Inspiration
We wanted to find out if question scores of discovery value, actionability, correctness/confidence, and level of expertise correlated with the measure of scientific productivity Relative Citation Ratio (RCR).
What it does
Graphs data points including conditional probabilities.
How we built it
Least Squares Regression
Challenges we ran into
Relative Citation Ratios (RCR) values are a relatively new metric that are used for biomedical articles, so only around 280 manuscripts were used as datapoints. Difficult to find a model.
Accomplishments that we're proud of
Data visualization.
What we learned
Scores are not a good predictor of RCR values, but we managed to detect different behavior between readers of across levels of expertise.
Log in or sign up for Devpost to join the conversation.