Use of hedonic regression for quality adjustment at Statistics New Zealand Frances Krsinich Geneva, May 2014 UNECE CPI meeting 2014.

Slides:

Advertisements

Similar presentations

1 A House Price Index Based on the SPAR Method Paul de Vries (OTB Research Institute) Jan de Haan (Statistics Netherlands) Gust Mariën (OTB Research Institute)

Advertisements

House Price Measurement in New Zealand and Australia Frances Krsinich - Statistics New Zealand Mark Dubner – Australian Bureau of Statistics 10 –12 May.

Methodological approaches to recording certain types of services in the Consumer Price Index in Belarus Ekaterina Grikhanova, National Statistical Committee.

The Quarter of Christmas Your digital strategy for this Christmas.

By Edwin St Catherine, Director of Statistics, SAINT LUCIA.

Section 1.1, Slide 1 Copyright © 2014, 2010, 2007 Pearson Education, Inc. Section 8.3, Slide 1 Consumer Mathematics The Mathematics of Everyday Life 8.

Inflation Chapter 7 Copyright © 2010 by the McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill/Irwin Principles of Economics: Macroeconomics.

No results on the Midterm yet. I will post them as soon as the grader gets them to me. Also, it is worth restating, that I do not plan to curve the exam.

A Matched-Model Geometric Mean Price Index for Supermarket Scanner Data Nicolette de Bruijn Peter Hein van Mulligen Jan de Haan Sixth EMG Workshop, 13.

Owner-occupied Housing in the New Zealand Consumers Price Index EMG Conference 13 – 15 December 2006 Daniel Griffiths Statistics New Zealand.

Chapter 7 homework Number 2: Scott Anderson Number 4: Eikeem Barron Number 10: Kelly Beck Number 14: Meghan Bouvier Number 16: Thomas Caruso Alternate:

Economists use Consumer Price Index [CPI] to estimate real wages and costs from nominal wages and costs.

Pricing Over the Product Life Cycle: An Empirical Analysis *The authors gratefully acknowledge the Bureau of Economic Analysis (BEA) and NPD Techworld,

28-30 April 2014UNECE - Work session on statistical data editing Data editing and scanner data I. Léonard, G. Varlet and P. Sillard Insee.

The Re-design of the Dutch CPI Jan de Haan Statistics Netherlands Geneva, May 2006.

1 UNECE Meeting of the Group of Experts on Consumer Price Indices, May, 2014 Federal Department of Home Affairs FDHA Federal Statistical Office FSO.

Miroslav Jankovic (Statistical Office of Serbia and Montenegro) Dragi Stojiljkovic Tatjana Stanojevic-Miladinovic (Statistical Office of the Republic of.

E&I of administrative data used for producing business statistics Vera Costa, Frances Krsinich, Rudi Van der Mescht 2008 UNECE Work Session on Statistical.

Meeting of the Group of Experts on Consumer Price Indices. Geneva May 2014, UNECE Workshop 7: Seasonal products. Palais des Nations, Geneva - Meeting.

Monitoring Residential Property Prices: Measurement Issues & The Handbook Project Geert Bruinooge Statistics Netherlands Seminar in Memory of Svein Longva.

United Nations Economic Commission for Europe Statistical Division Calculation of the consumer price index - Recommendations of the CPI Manual Joint EFTA/UNECE/SSCU.

WORKSHOP ON SCANNER DATA Geneva 10 May 2010 Joint presentation by Ragnhild Nygaard (Statistics Norway) and Heymerik van der Grient (Statistics Netherlands)

Chapter 11 Measuring the Cost of Living

Use of administrative data in short term economic indicators Statistics NZ Rochelle Barrow.

Dr Olga Filippova The University of Auckland Department of Property

Inflation & Index Numbers Problems & Issues Dr. D. Foster – ECO 285 – Spring 2014.

UNECE/ILO meeting on CPI Geneva, Switzerland May 2009 Lee Everts Housing in the CPI: The South African Experience and Concerns.

Consumer Loans © 2010 Pearson Education, Inc. All rights reserved.Section 9.3, Slide Determine payments for an add- on loan. Compute finance charges.

1. GROWTH OF REAL GDP AND BUSINESS CYCLES Learning Objectives 1.Define real gross domestic product and explain how its calculation avoids both double-counting.

