scdhlm - ggplot2 update

This release includes a bug fix in graph_SCD() that caused an error in plotting data from treatment reversal designs with slopes based on a fitted models. It also updates unit tests for compatibility with latest version of ggplot2.

- R
Published by jepusto over 2 years ago

scdhlm - Missing data handling

This is a re-submission and a maintenance release. The main changes are a small tweak to how missing observations are handled in the function preprocess_SCD() and a corresponding modification to one of the example datasets.

• Modified handling of missing outcome observations in preprocess_SCD() so that the session-by-treatment interaction variable is computed prior to dropping missing outcome observations.
• Modified Bryant2018 example dataset to clarify the timing of treatment phases.
• Added a newdata argument to graph_SCD(), which allows for computing fitted values from model_fit based on a different design structure than the actual data.
• Updates to package documentation.

- R
Published by jepusto over 3 years ago

scdhlm - Maintenance release

This is a maintenance release. The only change is a fix for an outstanding CRAN check error (on ATLAS build).

- R
Published by jepusto over 3 years ago

scdhlm - Convenience functions for calculating BC-SMDs

This version includes several new convenience functions for pre-processing data and calculating between-case effect size estimates. It also includes updates to the built-in web app, as well as a few small bug fixes.

• New convenience functions:
  • Added a convenience function calc_BCSMD() for pre-processing data, fitting an lme() model, and calculating g_mlm() all in one go.
  • Added a convenience function default_times() for calculating default time-points for multiple baseline designs.
  • Added batch_calc_BCSMD() function for calculating BC-SMD effect size estimates for multiple studies of the same design.
• Changes to the shiny app:
  • Fixed bug in shiny app that occurred when uploading a multiple baseline design or a treatment reversal design.
  • Updated the layout of model output in the shiny app so that it is easier to read.
  • Added rclipboard package to the installation instruction of the shiny app.
  • Added Bryant et al. (2018) and Thiemann & Goldstein (2001) to the references in the shiny app.
  • Updated the study design labels in example datasets for multiple baselines across participants.
• Changes to example datasets:
  • Added the academic response outcome data from Lambert et al. (2006) to the package and the shiny app.
  • Updated the Bryant et al. (2018) dataset using the group instead of school as the cluster variable.

- R
Published by jepusto over 3 years ago

scdhlm - shiny app features and documentation

This version includes extensive user-interface and back-end updates to the built-in shiny app (invoked by shine_scd()), as well as a few bug fixes. The vignette, examples, and unit tests have been updated so that the package can be compiled without any Suggested packages.

• Six more example datasets added to the package and the scdhlm web app.
• Revisions to shiny app:
  • The app now includes several options for modeling the dependence structure of level-1 error terms, including AR(1) (the default), MA(1), or independent errors.
  • The app now includes an option for allowing the variance of the level-1 errors to differ by phase.
  • More informative labels for the baseline trend and treatment phase trend options.
  • The centering, initial treatment time, and follow-up time sliders now only appear when they are relevant.
  • The centering slider now appears in the "Model estimates" tab because it is only relevant for interpreting the raw estimates from the fitted model (i.e., it does not affect the graph of fitted values).
  • The "Model" tab now includes a note regarding initial treatment time and follow-up time sliders, which only appears when relevant.
• Fixed a bug so that shine_scd() can take a tibble in the dataset argument.
• Fixed a bug in graph_SCD() function that occurred in treatment reversal designs with cases that had varying numbers of reversals.
• Updated vignette, examples, and unit tests so that the package can be compiled without any packages from SUGGESTS.

- R
Published by jepusto about 4 years ago

scdhlm - Preprocessing and replication code

This release includes a new function preprocess_SCD(), which handles initial data-cleaning steps for multiple baseline and treatment reversal designs. Plus, the scdhlm Shiny app now includes a tab with R code for replicating the app calculations.

- R
Published by jepusto over 5 years ago

scdhlm - Updates and new datasets

• Updated HPS estimation functions to work with datasets (issue #2 from austinj).
• Added additional example datasets (Ruiz, Salazar, Thiemann2001, Thiemann2004, Bryant2018).
• Updated web-app to allow use of .xlsx files.
• Fixed bug in web-app occurring when cases were listed out of alphabetical order.
• Fixed bug in web-app occurring when auto-correlation is very weakly identified.

- R
Published by jepusto over 6 years ago

scdhlm - First CRAN release

First release on CRAN. This version adds a shiny app for calculating between-case standardized mean difference effect sizes via a web interface.

- R
Published by jepusto almost 10 years ago