Peer effects and measurement error: the impact of sampling variation in school survey data (evidence from PISA)
Peer effects and measurement error: the impact of sampling variation in school survey data (evidence from PISA)
Investigation of peer effects on achievement with sample survey data on schools may mean that only a random sample of the population of peers is observed for each individual. This generates measurement error in peer variables similar in form to the textbook case of errors-in-variables, resulting in the estimated peer group effects in an OLS regression model being biased towards zero. We investigate the problem using survey data for England from the Programme for International Student Assessment (PISA) linked to administrative microdata recording information for each PISA sample member's entire year cohort. We calculate a peer group measure based on these complete data and compare its use with a variable based on peers in just the PISA sample. We also use a Monte Carlo experiment to show how the extent of the attenuation bias rises as peer sample size falls. On average, the estimated peer effect is biased downwards by about one third when drawing a sample of peers of the size implied by the PISA survey design.
peer effects, measurement error, school surveys, sampling variation, PISA
1136-1142
Micklewright, John
744a4bca-41f2-4cbb-9a4e-3e0effdaa739
Schnepf, Sylke V.
c987c810-d33c-4675-9764-b5e15c581dbc
Silva, Pedro N.
c1bf3829-1074-4c10-9360-b09d4f1b807d
December 2012
Micklewright, John
744a4bca-41f2-4cbb-9a4e-3e0effdaa739
Schnepf, Sylke V.
c987c810-d33c-4675-9764-b5e15c581dbc
Silva, Pedro N.
c1bf3829-1074-4c10-9360-b09d4f1b807d
Micklewright, John, Schnepf, Sylke V. and Silva, Pedro N.
(2012)
Peer effects and measurement error: the impact of sampling variation in school survey data (evidence from PISA).
Economics of Education Review, 31 (6), .
(doi:10.1016/j.econedurev.2012.07.015).
Abstract
Investigation of peer effects on achievement with sample survey data on schools may mean that only a random sample of the population of peers is observed for each individual. This generates measurement error in peer variables similar in form to the textbook case of errors-in-variables, resulting in the estimated peer group effects in an OLS regression model being biased towards zero. We investigate the problem using survey data for England from the Programme for International Student Assessment (PISA) linked to administrative microdata recording information for each PISA sample member's entire year cohort. We calculate a peer group measure based on these complete data and compare its use with a variable based on peers in just the PISA sample. We also use a Monte Carlo experiment to show how the extent of the attenuation bias rises as peer sample size falls. On average, the estimated peer effect is biased downwards by about one third when drawing a sample of peers of the size implied by the PISA survey design.
Text
Peer effects_28 Sept 2011.doc
- Accepted Manuscript
More information
Published date: December 2012
Keywords:
peer effects, measurement error, school surveys, sampling variation, PISA
Organisations:
Social Statistics & Demography
Identifiers
Local EPrints ID: 341625
URI: http://eprints.soton.ac.uk/id/eprint/341625
ISSN: 0272-7757
PURE UUID: a913f969-80ca-4340-940f-93247ab4fe12
Catalogue record
Date deposited: 30 Jul 2012 13:17
Last modified: 14 Mar 2024 11:42
Export record
Altmetrics
Contributors
Author:
John Micklewright
Author:
Sylke V. Schnepf
Author:
Pedro N. Silva
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics