My da|ra Login

Detailed view

metadata language: English

Data and Code for: Quality-adjusted house price indexes

Version
1
Resource Type
Dataset : event/transaction data, text
Creator
  • Nowak, Adam (West Virginia University)
  • Smith, Patrick (San Diego State University)
Publication Date
2020-08-26
Free Keywords
textual analysis; house price index; machine learning; repeat sales
Description
  • Abstract

    The constant-quality assumption in repeat-sales house price indexes (HPIs) introduces a significant time-varying attribute bias. The direction, magnitude, and source of the bias varies throughout the market cycle and across metropolitan statistical areas (MSAs). We mitigate the bias using a data-driven textual analysis approach that identifies and includes salient text from real estate agent remarks in the repeat-sales estimation. Absent the text, MSA-level HPIs are biased downwards by as much as 7% during the financial crisis and upwards by as much as 20% after the crisis. The geographic concentration of the bias magnifies its effect on local HPIs.
Temporal Coverage
  • 2000-01-01 / 2017-12-31
    Time Period: Sat Jan 01 00:00:00 EST 2000--Sun Dec 31 00:00:00 EST 2017
  • 2018-01-01 / 2018-12-31
    Collection Date(s): Mon Jan 01 00:00:00 EST 2018--Mon Dec 31 00:00:00 EST 2018
Geographic Coverage
  • 9 large MSAs across the United States
Sampled Universe
Transactions sold on the Multiple Listings Service platform across 9 MSAs. Smallest Geographic Unit: Property
Collection Mode
  • Data preparation code provided.  Multiple Listings Service (MLS) data is proprietary but is available for purchase from the MLS.  See README file for more information.

Availability
Download
This study is freely available to the general public via web download.
Relations
  • Is version of
    DOI: 10.3886/E116941

Update Metadata: 2020-08-29 | Issue Number: 1 | Registration Date: 2020-08-29

Nowak, Adam; Smith, Patrick (2020): Data and Code for: Quality-adjusted house price indexes. Version: 1. ICPSR - Interuniversity Consortium for Political and Social Research. Dataset. https://doi.org/10.3886/E116941V1