uations are based on simple survey questions that ask the respondents whether
they would have hypothetically reached the same decision in absence of the DSM
program. Due to the nature of these questions, the calculated free rider share
may therefore be susceptible to a hypothetical- or response bias.1 Malm (1996)
circumvents these difficulties by analyzing the revealed choice of high efficiency
heating system purchases among different clusters of consumers. He derives an
impressive share of 89% of households that would have bought the efficient equip-
ment even in the absence of a subsidy.
The present paper illustrates an alternative approach for quantifying free-
riding by combining revealed preference data with cost estimates derived from
engineering calculations. Our method is similar to Cameron’s (1985) in that nests
are imposed to capture correlation of the utility across alternatives, but, rather
than using the nested logit model, we employ an analog thereof that involves
the specification of an error-components structure (Brownstone and Train 1999).
We additionally allow for heterogeneous preferences by specifying household spe-
cific random parameters, closely following Revelt and Train’s (1998) analysis of
the willingness-to-pay for lower operating costs of household appliances. Our
investigation uncovers a potential free-rider share of up to 50% of the sampled
households, substantially lower than Malm’s (1996) estimates but still sufficiently
high to warrant scrutiny of financial support for renovations.
The paper is outlined as follows. After a brief description of the data, Section
2 discusses the challenges of accommodating unobserved heterogenity in a discrete
choice framework and describes alternative models derived from random utility
theory for addressing them. Section 3 catalogues the empirical results and uses
these to derive household-specific estimates of marginal willingness-to-pay. These
results are used to draw policy implications with respect to free-rider problems
in the context of Germany’s current grants scheme. Section 4 concludes.
1To the extent that program participants feel committed to justify the existence of the DSM
program the bias would yield an underestimation of the true free-rider share.