1 / 19

A real-time database for Canada

Introducing a new real-time database for Canada that provides monthly data on selected money and credit series. The database is constructed using information from banks, financial institutions, and Statistics Canada. It includes series such as gross M1+, gross M2++, short-term business credit, long-term business credit, total business credit, total household credit, total residential mortgage credit, and total consumer credit. Revisions to the data are made based on continuity adjustments, adjustments to non-bank data, seasonal adjustments, and new financial instruments. The database aims to improve estimation methods and enhance the understanding of money and credit trends in Canada.

jameswalsh
Download Presentation

A real-time database for Canada

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. A real-time database for Canada Roobina Keshishbanoosy rkeshishbanoosy@bankofcanada.ca roobina@rogers.com

  2. Outline • Presenting the new database • Sources of revisions • Patterns of revisions: short-term and long-term revisions • Future work

  3. The Database • The Canadian money and credit real-time database = monthly data representing selected vintages of various money and credit series • A vintage = the latest estimate of a given series at a particular time • Series: gross M1+, gross M2++, short-term business credit, long-term business credit, total business credit, total household credit, total residential mortgage credit, and total consumer credit

  4. The Database • Constructed with the information received from banks, other financial institutions, and Statistics Canada. • For most of the data, the earliest vintage date is January 1993. There are two exceptions: gross M1+ and gross M2++ which start from 1999.

  5. The Database • Many vintages were created in the third or fourth week of the month= the first release dates • Annualized month-over-month growth rates used in this article => definitional changes => breaks in the level data but not in growth rates = calculated within a given vintage.

  6. Sources of Revisions • 1. Continuity adjustments • Changes in thefinancial industry; mergers and acquisitions, => structural breaks in the data. • 2. Adjustments to non-bank data • Compiled by Statistics Canada • Two sources of revision: 1-Statistics Canada’s quarterly data received two months after the end of a quarter, the Bank of Canada estimates monthly data=> revised afterwards, 2- Statistics Canada revises the data.

  7. Sources of Revisions 3. Seasonal adjustments • New factors representing seasonal patterns are applied to the series in February.

  8. Sources of Revisions 4. New instruments • Some of the series, especially total business credit and long-term business credit, are subject to revisions because of new types of financial instrument. • Example: Flow through shares

  9. Biases and Patterns in Data Revisions • Methodology: -Mean revision= zero= unbiased revisions

  10. Biases and Patterns in Data Revisions • Methodology : -Mean Absolute Revisions: How much, on average and on absolute terms, the data are revised

  11. Revisions compared • Short-run (monthly) revisions • Long-run revisions (scenario A) • Long-run revisions (scenario B)

  12. Mean Revisions Compared

  13. Mean Absolute Revisions Compared

  14. Results • Revisions to non-bank data, seasonal-adjustment factors, and financial innovations major sources of data revisions. • Revising the data tends to settle down within three years or less. • No statistically significant evidence of bias in short-run (monthly) revisions; exception; total residential mortgage credit. • long-term business credit and total business credit = bias over longer periods. Financial Innovation. • Strong first-released (above-average growth) data =>downward revisions for some data. • Mean absolute revisions larger for short-term business credit, total consumer credit, and gross M1+.

  15. Future work • New database: the components of each aggregate: • First released by the Bank of Canada and first released by Statistics Canada • Components: Consumer credit numbers, Residential mortgage credit, M2+ Gross, Short-term and long-term business credit • Major Sub-components; Credit Unions and Caisses Populaires, Non-depository credit intermediaries, securitization • Securitization is the most volatile component • Improving estimation methods

More Related