Tactical approaches are often chosen based on the best cumulative return which implicitly incorporates significant hindsight bias. Just because an approach dominates for a period of time does not indicate that it will be the best approach. ...

Quantifying the success of government policies is clearly important. Randomized control trials, like those conducted by drug companies, are often described as the ‘gold-standard’ for policy evaluation. Under these, a policy is implemented in/to one area/group (treatment), but not in/to another (control). The difference in outcomes between the two areas or groups represents the effectiveness

I’ve had a few emails lately about forecast evaluation and estimation criteria. Here is one I received today, along with some comments. I have a rather simple question regarding the use of MSE as opposed to MAD and MAPE. If the parameters of a time series model are estimated by minimizing MSE, why do we

The jobs Within the New Zealand Ministry of Business, Innovation and Employment, the Sector Trends team has recently secured resourcing for additional analysts on a range of statistical programmes. That’s the team that I usually manage, although for the next few months I’m doing a stint on a similar team, different topics. The formal details and position descriptions...

Differential privacy was originally developed to facilitate secure analysis over sensitive data, with mixed success. It’s back in the news again now, with exciting results from Cynthia Dwork, et. al. (see references at the end of the article) that apply results from differential privacy to machine learning. In this article we’ll work through the definition … Continue reading...

Statisticians often need to integrate some function with respect to the multivariate normal (Gaussian) distribution, for example, to compute the standard error of a statistic, or the likelihood function in of a mixed effects model. In many (most?) useful cases, these integrals are intractable, and must be approximated using computational methods. Monte-Carlo integration is one

Authors: John Mount (more articles) and Nina Zumel (more articles). Our four part article series collected into one piece. Part 1: The problem Part 2: In-training set measures Part 3: Out of sample procedures Part 4: Cross-validation techniques “Essentially, all models are wrong, but some are useful.” George Box Here’s a caricature of a data … Continue reading...