Pending Research:
PAPER: mpress72.pdf = "Variance Estimates and Model Selection" is attached at the end. It is close to publishable, but needs a little more work.
Dear Asad Hoca,
In order to update the literature review part of our paper I made a
literature survey and found the following papers. I haven't downloaded the
full papers yet but as soon as I do so, I want to read them. Moreover
there is the GDP application that I have to work on.
Best wishes,
Sidika
We consider issues related to the order of an autoregression selected
using information criteria. We study the sensitivity of the estimated
order to (i) whether the effective number of observations is held fixed
when estimating models of different order, (ii) whether the estimate of
the variance is adjusted for degrees of freedom, and (iii) how the penalty
for overfitting is defined in relation to the total sample size.
Simulations show that the lag length selected by both the Akaike and the
Schwarz information criteria are sensitive to these parameters in finite
samples. The methods that give the most precise estimates are those that
hold the effective sample size fixed across models to be compared.
Theoretical considerations reveal that this is indeed necessary for valid
model comparisons. Guides to robust model selection are provided.
Suggested Citation
Ng, Serena and Perron, Pierre, "A Note on the Selection of Time Series
Models" . Oxford Bulletin of Economics & Statistics, Vol. 67, No. 1, pp.
115-134, February 2005
Available at SSRN: http://ssrn.com/abstract=647036
In this paper we consider the problem of estimating a non-parametric
regression function using the k nearest-neighbour method. We provide
asymptotic theories for the least-squares cross validation (CV) selected
smoothing parameter k for both local constant and local linear estimation
methods. We also establish the asymptotic normality results for the
resulting non-parametric regression function estimators. Some limited
Monte Carlo experiments show that the CV method performs well in finite
sample applications.
Suggested Citation
Ouyang, Desheng, Li, Dong and Li, Qi , "Cross-Validation and
Non-Parametric k Nearest-Neighbour Estimation" . Econometrics Journal,
Vol. 9, No. 3, pp. 448-471, November 2006 Available at SSRN:
http://ssrn.com/abstract=941531 or DOI: 10.1111/j.1368-423X.2006.00193.x
Estimating the lag length of autoregressive process for a time series is a
crucial econometric exercise in most economic studies. This study attempts
to provide helpfully guidelines regarding the use of lag length selection
criteria in determining the autoregressive lag length. The most
interesting finding of this study is that Akaike’s information criterion
(AIC) and final prediction error (FPE) are superior than the other
criteria under study in the case of small sample (60 observations and
below), in the manners that they minimize the chance of under estimation
while maximizing the chance of recovering the true lag length. One
immediate econometric implication of this study is that as most economic
sample data can seldom be considered “large” in size, AIC and FPE are
recommended for the estimation the autoregressive lag length.
Suggested Citation
Liew, Venus Khim-Sen, "Which Lag Length Selection Criteria Should We
Employ?" . Economics Bulletin, Vol. 3, No. 33, pp. 1−9, 2004
Available at SSRN: http://ssrn.com/abstract=885505
Model selection methods have shown to be useful in the process of
econometric modelling. The paper studies robust Akaike-Schwarz type
information criteria of model choice within the Cox model. The criteria
are based on a smooth modification of the partial likelihood function.
Apart from asymptotic results, a Monte Carlo study is presented, which
shows the finite sample behaviour of the procedure under discrepancies
from the Cox model. Analysis of a real unemployment data case is also
included.
Suggested Citation
Bednarski, Tadeusz and Mocarska, Edyta, "On Robust Model Selection Within
the Cox Model" . Econometrics Journal, Vol. 9, No. 2, pp. 279-290, July
2006
Available at SSRN: http://ssrn.com/abstract=913511 or DOI:
10.1111/j.1368-423X.2006.00185.x