Workshop on Price Index Compilation Issues February23-27, 2015 Quality Change and New Goods Gefinor Rotana Hotel, Beirut, Lebanon.

GPD and Changes in Price Level Chapter 13, Section 2.

Workshop on Price Index Compilation Issues February 23-27, 2015 Market Basket Items and Weights Gefinor Rotana Hotel, Beirut, Lebanon.

ECE/ILO Meeting on Consumer Price Indices, May 10-12, 2006, Geneva1 E-COMMERCE IN THE ISRAELI CPI Yoel Finkel Merav Yiftach Central Bureau of Statistics,

Improving the Quality of the HMRC Personal Wealth Statistics Rebecca Ambler and Abeda Malek - HMRC.

Handbook on Residential Property Price Indices Chapter 5: Methods Jan de Haan UNECE/ILO Meeting, May 2010.

Workshop on Price Index Compilation Issues February 23-27, 2015 Imputation of Missing Values, Seasonal Products and Quality Changes Gefinor Rotana Hotel,

Aim: Cost-efficient methodology for regional estimates, following SNA/ESA guidelines Why? Balance sheets, wealth inequality, consumption of fixed capital,

The Joint ECE/ILO Group meetings on Consumer Price Indices – 30 years on.

Inflation & Index Numbers Problems & Issues Dr. D. Foster – ECO 285.

Meeting of the Group of Experts on Consumer Price Indices. Geneva May 2014, UNECE Workshop 7: Seasonal products. Palais des Nations, Geneva - Meeting.

1 The Decomposition of a House Price index into Land and Structures Components: A Hedonic Regression Approach by W. Erwin Diewert, Jan de Haan and Rens.

Scanner data in the Luxembourg HICP/CPI Moving towards implementation Claude Lamboray Vanda Guerreiro Scanner Data Workshop ISTAT 1-2 October 2015.

Revising the CPI for the Eastern Caribbean Currency Union ECE/ILO CPI Meeting Geneva, Switzerland May , 2010.

United Nations Economic Commission for Europe Statistical Division ISSUES AND CHALLENGES IN ECONOMIC STATISTICS IN EECCA COUNTRIES Lidia Bratanova, Statistical.

McGraw-Hill/Irwin © 2002 The McGraw-Hill Companies, Inc., All Rights Reserved. Chapter 13 Overstatement of the Cost of Living by the CPI.

Quality Change and Price Indexes Comments by Ellen Dulberger Brookings Workshop on Economic Measurement, February 1, 2001 Second Session Hedonic Price.

The treatment of unmatched items in rolling year GEKS price indexes: Evidence from New Zealand scanner data Jan de Haan, Statistics Netherlands Frances.

1 Outline  Introduction  Methodology for compiling CPI  Data Collection and Compilation.

United Nations Economic Commission for Europe Statistical Division UNECE Workshop on Consumer Price Indices Istanbul, Turkey,10-13 October 2011 Session.

Use of rental equivalence method in CPI CPI workshop Istanbul, 10 – 13 October 2011.

Working with Cross-Section Time-Series Data Sometimes data has cross-section and time-series dimensions For example, consider following a group of firms,

United Nations Economic Commission for Europe Statistical Division UNECE Workshop on Consumer Price Indices Istanbul, Turkey,10-13 October 2011 Session.

Meeting of the Group of Experts on Population and Housing Censuses Geneva, 23 – 26 September 2014 Principles and Recommendations for Population and Housing.

1 Quality adjustment procedures in HICP Prepared by Oskars Alksnis, Central Statistical Bureau of Latvia EU Twinning Project Forwarding Armenian Statistics.

1 HICP experience in Latvia Prepared by Oskars Alksnis Central Statistical Bureau (CSB) of Latvia EU Twinning Project Forwarding Armenian Statistics Through.

CPI/HICP price collection Validation of prices Twinning project: Development of new statistical methodologies and indicators in selected areas of statistics.

Development of a Single Official UK House Price Index Friday 11 th March 2016.

Accounting for Spatial Variation of Land Prices in Hedonic Imputation House Price Indexes: A Semi- Parametric Approach Jan de Haan * and Yunlong Gong **

Copyright 2010, The World Bank Group. All Rights Reserved. Producer prices, part 2 Measurement issues Business Statistics and Registers 1.

