Abstract
This paper proposes plug-in bandwidth selection for kernel density estimation with discrete data via minimization of mean summed square error. Simulation results show that the plug-in bandwidths perform well, relative to cross-validated bandwidths, in non-uniform designs. We further find that plug-in bandwidths are relatively small. Several empirical examples show that the plug-in bandwidths are typically similar in magnitude to their cross-validated counterparts.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 199-214 |
| Number of pages | 16 |
| Journal | Econometrics |
| Volume | 3 |
| Issue number | 2 |
| DOIs | |
| State | Published - Jun 1 2015 |
Fingerprint
Keywords
- Bandwidth selection
- Discrete variable
- Kernel
- Nonparametric
- Plug-in
ASJC Scopus subject areas
- Economics and Econometrics
Cite this
Plug-in bandwidth selection for kernel density estimation with discrete data. / Chu, Chi Yang; Henderson, Daniel J.; Parmeter, Christopher.
In: Econometrics, Vol. 3, No. 2, 01.06.2015, p. 199-214.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Plug-in bandwidth selection for kernel density estimation with discrete data
AU - Chu, Chi Yang
AU - Henderson, Daniel J.
AU - Parmeter, Christopher
PY - 2015/6/1
Y1 - 2015/6/1
N2 - This paper proposes plug-in bandwidth selection for kernel density estimation with discrete data via minimization of mean summed square error. Simulation results show that the plug-in bandwidths perform well, relative to cross-validated bandwidths, in non-uniform designs. We further find that plug-in bandwidths are relatively small. Several empirical examples show that the plug-in bandwidths are typically similar in magnitude to their cross-validated counterparts.
AB - This paper proposes plug-in bandwidth selection for kernel density estimation with discrete data via minimization of mean summed square error. Simulation results show that the plug-in bandwidths perform well, relative to cross-validated bandwidths, in non-uniform designs. We further find that plug-in bandwidths are relatively small. Several empirical examples show that the plug-in bandwidths are typically similar in magnitude to their cross-validated counterparts.
KW - Bandwidth selection
KW - Discrete variable
KW - Kernel
KW - Nonparametric
KW - Plug-in
UR - http://www.scopus.com/inward/record.url?scp=85028328469&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85028328469&partnerID=8YFLogxK
U2 - 10.3390/econometrics3020199
DO - 10.3390/econometrics3020199
M3 - Article
VL - 3
SP - 199
EP - 214
JO - Econometrics
JF - Econometrics
SN - 2225-1146
IS - 2
ER -