California Housing Data

This is the data from the paper Sparse spatial autoregressions by R. Kelley Pace and Ronald Barry (Statistics & Probability Letters, Volume 33, Issue 3, 1997, Pages 291-297). The original data comes from a 1990 census in California. The data was downloaded from a different website.

The dataset here was slightly modified:

• All samples with a median house value of $500,001 have been removed.
• The remaining samples have randomly been split into training set and a test set of (approximately) equal size.

Description

The training dataset has 9838 rows, the test dataset has 9837 rows. The rows correspond to different block groups in the census. (A block group is to a geographic unit used by the United States Census Bureau for tabulation and reporting of census data. Block groups are designed to be relatively homogeneous units with respect to population characteristics, economic status and living conditions.)

Both data sets have 9 columns:

• latitude [degrees]
• longitude [degrees]
• housing median age [years]
• total rooms in the block group
• total bedrooms in the block group
• total population for the block group
• number of households in the block group
• median income [1,000 USD/year]
• median house value [USD]

Download

• training dataset: train.csv
• test dataset: test.csv

Copyright © 2024 Jochen Voss. All content on this website (including text, pictures, and any other original works), unless otherwise noted, is licensed under the CC BY-SA 4.0 license.