Black Litterman model has been used largely for portfolio construction, one of the major differences with Markowitz mean-variance Efficient Frontier model, among others, is BL allows users to input certain views under confidence level on assets, say, "I am 85% confident S&P 500 will have 5% excess return", or "Bond index will outperform equity index by 1.5% certainly", etc. If you are totally fresh to Black Litterman model, click here.

Most of paper on Black litterman are about how to construct an optimized portfolio, and this portfolio can be adjusted under given risk constraint, Attilio Meucci, going further step, has a paper incorporating natually stress testing and scenerio analysis under Black Litterman framework, they propose a unified methodology to input non-linear views from any number of users in fully general non-normal markets, and perform, among others, stress-testing, scenario analysis, and ranking allocation. Paper "Fully Flexible Views: Theory and Practice" and Matlab codes are at http://papers.ssrn.com/sol3/papers.cfm?abstract_id=1213325 and http://www.mathworks.com/matlabcentral/fileexchange/21307.

Just finished an interview today, Balabala one and half an hour without even a detailed technical question, I suspect if it is really a Quant related job position or the desire the company indeed needs a people. Anyway, fighting.

Cointegration is the foundation upon which pair trading (“statistical arbitrage”) is built, basic cointegration function can be easily found in any popular statistical software package, for instance, Unit root and cointegration tests for time series data (urca) in R. Should you are interested in playing with advanced cointegration test, go there, for instance, estimating a threshold bi-variate VECM, and testing for the presence of a threshold.

Focusing on 3 publications
"Tests for parameter instability in regressions with I(1) Processes." Journal of Business and Economic Statistics (1992).

"Residual-based tests for cointegration in models with regime shifts." with Allan Gregory, Journal of Econometrics, (1996).

"Testing for two-regime threshold cointegration in vector error correction models," with Byeongseon Seo, Journal of Econometrics (2002).

A collection of codes on Copula estimation and simulation is shown here, where you can find parameter estimation for t-copula, Grouped-t copula, asymmetric copula, etc., another simple recursive routine to estimate by maximum likelihood the correlation matrix and the degrees of freedom for structured t-copula is shared at http://www.mathworks.com/matlabcentral/fileexchange/19751, the authors impose extra structure on the correlation matrix in the estimation process, where the number of variables is large as compared to the number of observations.

The paper "Estimation of Structured t-Copulas" is available at: http://papers.ssrn.com/sol3/papers.cfm?abstract_id=1126401, more paper and codes are at the author's homepage: http://www.symmys.com/AttilioMeucci/Home/Home.html

Generalized method of moments (GMM) estimation has got more and more popularity for linear and non-linear models with applications in economics and finance. GMM estimation was formalized by Hansen (1982), and since has become one of the most widely used methods of estimation for models in economics and finance. Unlike maximum likelihood estimation (MLE), GMM does not require complete knowledge of the distribution of the data. Only specified moments derived from an underlying model are needed for GMM estimator. In some cases in which the distribution of the data is known, MLE can be computationally very burdensome whereas GMM can be computationally very easy. The log-normal stochastic volatility model is one example. In models for which there are more moment conditions than model parameters, GMM estimation provides a straightforward way to test the specification of the proposed model. This is an important feature that is unique to GMM estimator.

Download Programs for GMM and Empirical Likelihood at http://www.ssc.wisc.edu/~bhansen/progs/progs_gmm.html

Finally, Happy easter day to all of you, while I will have to stay at home preparing interview

A simple, straightforward way to estimate density nonparametrically is kernel density estimator, for instance, in R a built-in function density() is for this, with different kernel choices "gaussian", "epanechnikov", "rectangular", "triangular", "biweight", "cosine", and "optcosine". Should you are unhappy with this function and eager for an extention, take a look at the following papers and associated codes:

"Exact Mean Integrated Squared Error of Higher-Order Kernels" Econometric Theory (2005).
"Bandwidth Selection for Nonparametric Distribution Estimation" unpublished working paper (2004).
"Nonparametric Estimation of Smooth Conditional Distributions" unpublished working paper (2004).
"Interval Forecasts and Parameter Uncertainty" Journal of Econometrics (2006).

http://www.ssc.wisc.edu/~bhansen/progs/progs_np.html