Regression Analysis or Monte Carlo Methods

[Mini-Dow]

Hello,

I'm planning on taking either Linear Regression Analysis or Markov Chain Monte Carlo Methods (MCMC) next semester, and am wondering which one of the two is more frequently used in an MFE curriculum. Thanks.

 

[Andy Nguyen]

Aside from the course title, a syllabus/book used would be more helpful.

 

[Mini-Dow]

Aside from the course title, a syllabus/book used would be more helpful.

Linear Regression course description:
Theory of linear models, with emphasis on matrix approach to linear regression. Topics include model fitting, extra sums of squares principle, testing general linear hypothesis in regression, inference procedures, Gauss/Markov theorem, examination of residuals, principle component regression, stepwise procedures.

Monte Carlo Methods course description:
Introduction to Markov chain Monte Carlo (MCMC) algorithms for scientific computing. Generation of random numbers from specific distribution. Rejection and importance sampling and its role in MCMC. Markov chain theory and convergence properties. Metropolois and Gibbs sampling algorithms. Extensions as simulated tempering. Theoretical understanding of methods and their implementation in concrete computational problems.

For Linear Regression course, textbook used is Intro Regression Modeling by Bovas Abraham
For Monte Carlo Methods, textbook used is Introducing Monte Carlo Methods With R by Christian Robert and George Casella

I assume Monte Carlo Methods has more advanced techniques and I should focus on the more elementary Regression Analysis?

 

[Jacek Podlewski]

Regression Analysis is definitely more "fundamental", however I'd probably take Monte Carlo. The course looks more advanced indeed, but there's a ton of good books about regression and it is IMHO much easier to learn by yourself assuming some decent background in probability & stats. Not to mention the importance of MC in financial derivatives pricing