Abstract
In this paper, we estimate a conditional density. In contrast to standard results in the literature in this context we assume that for each observed value of the covariate we observe a sample of the corresponding conditional distribution of size larger than one. A density estimate is defined taking into account the data from all the samples by computing a weighted average using weights depending on the covariates. The error of the density estimate is measured by the \(L_1\)-error. Results concerning consistency and rate of convergence of the estimate are presented, and the performance of the estimate for finite sample size is illustrated using simulated data. Furthermore, the estimate is applied to a problem in fatigue analysis.
Similar content being viewed by others
References
Bott, A., Felber, T., Kohler, M. (2013). Estimation of a density in a simulation model. Journal of Nonparametric Statistics, 2015.
Devroye, L. (1983). The equivalence in L1 of weak, strong and complete convergence of kernel density estimates. Annals of Statistics, 11, 896–904.
Devroye, L. (1987). A course in density estimation. Basel: Birkhäuser.
Devroye, L. (2015). Personal communication.
Devroye, L., Györfi, L. (1985). Nonparametric density estimation. The L1 view. Wiley series in probability and mathematical statistics: Tracts on probability and statistics. New York: Wiley.
Devroye, L., Lugosi, G. (2001). Combinatorial methods in density estimation. New York: Springer.
Efromovich, S. (2007). Conditional density estimation in a regression setting. Annals of Statistics, 35, 2504–2535.
Fan, J., Yim, T. H. (2004). A crossvalidation method for estimating conditional densities. Biometrika, 91, 819–834.
Fan, J., Yao, Q., Tong, H. (1996). Estimation of conditional densities and sensitivity measures in nonlinear dynamical systems. Biometrika, 83, 189–206.
Furer, D., Kohler, M. (2013). Smoothing spline regression estimation based on real and artificial data. Metrika, 2015.
Gooijer, J. G. D., Zerom, D. (2003). On conditional density estimation. Statistica Neerlandica, 57, 159–176.
Györfi, L., Kohler, M. (2007). Nonparametric estimation of conditional distributions. IEEE Transactions on Information Theory, 53, 1872–1879.
Györfi, L., Kohler, M., Krzyżak, A., Walk, H. (2002). A distribution-free theory of nonparametric regression. New York: Springer.
Hyndman, R. J., Bashtannyk, D. M., Grunwald, G. K. (1996). Estimating and visualizing conditional densities. Journal of Computational and Graphical Statistics, 5, 315–336.
Manson, S. S. (1965). Fatigue: A complex subject—some simple approximation. Experimental Mechanics, 5, 193–226.
Parzen, E. (1962). On the estimation of a probability density function and the mode. Annals of Mathematical Statistics, 33, 1065–1076.
Rosenblatt, M. (1956). Remarks on some nonparametric estimates of a density function. Annals of Mathematical Statistics, 27, 832–837.
Rosenblatt, M. (1969). Conditional probability density and regression estimates. In P. R. Krishnaiah (Ed.), Multivariate analysis II (pp. 25–31). New York: Academic Press.
Scott, D. W. (1992). Multivariate density estimation: Theory, practice and visualization. New York: Wiley.
Stone, C. J. (1977). Consistent nonparametric regression. Annals of Statistics, 5, 595–645.
Williams, C. R., Lee, Y.-L., Rilly, J. T. (2002). A practical method for statistical analysis of strain-life fatigue data. International Journal of Fatigue, 25, 427–436.
Acknowledgments
The authors would like to thank the German Research Foundation (DFG) for funding this project within the Collaborative Research Center 666, and two anonymous referees and an associate editor for detailed and very helpful comments improving an early version of the manuscript.
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Bott, AK., Kohler, M. Nonparametric estimation of a conditional density. Ann Inst Stat Math 69, 189–214 (2017). https://doi.org/10.1007/s10463-015-0535-8
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10463-015-0535-8