5.0 broom_0.5.0 crayon_1.3.4</code></pre>
OSF does not support the use of Internet Explorer. For optimal performance, please switch to another browser.
This website relies on cookies to help provide a better user experience. By clicking Accept or continuing to use the site, you agree. For more information, see our Privacy Policy and information on cookie use.

Start managing your projects on the OSF today.

Free and easy to use, the Open Science Framework supports the entire research lifecycle: planning, execution, reporting, archiving, and discovery.