administrative data
play

Administrative Data: U.S. Bureau of Labor Statistics David Friedman - PowerPoint PPT Presentation

Measuring Retail Trade with Administrative Data: U.S. Bureau of Labor Statistics David Friedman Associate Commissioner for Prices & Living Conditions Federal Economic Statistics Advisory Committee June 10, 2016 1 U.S. B UREAU OF L


  1. Measuring Retail Trade with Administrative Data: U.S. Bureau of Labor Statistics David Friedman Associate Commissioner for Prices & Living Conditions Federal Economic Statistics Advisory Committee June 10, 2016 1 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  2. Data Sources  Administrative/Publicly available data  Purchased data sets  Company provided data – “corporate level data”  Web scraping/ application program interface (API) 2 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 2 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  3. CPI Data Uses  Create sample frames  Benchmark samples  Supplement collected data to support hedonic modeling (quality adjustment)  Replace/supplement current data collection methods 3 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 3 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  4. Summary: Replacing Collection Initiatives  Almost complete  CorpY – company provided dataset  In progress  CorpX – company provided dataset  JD Power – purchased data  Nielsen – purchased data 4 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 4 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  5. Corporate Level Data: CorpY  Great Opportunity  maintain respondent cooperation  reduce respondent burden  work with transaction level data  receive insurance prices  Challenges  Average prices for broader category and aggregated  Data received in format difficult to process  Status: 1 st production use is May 2016 Index for monthly quotes 5 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 5 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  6. Corporate Level Data: CorpX  Receive sales data monthly by 5 th of following month  Great Opportunity  maintain respondent cooperation  reduce burden  work with sales data 6 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 6 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  7. Corporate Level Data: CorpX  Challenges  mapping the CorpX item categories to the CPI structure  melding the sales level data into our methodology and current system o in particular, accommodate seasonality & item substitution including new methodology o achieve constant-quality price change w/a big data set  lack of characteristic detail  having enough history to validate method 7 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 7 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  8. CorpX Current Status I. Received data for all CPI Primary Sampling Units (PSU’s) beginning with October 2014 II. Testing various methodologies III. Will develop necessary CPI system changes to be ready to use 8 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 8 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  9. JD Power Project  Purchase JD Power dataset as source for replacement in New Vehicles index  Prime example of benefits and challenges of “big data”  Breadth of information  Challenge of integration with current systems  Methodological issues 9 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 9 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  10. New Vehicle Observations 450,000 400,000 350,000 Number of Observations 300,000 250,000 200,000 150,000 100,000 50,000 0 CPI JDPower 10 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 10 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  11. Model Year Price Indexes 11 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 11 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  12. 12 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov Index (100=1/2007) 100 110 120 130 40 50 60 70 80 90 Jan-07 Apr-07 Jul-07 Oct-07 Jan-08 Unit Prices Increase Apr-08 Jul-08 Oct-08 Jan-09 Apr-09 Jul-09 UnitPriceInx Oct-09 Jan-10 Apr-10 Jul-10 Oct-10 Jan-11 MatchedModelTorn Apr-11 Jul-11 Oct-11 Jan-12 Apr-12 Jul-12 Oct-12 Jan-13 Apr-13 Jul-13 Oct-13 Jan-14 Apr-14 Jul-14 Oct-14 Jan-15

  13. Ways to Treat the Price Declines  Show the drop  Show price change across model years  Create “Changeover” price relatives  Use Year-Over-Year Index 13 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 13 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  14. Price Dynamics Average Prices (Source: Aizcorbe, Bridgman and Nalewaik (2010)) 14 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 14 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  15. Price Dynamics Average Prices (Source: Aizcorbe, Bridgman and Nalewaik (2010)) 15 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 15 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  16. 16 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov Index (100=06/2009) 100 102 104 106 108 110 90 92 94 96 98 2007_1 2007_3 2007_5 2007_7 2007_9 2007_11 2008_1 2008_3 JDPower vs CPI 2008_5 2008_7 2008_9 2008_11 2009_1 2009_3 2009_5 2009_7 2009_9 2009_11 Proposed JDPower Index CPI: New Vehicles 2010_1 2010_3 2010_5 2010_7 2010_9 2010_11 2011_1 2011_3 JDP: YOY + Cycle 2011_5 2011_7 2011_9 2011_11 2012_1 2012_3 2012_5 2012_7 2012_9 2012_11 2013_1 2013_3 2013_5 2013_7 2013_9 2013_11 2014_1 2014_3 2014_5 16 2014_7 2014_9 2014_11 2015_1 2015_3

