Enoch Choi thoughts and many many links.
Nicely designed personal log.
And more links.
We model 1980--2003 rating and cohort specific cumulative default
frequencies. The data is decomposed into systematic and firm-specific
risk components. We have to cope with
(i) the shared exposure of each cohort and rating class to the same
systematic risk factor;
(ii) strongly non-Gaussian features of the individual time series;
(iii) possible dynamics of the unobserved common risk factor;
(iv) changing default probabilities per rating cohort over time
(ageing effects), and
(v) missing observations. We propose a non-Gaussian multivariate state
space model that simultaneously deals with all of this issues.
The model is estimated using importance sampling techniques.
A NON-GAUSSIAN PANEL TIME SERIES MODEL FOR ESTIMATING AND
DECOMPOSING DEFAULT RISK
Session Credit Risk
Session Chair Haibin Zhu, Bank for International Settlements
Presenter(s) Robert J.O. Daniels, De Nederlandsche Bank
Co-Author(s) Andre Lucas, Vrije Universiteit Amsterdam and
Tinbergen Institute and Siem Jan Koopman, Vrije Universiteit Amsterdam
Topics Banking, Empirical Finance, Financial Econometrics and State
Space and Factor Models
Keywords credit risk, importance sampling, multivariate
unobserved components models and non-Gaussian state space models
JEL Codes C32, G21
Macroeconomic variables besides inflation and real activity drive the
yield curve in the framework of no-arbitrage affine term structure
models. We construct model-based projection of all the latent factors
onto the observable macro factors, which are real activity and
As a result, the factors are decomposed into the “macro” part: a
linear function of the macro variables and their lags; and the truly
novel part which is orthogonal to the entire history of the macro
variables. We are able to relate the unexplained part of the short
rate to such measures of liquidity as the AAA credit spread and MZM
growth rate. The unexplained part of the slope is highly correlated
with the budget deficit.
NO-ARBITRAGE MACROECONOMIC DETERMINANTS OF THE YIELD CURVE
Session Term Structure Models
Session Chair Ricardo Brito, Ibmec São Paulo
Presenter(s) Ruslan Bikbov, Columbia Business School
Co-Author(s) Mikhail Chernov, Columbia Business School
Topics Asset Pricing, Empirical Finance, Financial Econometrics and
State Space and Factor Models
Keywords Affine models, Credit Spread, dynamic no-arbitrage
models, Liquidity, Monetary policy, MZM money, Public debt, Taylor
Rules, Term Structure of Interest rates and Vector Auto Regression
JEL Codes E43, E44, G12
Kernel density estimation for multivariate data is an important
technique that has a wide range of applications in econometrics and
finance. The lower level of its use is mainly due to the increased
difficulty in deriving an optimal data-driven bandwidth as the
dimension of data increases. We provide Markov chain Monte Carlo
(MCMC) algorithms for estimating optimal bandwidth matrices for
multivariate kernel density estimation.
Our approach is based on treating the elements of the bandwidth matrix
as parameters whose posterior density can be obtained through the
likelihood cross-validation criterion. Numerical studies for bivariate
data show that the MCMC algorithm generally performs better than the
plug-in algorithm under the Kullback-Leibler information criterion.
Numerical studies for five dimensional data show that our algorithm is
superior to the normal reference rule.
MCMC method bandwidth selection for multivariate kernel density
Session Nonparametric Estimation II
Session Chair Qi Li, Texas A&M University
Presenter(s) Maxwell King, Monash University
Co-Author(s) Xibin Zhang, Department of Econometrics and Business
Statistics, Monash University and Rob Hyndman, Monash University
Keywords Cross-validation, Kullback-Leibler information, Mean
integrated squared errors, Monte Carlo kernel likelihood and Sampling
JEL Codes C11, C14, C51
This paper explores prediction in time series in which the data is
generated by a curve-valued autoregression process. It develops a
novel technique, the predictive factor decomposition, for estimation
of the autoregression operator, which is designed to be better suited
for prediction purposes than the principal components method.
The technique is based on finding a reduced-rank approximation to the
autoregression operator that minimizes the norm of the expected
prediction error. The new method is illustrated by an analysis of the
dynamics of Eurodollar futures rates term structure. We restrict the
sample to the period of normal growth and find that in this subsample
the predictive factor technique not only outperforms the principal
components method but also performs on par with the best available
Curve Forecasting by Functional Autoregression
Presenter(s) Alexei Onatski, Columbia University
Co-Author(s) Vladislav Kargin, Cornerstone Research
Session Chair James Stock, Harvard University
Topics Financial Econometrics, Forecasting, State Space and Factor
models and Time Series
Keywords Dimension reduction, Functional data analysis,
Generalized eigenvalue problem, Interest rates, Predictive factors,
Principal components, Reduced-rank regression and Term structure
JEL Codes C23, C53, E43
LMM Calibrator Estimation of volatility and correlation parameters in
the sense of (Brigo and Mercurio 2001), (Brigo and Morini 2004) and
(Brigo, Mercurio, and Morini 2005)
Alternative strategies and implementation issues, Thomas Weber, .
