Validation of Local and Remote Data Tables (pointblank)
Validate data in local data frames, local ‘tibble’ objects, in ‘CSV’ and ‘TSV’ files, and in database tables (‘PostgreSQL’ and ‘MySQL’). Validation pipelines can be made using easily-readable, consecutive validation steps and such pipelines allow for switching of the data table context. Upon execution of the validation plan, several reporting options are available. User-defined thresholds for failure rates allow for the determination of appropriate reporting actions (e.g., sending email notifications).

Power Calculations for Longitudinal Multilevel Models (powerlmm)
Calculate power for two- and three-level multilevel longitudinal studies with missing data. Both the third-level factor (e.g. therapists, schools, or physicians), and the second-level factor (e.g. subjects), can be assigned random slopes. Studies with partially nested designs, unequal cluster sizes, unequal allocation to treatment arms, and different dropout patterns per treatment are supported. For all designs power can be calculated both analytically and via simulations. The analytical calculations extends the method described in Galbraith et al. (2002) <doi:10.1016/S0197-2456(02)00205-2>, to three-level models. Additionally, the simulation tools provides flexible ways to investigate bias, type I errors and the consequences of model misspecification.

Semi-Definite Quadratic Linear Programming Solver (sdpt3r)
Solves the general Semi-Definite Linear Programming formulation using an R implementation of SDPT3 (K.C. Toh, M.J. Todd, and R.H. Tutuncu (1999) <doi:10.1080/10556789908805762>). This includes problems such as the nearest correlation matrix problem (Higham (2002) <doi:10.1093/imanum/22.3.329>), D-optimal experimental design (Smith (1918) <doi:10.2307/2331929>), Distance Weighted Discrimination (Marron and Todd (2012) <doi:10.1198/016214507000001120>), as well as graph theory problems including the maximum cut problem. Technical details surrounding SDPT3 can be found in R.H Tutuncu, K.C. Toh, and M.J. Todd (2003) <doi:10.1007/s10107-002-0347-5>.

Access the System Credential Store from R (keyring)
Platform independent ‘API’ to access the operating system’s credential store. Currently supports: ‘Keychain’ on ‘macOS’, Credential Store on ‘Windows’, the Secret Service ‘API’ on ‘Linux’, and a simple, platform independent store implemented with environment variables. Additional storage back-ends can be added easily.

Fast Imputation of Missing Values (missRanger)
Alternative implementation of the beautiful ‘MissForest’ algorithm used to impute mixed-type data sets by chaining tree ensembles, introduced by Stekhoven, D.J. and Buehlmann, P. (2012) <doi:10.1093/bioinformatics/btr597>. Under the hood, it uses the lightning fast random jungle package ‘ranger’. Between the iterative model fitting, we offer the option of using predictive mean matching. This firstly avoids imputation with values not already present in the original data (like a value 0.3334 in 0-1 coded variable). Secondly, predictive mean matching tries to raise the variance in the resulting conditional distributions to a realistic level. This would allow e.g. to do multiple imputation when repeating the call to missRanger().

Advertisements