Estimating and Visualizing Conditional Densities
Rob J. Hyndman, David M. Bashtannyk, Gary K. Grunwald · Journal of Computational and Graphical Statistics · 1996
We consider the kernel estimator of conditional density and derive its asymptotic bias, variance, and mean-square error. Optimal bandwidths (with respect to integrated mean-square error) are found and it is shown that the convergence rate of the density estimator is order n –2/3. We also note that the conditional mean function obtained from the estimator is equivalent to a kernel smoother. Given the undesirable bias properties of kernel smoothers, we seek a modified conditional density estimator that has mean equivalent to some other nonparametric regression smoother with better bias properties. It is also shown that our modified estimator has smaller mean square error than the standard estimator in some commonly occurring situations. Finally, three graphical methods for visualizing conditional density estimators are discussed and applied to a data set consisting of maximum daily temperatures in Melbourne, Australia.
Cited by 357 works. doi:10.1080/10618600.1996.10474715
Authors
References
- The Market for "Lemons": Quality Uncertainty and the Market Mechanism
- The Tragedy of the Commons
- Generalized Additive Models.
- Social Capital in the Creation of Human Capital
- Generalized Additive Models.
- Focus Groups: A Practical Guide for Applied Research
- The Logic of Collective Action: Public Goods and the Theory of Groups.
- The Virtual Community: Homesteading on the Electronic Frontier
- The Forms of Capital
- Focus Groups as Qualitative Research