8.2 LR in R: Predicting Recidvism (1)

  • Logistic regression (LR) models the probability that \(Y\) belongs to a particular category (0 or 1)
    • Rather than modeling response \(Y\) directly
  • COMPAS data: Model probability to recidivate (reoffend)
    • Outcome \(y\): Recidivism is_recid (0,1,0,0,1,1,...)
    • Various predictors \(x's\)
      • age = age
      • prior offenses = priors_count
  • Use LR to obtain predicted values \(\hat{y}\) + As probabilities predicted values will range between 0 and 1 + Depend on input/features (e.g., age, prior offences)
  • Convert predicted values (probabilities) to a binary variable
    • e.g., individuals will recidivate (is_recid = Yes) if Pr(is_recid=Yes|age) > 0.5 (p(age) > 0.5)
    • Here we call this variable classified
    • More conservative: Use lower threshold, e.g., individuals will recidivate (is_recid = Yes) if Pr(is_recid=Yes|age) > 0.1
  • Source: James et al. (2013, chap. 4.3)

References

James, Gareth, Daniela Witten, Trevor Hastie, and Robert Tibshirani. 2013. An Introduction to Statistical Learning: With Applications in R. Springer Texts in Statistics. Springer.