YourCast: Time Series Cross-Sectional
Forecasting with Your Assumptions

Federico Girosi and Gary King

Version:0.95

graph

YourCast is (open source and free) software that makes forecasts by running sets of linear regressions together in a variety of sophisticated ways. YourCast avoids the bias that results when stacking datasets from separate cross-sections and assuming constant parameters, and the inefficiency that results from running independent regressions in each cross-section. The models enable you to have different covariates, or the same covariates with different meanings, in each cross-section. You may choose from a wide variety of smoothing techniques, such as assuming that the separate time series regressions in neighboring (or "similar") countries are alike, based on similarites in the coefficients (as in other approaches) or in the values or trends in the expected value of the dependent variable. This approach is advantageous because prior knowledge almost always exists about the dependent variable, and the expected value is always on the same metric even when including explanatory variables that differ in number or meaning in each country. You can also decide whether to smooth over indices that are geographic, grouped continuous variables (such as age groups), time, or interactions among these. For example, you can assume that, unless contradicted by the data, forecasts should be relatively smooth over time, or that the forecast time trends should be similar in adjacent age groups, or even that the differences in time trends between adjacent age groups stay roughly similar as they vary over countries.

The model works with time-series-cross-sectional data but also data for which the time series varies over more than one cross-section such as log-mortality over time by age, country, sex, and cause. The specific notion of "smoothness" or "similarity" used in YourCast is also your choice. The assumptions made by the statistical model are therefore governed your choices, and the sophistication of those assumptions and the degree to which they match empirical reality are, for the most part, limited only by what you may know or are willing to assume rather than arbitrary choices embedded in a mathematical model.

YourCast implements the methods introduced in Federico Girosi and Gary King's book manuscript on Demographic Forecasting, Princeton University Press, forthcoming. The present version is for those familar with R (if you're not, see Zelig); the next version will have more extensive preprocessing to make data input easier, and the version after that will have a GUI so that knowledge of R is unnecessary.