  17. Research Nielsen Indexes  Data set for August 2005 – September 2010  2 million UPC codes  Scantrack coverage limitations  Grocery>$2 million; Drug Stores>$1 million; Mass Merchandisers  Excludes one major retailer and non-UPC items (some produce, deli, bakery, fresh meat, etc.) 17 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 17 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  18. Nielsen Indexes FJ011 - Milk 140 120 100 80 60 40 20 0 CPI Nielsen 18 18 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 18 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  19. Nielsen Indexes FR02 - Candy and chewing gum 140 120 100 80 60 40 20 0 CPI Nielsen 19 19 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 19 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  20. Nielsen Indexes – Current focus  Refine Nielsen indexes to :  Limit research to items that are well represented in the Scantrack data  Account for product downsizing  Account for UPC “churn”  Calculate a geomeans index (in addition to a Tornqvist index) 20 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 20 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  21. Nielsen indexes – Current focus  Preliminary results for 4 item strata  Work on additional 10-12 strata in FY16 CPI and Nielsen Indexes for FA02 – 0000 Cereal and Cereal Products CPI TQ (price in t & (t-1); Churn & Dwnsz) Geo (No missing prices, Churn & Dwnsz) 115 110 105 100 95 200608 200609 200610 200611 200612 200701 200702 200703 200704 200705 200706 200707 200708 200709 200710 200711 200712 200801 200802 200803 200804 200805 200806 200807 200808 200809 200810 200811 200812 200901 200902 200903 200904 200905 200906 200907 200908 200909 200910 200911 200912 201001 201002 201003 201004 201005 201006 201007 201008 201009 21 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 21 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  22. Nielsen Indexes – Current focus CPI and Nielsen Indexes for FA01 – 0000 Flour & Prepared Flour Mixes CPI TQ (price in t and (t-1); churn & dwnsz Geo (no missing prices; churn & dwnsz) 130.00 125.00 120.00 115.00 110.00 105.00 100.00 95.00 90.00 200608 200609 200610 200611 200612 200701 200702 200703 200704 200705 200706 200707 200708 200709 200710 200711 200712 200801 200802 200803 200804 200805 200806 200807 200808 200809 200810 200811 200812 200901 200902 200903 200904 200905 200906 200907 200908 200909 200910 200911 200912 201001 201002 201003 201004 201005 201006 201007 201008 201009 22 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 22 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  23. Nielsen downsizing  Automate identification  Compare to CPI Betty Crocker Fudge Brownie Mix 1600019726 - 18.3OZ 1600044830 - 19.8OZ $4 Millions $3 $2 $1 $0 23 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 23 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  24. Summary: Benefits vs. Challenges Benefits: Challenges:  Increasingly more available  Data quality issues – especially lack of descriptive  Allows for evaluation & info improvement  Timeliness and reliability  May reduce collection costs concerns – mitigation  Reduces respondent burden strategies  Increased sample size  Cost and other  May increase data quality considerations (new skill set,  Sometimes ability to get IT infrastructure, etc.) quantity data 24 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  25. What’s Next  Continue work on CorpX, JD Power, Nielsen  Project to modify CPI production to more readily accept future alternative data  Work with CE to investigate secondary sources for Rent Data  Explore new opportunities 25 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov 25 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

  26. Contact Information David Friedman Associate Commissioner for Prices & Living Conditions www.bls.gov/bls/inflation.htm 202-691-6307 Friedman.David@bls.gov 26 — U.S. B UREAU OF L ABOR S TATISTICS • bls.gov

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend