A dataset containing results for reproducing Figure 5 in Section 5 of the UAI article.
1 |
A data frame containing evaluations of JAM-MR and MASSIVE in various simulated scenarios.
Name of algorithm, either JAM-MR or MASSIVE.
Integer number of valid instruments in the simulation.
Numeric value of beta (causal effect from X to Y) in the simulation.
Root-mean-square error (RMSE) achieved by the algorithm.
Standard error for RMSE metric across replications.
Bootstrapped confidence interval 2.5% quantile for RMSE across replications.
Bootstrapped confidence interval 97.5% quantile for RMSE across replications.
Simulation configuration (number of observations):(noise magnitude).
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.