Overview

Column

  • Pre-K provider data, including geographic data, licensure, and other quality indicators
    • Schools associated with pre-K provider data by computing a weighted (by physical distance from the school) sum of features for all providers within a 40 mile radius
  • 203 total features, including geographical location of school and other enrollment data
  • District-level covariates included from the Stanford Educational Data Archive

Summary of features

Column

Pre-K Features

Math

Column

Test RMSE

3.00

Test MAE

2.39

Test \(R^2\)

0.11

Column

Tree parameters

Hyperparameter tuning

Gamma (regularization)

Hyperparameter tuning

Stochastic parameters

Hyperparameter tuning

L1/L2 regularization

Hyperparameter tuning

Learning rate

Hyperparameter tuning

Column

School proportion FRL

Feature interpretation

Hispanic student

Feature interpretation

Bachelor’s plus

Feature interpretation

Letter Sounds

Column

Test RMSE

8.80

Test MAE

6.76

Test \(R^2\)

0.17

Column

Tree parameters

Hyperparameter tuning

Gamma (regularization)

Hyperparameter tuning

Stochastic parameters

Hyperparameter tuning

L1/L2 regularization

Hyperparameter tuning

Learning rate

Hyperparameter tuning

Column

School proportion FRL

Feature interpretation

Hispanic student

Feature interpretation

Bachelor’s plus

Feature interpretation

Social

Column

Test RMSE

6.02

Test MAE

4.59

Test \(R^2\)

0.02

Column

Tree parameters

Hyperparameter tuning

Gamma (regularization)

Hyperparameter tuning

Stochastic parameters

Hyperparameter tuning

L1/L2 regularization

Hyperparameter tuning

Learning rate

Hyperparameter tuning

Column

School proportion FRL

Feature interpretation

Hispanic student

Feature interpretation

Bachelor’s plus

Feature interpretation