DeclareDesign Flashcards
What does declare_model() do?
Defines the background variables (independent variables) and potential outcomes (dependent variables) of your research.
What does declare_inquiry() do?
Specifies the research question and the answer you’re seeking (the estimand). This could be a causal or descriptive inquiry.
What does declare_sampling() do?
Outlines the procedures used to select your sample units from the population.
What does declare_assignment() do?
Defines how treatments or conditions are assigned to the units in your study
What does declare-measurement() do?
Details the procedures used to measure the variables in your research
What does declare_estimator() do?
Specifies the method for estimating the answer (eg, point estimate, interval estimate) based on your data and inquiry
What does declare_test() do?
Defines the statistical tests used to assess the significance of your findings
What does Diagnose_Design do?
Helps you evaluate the strengths and weaknesses of your research design. It generates various “diagnosands” to assess potential issues like bias, RMSE, power, estimate mean, standard deviation and Type S error rate.
What is RMSE?
Root Mean Squared Error indicates the presence of outliers in your data.
What do you need to include when declaring a model?
Units, unit characterisation, potential outcomes, effect sizes
What do you need when declaring an Inquiry?
Whether it is causal or descriptive. If it is a group level inquiry. Or if there are multiple inquiries.
What do you need to include when declaring a data strategy?
Sampling, treatment assignment and measurement
What do you need to include when declaring answer strategies?
Method, functional forms, answer summary, additional outputs.