Robust Econometrics



The influence of infinitesimal contamination on an estimator is charac-
terized by the
influence function, which measures the relative change in es-
timates caused by an infinitesimally small amount
ε of contamination at x
(Hampel et al., 1986). More formally,

IF(x; T, F) = lim T{(1 - ε)F + εδx} - T(F).            (1)

ε→0              ε

For each point г, the influence function reveals the rate at which the esti-
mator
T changes if a wrong observation appears at г. In the case of sample
mean
x = T(Fn) for {xi}n=1, we obtain

(1 - ε)   udFn(u) + ε udδx (u) -   udFn (u)


г; T, Fn ) = lim
ε→0

= lim

- udFn(u) + udδx (u)


ε→0

The influence function allows us to define various desirable properties
of an estimation method. First, the largest influence of contamination on
estimates can be formalized by the
gross-error sensitivity,

γ(T,F) = supIF(x;T,F),                     (2)

xR

which under robustness considerations be finite and small. Even though such
a measure can depend on
F in general, the qualitative results (e.g., γ(T, F)
being bounded) are typically independent of
F. Second, the sensitivity to
small changes in data, for example moving an observation from
x to y R,
can be measured by the
local-shift sensitivity

λT Fy-F ( χ ; T,F ) - 1F ( y ; T-F ) k             rn

λ ( T’F ) =    ----------iF-yii----------              (3)



More intriguing information

1. Financial Markets and International Risk Sharing
2. Trade Liberalization, Firm Performance and Labour Market Outcomes in the Developing World: What Can We Learn from Micro-LevelData?
3. Synthesis and biological activity of α-galactosyl ceramide KRN7000 and galactosyl (α1→2) galactosyl ceramide
4. Fiscal Rules, Fiscal Institutions, and Fiscal Performance
5. The name is absent
6. Mergers under endogenous minimum quality standard: a note
7. SOME ISSUES CONCERNING SPECIFICATION AND INTERPRETATION OF OUTDOOR RECREATION DEMAND MODELS
8. Nonlinear Production, Abatement, Pollution and Materials Balance Reconsidered
9. The name is absent
10. The name is absent