Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review
Higher-order properties of approximate estimators. / Kristensen, Dennis; Salanié, Bernard.
In: Journal of Econometrics, Vol. 198, No. 2, 01.06.2017, p. 189-208.Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review
}
TY - JOUR
T1 - Higher-order properties of approximate estimators
AU - Kristensen, Dennis
AU - Salanié, Bernard
PY - 2017/6/1
Y1 - 2017/6/1
N2 - Many modern estimation methods in econometrics approximate an objective function, for instance, through simulation or discretization. These approximations typically affect both bias and variance of the resulting estimator. We first provide a higher-order expansion of such “approximate” estimators that takes into account the errors due to the use of approximations. We show how a Newton–Raphson adjustment can reduce the impact of approximations. Then we use our expansions to develop inferential tools that take into account approximation errors: we propose adjustments of the approximate estimator that remove its first-order bias and adjust its standard errors. These corrections apply to a class of approximate estimators that includes all known simulation-based procedures. A Monte Carlo simulation on the mixed logit model shows that our proposed adjustments can yield significant improvements at a low computational cost.
AB - Many modern estimation methods in econometrics approximate an objective function, for instance, through simulation or discretization. These approximations typically affect both bias and variance of the resulting estimator. We first provide a higher-order expansion of such “approximate” estimators that takes into account the errors due to the use of approximations. We show how a Newton–Raphson adjustment can reduce the impact of approximations. Then we use our expansions to develop inferential tools that take into account approximation errors: we propose adjustments of the approximate estimator that remove its first-order bias and adjust its standard errors. These corrections apply to a class of approximate estimators that includes all known simulation-based procedures. A Monte Carlo simulation on the mixed logit model shows that our proposed adjustments can yield significant improvements at a low computational cost.
KW - Bias adjustment
KW - Extremum estimators
KW - Higher-order expansion
KW - Numerical approximation
KW - Simulation-based estimation
U2 - 10.1016/j.jeconom.2016.10.008
DO - 10.1016/j.jeconom.2016.10.008
M3 - Journal article
AN - SCOPUS:85015363417
VL - 198
SP - 189
EP - 208
JO - Journal of Econometrics
JF - Journal of Econometrics
SN - 0304-4076
IS - 2
ER -