I am a statistician, but I have worked in a department of predominantly econometricians for the past 17 years. It is a little like an Australian visiting the United States. Initially, it seems that we talk the same language, do the same sorts of things, and have a very similar culture. But the longer you stay there, the more you realise there are differences that run deep and affect the way you see the world.
Rolling forecasts are commonly used to compare time series models. Here are a few of the ways they can be computed using R. I will use ARIMA models as a vehicle of illustration, but the code can easily be adapted to other univariate time series models. (more…)
Every year, the International Institute of Forecasters in conjunction with SAS offer some small grants to help promote research in forecasting. There are two $5000 grants per year for research on forecasting methodology and applications. This year, applications close on 30 September 2014. More details are given here.
Information about past SAS-IIF awards is given on the IIF website. It is interesting to see the range of topics covered. Here are the winning projects in the last two years:
- Jeffrey Stonebraker: “Probabilistic Forecasting of the Global Demand for the Treatment of Hemophilia B.”
- Yongchen (Herbert) Zhao: “Robust Real-Time Automated Forecast Combination in SAS: Development of a SAS Procedure and a Comprehensive Evaluation of Recently Developed Combination Methods.”
- Zoe Theocharis, Nigel Harvey, Leonard Smith: “Improving judgmental input to hurricane forecasts in the insurance and reinsurance sector.”
- Elena-Ivona Dumitrescu, Janine Christine Balter, Peter Reinhard Hansen: “Forecasting Exchange Rate Volatility: Multivariate Realized GARCH Framework.”
- Yorghos Tripodis: “Forecasting the Cognitive Status in an Aging Population.”
Last week my research group discussed Hal Varian’s interesting new paper on “Big data: new tricks for econometrics”, Journal of Economic Perspectives, 28(2): 3–28.
It’s a nice introduction to trees, bagging and forests, plus a very brief entrée to the LASSO and the elastic net, and to slab and spike regression. Not enough to be able to use them, but ok if you’ve no idea what they are. (more…)
With the latest version of the hts package for R, it is now possible to specify rather complicated grouping structures relatively easily.
All aggregation structures can be represented as hierarchies or as cross-products of hierarchies. For example, a hierarchical time series may be based on geography: country, state, region, store. Often there is also a separate product hierarchy: product groups, product types, packet size. Forecasts of all the different types of aggregation are required; e.g., product type A within region X. The aggregation structure is a cross-product of the two hierarchies.
This framework includes even apparently non-hierarchical data: consider the simple case of a time series of deaths split by sex and state. We can consider sex and state as two very simple hierarchies with only one level each. Then we wish to forecast the aggregates of all combinations of the two hierarchies.
Any number of separate hierarchies can be combined in this way. Non-hierarchical factors such as sex can be treated as single-level hierarchies. (more…)
For the next month I am travelling in Europe and will be giving the following talks.
I’m about to head off on a speaking tour to Europe (more on that in another post) and one of my hosts has asked for my powerpoint slides so they can print them. They have made two false assumptions: (1) that I use powerpoint; (2) that my slides are static so they can be printed.
Instead, I produced a cut-down version of my beamer slides, leaving out some of the animations and other features that will not print easily. Then I produced a pdf file with several slides per page. (more…)
I’m tired of reading about tests for structural breaks and here’s why.
A structural break occurs when we see a sudden change in a time series or a relationship between two time series. Econometricians love papers on structural breaks, and apparently believe in them. Personally, I tend to take a different view of the world. I think a more realistic view is that most things change slowly over time, and only occasionally with sudden discontinuous change. (more…)
Last week, my research group discussed Galit Shmueli’s paper “To explain or to predict?”, Statistical Science, 25(3), 289–310. (See her website for further materials.) This is a paper everyone doing statistics and econometrics should read as it helps to clarify a distinction that is often blurred. In the discussion, the following issues were covered amongst other things.
- The AIC is better suited to model selection for prediction as it is asymptotically equivalent to leave-one-out cross-validation in regression, or one-step-cross-validation in time series. On the other hand, it might be argued that the BIC is better suited to model selection for explanation, as it is consistent.
- P-values are associated with explanation, not prediction. It makes little sense to use p-values to determine the variables in a model that is being used for prediction. (There are problems in using p-values for variable selection in any context, but that is a different issue.)
- Multicollinearity has a very different impact if your goal is prediction from when your goal is estimation. When predicting, multicollinearity is not really a problem provided the values of your predictors lie within the hyper-region of the predictors used when estimating the model.
- An ARIMA model has no explanatory use, but is great at short-term prediction.
- How to handle missing values in regression is different in a predictive context compared to an explanatory context. For example, when building an explanatory model, we could just use all the data for which we have complete observations (assuming there is no systematic nature to the missingness). But when predicting, you need to be able to predict using whatever data you have. So you might have to build several models, with different numbers of predictors, to allow for different variables being missing.
- Many statistics and econometrics textbooks fail to observe these distinctions. In fact, a lot of statisticians and econometricians are trained only in the explanation paradigm, with prediction an afterthought. That is unfortunate as most applied work these days requires predictive modelling, rather than explanatory modelling.