Phone: +44(0)1865 281441
Fax: +44(0)1865 271094
Ian Crawford
Reader in Economics. Department of Economics, University of Oxford, Manor Road Building, Manor Road, Oxford, OX1 3UQEmail: ian.crawford_at_economics.ox.ac.uk
Phone: +44(0)1865 281441
Fax: +44(0)1865 271094
Recent Publications:
Teaching:
Undergraduate Lectures:
Some Current Research
How Demanding is the Revealed Preference Approach to Demand? (with Tim Beatty)
A well-known worry associated with RP tests is that they lack the ability to reject the theory of interest
(see Andreoni and Harbaugh (2008), for example).
For example, if budget constraints do not cross then tests of GARP, whatever the observed choices, cannot fail.
The statistical analogue of this problem of failing to reject is, of course, "power". However, generally the data used
in RP tests consists of non-random variables and the ideas of "power" and "significance", at least given their
established and precise meaning in the statistical literature, are not relevant. In this paper we follow a
suggestion made by John Hey (York) that predictive success is a more useful concept
when dealing with non-random variables. We investigate the measure of predictive success put forward by Selten
(1991) in the context of experimental game theory. This measure takes into account both the "pass rate" (the proportion of the
observed outcomes which conform to the theory) and the "area" of the theory (the proportion of all possible outcomes which are
allowed by the restrictions of the model). Empirically successful models combine high pass rates with small targets. Three requirements of for
a measure of predictive success in RP-tests on heterogeneous samples identify Selten's measure up to positive linear transformation.
Paper
How Many Types are There? (with Krishna Pendakur)
Unobserved heterogeneity is a big deal in applied micro. But anything much more complex that the traditional linear
model with a single fixed effect is very tricky to deal with in a way which is consistent with economic theory.
There is also a whiff of "the unspeakable in pursuit of the inedible" about methods in which the identification of
an unobservable object is bound up with the residuals in a statistical model. Drawing on the long literature on revealed-preference/combinatorial tests of optimising behaviour
we take an economic-theory driven, nonparametric look at unobserved heterogeneity. We provide partitioning
algorithms which will allow researchers to explain cross section data in terms of standard economic models with
precision and minimal recourse to unobserved heterogeneity as part of that explanation. It appears that
unobserved heterogeneity is less important that we may think. No paper, yet, but here are some
slides.
Link to Krish's web page (now with added awesome-ness)
“Your manuscript is both good and original. But the part that is good is not original, and the part that is
original is not good.” Attr. Samuel Johnson
Articles
"Habits Revealed" Review of Economic Studies, forthcoming
"Best Nonparametric Bounds on Demand Responses" Econometrica, 76(6), 2008, 1227–1262 (with R. Blundell and M. Browning)
"Testing for a Reference Consumer in International Comparisons of Living Standards" Amercian Economic Review 98(4), pp. 1731–32, 2008, (with J. Peter Neary)
"Revealed Preference Methods for the Consumer Characteristics Model" Review of Economic Studies, vol 75, pp. 371-389, 2008, (with L. Blow and M. Browning)
"Improving Bounds on Demand Curves " International Economic Review, Vol. 48, No. 4, November 2007, (with R. Blundell and M. Browning).
"The RPI and the cost-of-living index: testing for consistency between theory and practice", Fiscal Studies, (2004), vol. 25, no. 1, pp. 79-91 (with I. Image)
"Nonparametric Engel Curves and Revealed Preference", Econometrica, (2003) vol. 71, no. 1, pp. 205-240, (with R. Blundell and M. Browning)
"Estimation of household demand systems with theoretically compatible Engel curve and unit value specifications", Journal of Econometrics, (2003) vol. 114, pp. 221-241, (with F. Laisney and I. Preston).
"The cost of living with the RPI: Substitution bias in the UK Retail Prices Index", Economic Journal, (2001), 111, F311-334 (with L. Blow)
Book Chapters
“The revealed preference approach to demand” in Quantifying consumer preferences: estimating demand
systems - Contributions to economic analysis Daniel Slottje (ed.), Emerald Press. 2009, with L. Cherchye
L, B. De Rock, F. Vermeulen F.
“Efficiency Analysis and the Lower Convex Hull Approach”, in Quantitative Approaches to Multidimensional
Poverty Measurement, Nanak Kakwani and Jacques Silber (ed.’s) Palgrave Macmillan, 2008, with
G. Anderson and A. Leicester
“Value Added Tax and Excises” in The Mirrlees Review: Dimensions of Tax Design, S. Adam, T. Besley
and R. Blundell (ed.’s), Oxford University Press, 2009, with M. Keen and S. Smith
“The discipline of colleges and universities is in general contrived, not for the benefit of the students,
but for the interest, or more properly speaking, for the ease of the masters. Its object is, in all cases,
to maintain the authority of the master, and whether he neglects or performs his duty, to oblige the students
in all cases to behave toward him as if he performed it with the greatest diligence and ability.” Adam Smith
Microeconomics (Prelims)
Course Page
Lecture Material
Quantitative Economics (Finals)
Course Page
Inequality
Evaluation
Review
Probability Theory
Course Page
Lecture 1
Lecture 2
Lecture 3
Graduate Lectures:
Advanced Econometrics (Nonparametric Estimation) Course Page
Lecture 1
Lecture 2
Lecture 3
Tutorial:
Prelims Tutorial Material
Finals Tutorial Material
“If we knew what it was we were doing, it would not be called research, would it?” Albert Einstein