Researchers need to select high quality research designs and communicate those designs to readers. Both tasks are difficult. We provide a framework for formally characterizing the analytically relevant features of a research design. In standard applications, the approach to design declaration we describe requires defining a model of the world (M), an inquiry (I), a data strategy (D), and answer strategy (A). We advocate that scholars declare each feature formally in computer code, and then use Monte Carlo techniques to diagnose properties such as power, bias, expected mean squared error, external validity with respect to some population, and other “diagnosands.” Declaring a design in this way lays researchers’ assumptions bare. Ex ante design declarations can be used to improve designs and facilitate preregistration, analysis, and reconciliation of intended and actual analyses. Ex post design declarations are also useful for describing, sharing, reanalyzing, and critiquing existing designs. We provide an open-source software package, DeclareDesign, to implement the proposed approach.

The full paper can be found here: [ Ссылка ]

Read more about the Annual Meeting here: [ Ссылка ]

свернуть