FF Challenge Files

Data files from the FF Challenge project are now available for download through the the OPR Data Archive.

The FF Challenge data files are associated with the predictive modeling stage of the FF Challenge competition, held in Summer 2017. These files are now being provided so that other data users may replicate and extend what participants did in the Challenge.

The Challenge files include:
-    readme.txt – a text file with descriptions of the remaining files
-    background.csv - birth-Year 9 data, as a .csv
-    background.dta - birth-Year 9 data, as a Stata .dta file
-    codebook_FFChallenge.txt - merged codebook for all waves
-    prediction.csv - an example submission that predicts the mean of the training data for all outcomes
-    train.csv - outcomes for training observations (half the sample)
-    test.csv - outcomes for test observations
-    leaderboard.csv - outcomes for observations in the leaderboard set, with missing outcomes imputed (as provided via Codalab)
-    leaderboardUnfilled.csv - outcomes for observations in the leaderboard set (not imputed)

For more detail on what's available, please visit the Fragile Families Challenge blog.