Stanford MS&E 226 – “Small” Data

Datasets

• Datasets from Data Analysis Using Regression and Multilevel/Hierarchical Models by Gelman and Hill

• Datasets from Introduction to Statistical Learning by James, Witten, Hastie, and Tibshirani

• Datasets from Applied Predictive Modeling by Kuhn and Johnson

• Crime dataset from CMU's Data and Story Library (see Lecture 7)

• Ames real estate data

  • See this article for further details

  • The zip file contains a data dictionary giving interpretation of field names

• (Reduced version of) College Scorecard data

  • See College Scorecard for further deatils

  • This dataset is a simplified version of the scorecard data

  • The download contains a zip file with a data dictionary; the full data dictionary is available here

• Spam dataset

  • Based on data provided as part of the UCI ML repository

• Wine dataset

  • From the UCI ML repository

Notes

• To load .dta files in R, you will need to use the following set of commands:

library(foreign)
indata = read.dta(<filename>)

where <filename> is the data file you wish to read in.

• Files with extension .dat are typically text files with a header line. To load these files in R, you can use the following set of commands:

indata = read.table(<filename>, header = TRUE)

where <filename> is the data file you wish to read in.