For #DeclareDesign #launchday, here’s a thread about our five #rstats packages for research design and analysis: DeclareDesign, fabricatr, estimatr, randomizr, and DesignLibrary.
5 📦’s in 5 📣’s!
@graemedblair @jasperjcooper @maqartan
5 📦’s in 5 📣’s!
@graemedblair @jasperjcooper @maqartan
DeclareDesign is “ggplot for research designs.” You add together design elements – data generating processes, sampling and assignment schemes, and estimators to declare a design. declaredesign.org/r/declaredesig… 
fabricatr simulates fake data to help imagine your data before you collect it, especially hierarchical data common in the social sciences (students in classes in schools). Aaron Rudkin and Neal Fultz deserve big credit for development. declaredesign.org/r/fabricatr/
randomizr makes common forms of random assignment (like blocked-and-clustered designs) and random sampling (like stratified designs) easier, and less error-prone. Check out the cheatsheat here: github.com/rstudio/cheats… declaredesign.org/r/randomizr/
estimatr fulfills all your robust standard errors needs for commonly-used OLS, IV, and fixed effects models. If you don’t like our defaults, you can use @stata’s with se_type = “stata.” estimatr shines because of @lukesonnet’s technical brilliance declaredesign.org/r/estimatr/
DesignLibrary provides one-line functions to declare common designs. This reduces typing so you can diagnose and modify quickly. Big thanks to @clara_bmc and Lily Medina who helped lead on this one! declaredesign.org/library
Our software is inspired by the “tidy” standards set by @hadleywickham and the rest of the @RStudio team. We’ve worked hard so each package fits in easily to a tidy workflow. @dataandme @StatGarrett @alexpghayes