Functional data analysis (FDA) handles longitudinal data and treats
each observation as a function of time (or other variable). The
functions are related. The goal is to analyze a sample of functions
instead of a sample of related points.
FDA differs from traditional data analytic techniques in a number of
ways. Functions can be evaluated at any point in their domain.
Derivatives and integrals, which may provide better information (e.g.
graphical) than the original data, are easily computed and used in
multivariate and other functional analytic methods.
S+Functional Data Analysis User's Guide
by Douglas B. Clarkson, Chris Fraley, Charles C. Gu, James O. Ramsay
Functional Data Analysis (Springer Series in Statistics) (Hardcover)
by J. Ramsay, B. W. Silverman
Covers topics of linear models, principal components, canonical
correlation, and principal differential analysis in function spaces.
Applied Functional Data Analysis (Paperback)
by J.O. Ramsay, B.W. Silverman
Bernard W. Silverman's code site Applied Functional Data Analysis: Methods and Case Studies
Mathematical Statistics with MATHEMATICA,
Colin Rose, Murray D. Smith (Hardcover)
The mathStatica software, an add-on to Mathematica, provides a
toolset specially designed for doing mathematical statistics. It
enables students to solve difficult problems by removing the technical
calculations often associated with mathematical statistics. The
professional statistician will be able to tackle tricky multivariate
distributions, generating functions, inversion theorems, symbolic
maximum likelihood estimation, unbiased estimation, and the checking
and correcting of textbook formulas. This text would be a useful
companion for researchers and students in statistics, econometrics,
engineering, physics, psychometrics, economics, finance, biometrics,
and the social sciences.
Companion site mathStatica.com
See also Suzette Haden Elgin ...
The Gentle Art of Verbal Self-Defense at Work (Paperback)
How I Learned to Love Economics (New Economist)
Going on the job market got rid of my self-esteem problem.
There's nothing like explaining why your work is important to a
new captive audience every 30 minutes to make you believe that your
work really is interesting and important.
At some point it dawned on me, I really did want to be a professor.
I can work hours and hours without stopping, so long as I get to
sleep in the next morning. (If only I felt that way about exercise.)
I like being able to choose my own short-term deadlines. I like doing
research. I have important questions to answer and I enjoy the freedom
to work on them.
The process of completing my dissertation has made it much easier
both to come up with new research topics and to figure out, ahead of
time, which projects might be viable. I know which subfields in my
area are understudied. I know what data sets have or don't have the
information I would need to answer those questions. Literature reviews
for new projects bring up questions that beget future work. I have an
* Ben Jones
Patrick Killelea, National and SF.
Another Fucked Borrower is pure gloom, San Diego-centric.
Ready to burst gives a pop view.
housingtracker tracks MLS inventory and quartile prices.
Bubble tracking is mostly statistics, San Diego-centric.
* Housing Panic
boy in the big housing bubble, eg.
Global Economic Analysis / Mike 'Mish' Shedlock
Bill Fleckenstein (Contrarian Chronicles - moneycentral.msn.com)
Dean Baker (CEPR.net)
Jim Puplava (financialsense.com)
local froth and bubbles in housing.
Buy a fund of funds or a hedge fund index ?
Measure risk with more than Sharpe ratio and multi-factor models.
With very Germanic style:
Unique Access to all Information
Edhec-risk.com offers a unique access to all information appearing in
the different sections and archives. The information is accessed using
a search engine which generates both the key words and the content of
available documents. All the information available on the site is
accessible in relation to the key themes that correspond to the
Centre’s research programmes.
The news media have also become more sensational, more prone to
scandal and possibly less accurate. But note the tension between sensationalism and polarization: the trial of Michael Jackson
got tremendous coverage, displacing a lot of political coverage,
but it had no political valence.
"If you are an old fan and it doesn't fit what you need, don't buy the
disc." she said with firmness, but no rancor.
This Republican Theme Park from America is My Girlfriend by Jasik.
Most pro-life voters aren't looking for 'evolving' views among
candidates. They're hungry for principled positions based on immovable
morals - something that doesn't come from a veto and an op-ed.
-- Carrie Gordon Earll, senior policy analyst for bioethics
for Focus on the Family.
Supporters say Mr. Romney is simply being adroit.
[ * ]