1 Chapter 4: Elements for a Conceptual Framework Workshop on Residential Property Price Indices: Statistics Netherlands, The Hague, February 10-11, 2011.

Housing Update SPD and Questionnaires 2 nd Regional Coordinating Agencies meeting May 27-29, 2015 Washington, DC.

 Most common weighted price index used to calculate inflation.  The CPI is calculated four times per year (quarterly) and results from household surveys.

Real Personal Income and Regional Price Parities

Workshop on Residential Property Price Indices

Introduction to statistical background

Session 7: Adjustment for quality changes

Inflation & Index Numbers Problems & Issues

Correcting Statistics for Inflation

Amazon Data Analysis 2014/12/19.

Quality Adjustment Review of UK Consumer Price Statistics

Presentation transcript:

Use of hedonic regression for quality adjustment at Statistics New Zealand Frances Krsinich Geneva, May 2014 UNECE CPI meeting 2014

Outline Used cars Rental survey Consumer electronics scanner data Supermarket scanner data Online data UNECE CPI meeting /05/2014

Used cars Hedonics used since 2001, updated model in 2011 Approx 3500 prices each quarter from sample of used car dealers Initially used an estimation cell method – inefficient and wasted a lot of data UNECE CPI meeting /05/2014

Used cars (2) 2001 introduced time-dummy hedonic index Linear hedonic model K characteristics: - town of purchase (15 categories) - make and model (47) - age (years) - size of engine (cc rating) - odometer reading (km) Rolling 8 quarters estimation, splice on last quarter UNECE CPI meeting /05/2014

Used cars (3) Updated in 2011 Logged price More detailed make and model (47 -> 96) Added squared terms for age and cc rating Added car dealer identifiers (approx 300) UNECE CPI meeting /05/2014

Used cars (4) UNECE CPI meeting /05/2014

Used cars (5) UNECE CPI meeting /05/2014

Rental index Longitudinal (quarterly) survey of landlords of approx 2,800 rental dwellings Updated quarter from bond data for new tenancies Average rents within strata based on bedroom # and region Matched-sample approach to hold quality constant Concern about bias due to missing implicit rent increases at start of tenancies UNECE CPI meeting /05/2014

Rental index (2) Hedonic index to benchmark performance of matched-sample index Not enough characteristics for hedonic model Fixed effects – ie rental dwelling-specific intercepts (controls for time-invariant characteristics) 2 obs needed – retrospective index 27/05/2014UNECE CPI meeting 20149

Rental index (3) Matched-sample bias not large Potential for reducing sample-size if hedonic estimation adopted in production 27/05/2014UNECE CPI meeting

Rental index (4) Validity of fixed-effects approach questioned Extended result of Aizcorbe et al (2003) to show the (implicitly imputed) price movement for a newly rented dwelling is the movement from the average of the quality adjusted rents for ‘continuing’ rental dwellings in previous quarter to the quality adjusted rent of new dwelling Won’t control for time-varying characteristics of rental dwellings (aging, renovation) 27/05/2014UNECE CPI meeting

Consumer electronics scanner data Scanner data from market research company GfK for 12 products (monthly, full set of characteristics) Implementing from Sept 2014 quarter de Haan’s ITRYGEKS method (imputation Tornqvist RYGEKS) - RYGEKS averaging based on bilateral time-dummy hedonic indexes UNECE CPI meeting /05/2014

Consumer electronics scanner data (2) Flat panel TVs Laptops Tablets Smartphones Desktop computers Heat pumps Digital still cameras Audio systems DVD players and recorders Set-top boxes Memory cards Multi-function devices. 27/05/2014UNECE CPI meeting

Supermarket scanner data Still negotiating data Initially may only get data for specifications in basket (and info to help select replacements) Aiming for full-coverage No characteristics, likely to use fixed-effects window-splice (FEWS) index UNECE CPI meeting /05/2014

Online data Investigating potential / methodologies (FEWS index) Initial analysis on 15 months Billion Prices Project daily data for consumer electronics Research agreement with PriceStats – supply of online data for range of NZ retailers UNECE CPI meeting /05/2014