Goodness-of-Fit Testing With Discrete "Circular" Data

Tests for goodness-of-fit based on the empirical distribution function are pretty standard fare. Their applicability relies on the Glivenko-Cantelli Theorem.

However, things get a little tricky when the data are discrete (rather than continuous), or when they are "circular" in nature. When the data exhibit both of these characteristics, some really interesting testing issues have to be handled.

A paper that I wrote a short while back on this topic has just been accepted for publication in the Chilean Journal of Statistics. The paper is titled, "Exact Asymptotic Goodness-of-Fit Testing For Discrete Circular Data, With Applications", and it'll be appearing in the 2013 volume of the journal.

You can download  a copy of the paper here.

 

© 2012, David E. Giles

The Likelihood Principle

The so-called "Likelihood Principle" forms the foundation of both classical (frequentist) statistics, as well as Bayesian statistics. So, as an econometrician, whether you rely on Maximum Likelihood estimation and the associated asymptotic tests, or if you prefer to adopt a Bayesian approach to inference, this principle is of fundamental importance to you.

What is this principle? Suppose that x is the value of a (possibly vector-valued) random variable, X, whose density depends on a vector of parameters, θ. Then, the Likelihood Principle states that:

"All the information about θ obtainable from an experiment is contained in the likelihood function for θ given x. Two likelihood functions for θ (from the same or different experiments) contain the same information about θ if they are proportional to one another."  (Berger and Wolpert, 1988, p.19).

Promoting Econometrics

A post today on the "Simply Statistics" blog is titled, "Statistics/Statisticians Need Better Marketing". 

I liked it a lot, and much of the content could be applied to the econometrics community. 

However, one of the suggestions worried me a bit - namely:

"Whenever someone does something with data, we should claim them as a statistician."

I'm not sure I'd like to claim as an econometrician, anyone who does some empirical analysis involving economic data. Goodness knows there's an awful lot of garbage out there! And it's produced by people I wouldn't call econometricians, even if that's how they describe tehmselves!

But maybe I'm just getting old and grumpy.

© 2012, David E. Giles

Videos on Using R

In this post on his blog some months ago, Ethan Fosse drew attention to Anthony Damico's collection of over 90 videos on using the R software environment.

Definitely worth looking at!

© 2012, David E. Giles

International Year of Statistics

2013 will be The International Year of Statistics. The associated website can be found here.

Quoting from the site:

"The International Year of Statistics ("Statistics2013") is a worldwide celebration and recognition of the contributions of statistical science. Through the combined energies of organizations worldwide, Statistics2013 will promote the importance of Statistics to the broader scientific community, business and government data users, the media, policy makers, employers, students, and the general public. 

The goals of Statistics2013 include: 

• increasing public awareness of the power and impact of Statistics on all aspects of society;
• nurturing Statistics as a profession, especially among young people; and
• promoting creativity and development in the sciences of Probability and Statistics"

Various upcoming activities that acknowledge the International Year of Statistics can be found here.

© 2012, David E. Giles

James Durbin

James Durbin has passed away at the age of 89. Jim's numerous contributions to statistics included many that also made him a "household name" in econometrics circles.

There is a short obituary on p.7. of the latest issue of RSS News. A full obituary will follow in a future issue of The Journal of the Royal Statistical Society, Series A.

For some earlier historical material relating to James Durbin in this blog, see the earlier post here.

© 2012, David E. Giles

Beware of Tests for Nonlinear Granger Causality

Standard tests for Granger causality (or, more correctly, Granger non-causality) are conducted under the assumption that we live in a linear world.

I've discussed some of the issues associated with applying such tests in the presence of possibly integrated/cointegrated time-series data previously, here and here.

But can we justify limiting our attention to a linear environment?

Summertime!

It's been a quiet week at the lake - specifically, no internet access! And hence no posts.

I haven't been able to respond to comments and requests either, so please accept my apology for that.

Yes, I know I should be better organized!

Hodrick-Prescott Filter Paper

A while back I posted (here, here, and here) about constructing confidence bands to go with the Hodrick-Prescott filter. Subsequently, I wrote up the material more formally, and that paper is to appear in Applied Economics Letters.

You can find the final version of the paper here.

Hat-tip to my colleague, Graham Voss, for encouraging me to write up the material properly.

Reference

Giles, D. E., 2012. Constructing confidence bands for the Hodrick-Prescott filter. Forthcoming in Applied Economics Letters.

© 2012, David E. Giles

Cleaning up Your Data Files

A recent post on The Data Monkey blog describes a really neat (and free) text editor, called Hex Editor Neo.

If you have large, messy, data files that need cleaning, this looks like the editor for you!

© 2012, David E. Giles