nep-for New Economics Papers
on Forecasting
Issue of 2016‒08‒21
four papers chosen by
Rob J Hyndman
Monash University

  1. A simple benchmark for mesothelioma projection for Great Britain By Bent Nielsen; María Dolores Martínez-Miranda; Jens Perch Nielsen
  2. Approximating fixed-horizon forecasts using fixed-event forecasts By Knüppel, Malte; Vladu, Andreea L.
  3. The economic value of seasonal forecasts stochastic economywide analysis for East Africa By Rodrigues, Joao; Thurlow, James; Landman, Willem; Ringler, Claudia; Robertson, Richard D.; Zhu, Tingju
  4. The Total Fertility Rate in Germany until 2040 - A Stochastic Principal Components Projection based on Age-specific Fertility Rates By Vanella, Patrizio

  1. By: Bent Nielsen (Nuffield College, Oxford); María Dolores Martínez-Miranda (Department of Statistics and Operations Research, University of Granada, Granada, Spain); Jens Perch Nielsen (Cass Business School, London)
    Abstract: Background: It is of considerable interest to forecast the future burden of mesothelioma mortality. Data on deaths are available, whereas no measure of asbestos exposure is available. Methods. We compare two Poisson models: a response-only model with an age-cohort specification and a multinomial model with epidemiologically motivated frequencies. Results. The response-only model has 5% higher peak mortality than the dose-response model.The former performs slightly better in out-of-sample comparison. Conclusion. Mortality is predicted to peak at about 2100 deaths around 2017 among males in cohorts until 1966 and below 90 years of age. The response-only model is a simple benchmark that forecasts just as well as more complicated models.
    Date: 2016–06–06
  2. By: Knüppel, Malte; Vladu, Andreea L.
    Abstract: In recent years, survey-based measures of expectations and disagreement have received increasing attention in economic research. Many forecast surveys ask their participants for fixed-event forecasts. Since fixed-event forecasts have seasonal properties, researchers often use an ad-hoc approach in order to approximate fixed-horizon forecasts using fixed-event forecasts. In this work, we derive an optimal approximation by minimizing the mean-squared approximation error. Like the approximation based on the ad-hoc approach, our approximation is constructed as a weighted sum of the fixed-event forecasts, with easily computable weights. The optimal weights tend to differ substantially from those of the ad-hoc approach. In an empirical application, it turns out that the gains from using optimal instead of ad-hoc weights are very pronounced. While our work focusses on the approximation of fixedhorizon forecasts by fixed-event forecasts, the proposed approximation method is very flexible. The forecast to be approximated as well as the information employed by the approximation can be any linear function of the underlying high-frequency variable. In contrast to the ad-hoc approach, the proposed approximation method can make use of more than two such informationcontaining functions.
    Keywords: survey expectations,forecast disagreement
    JEL: C53 E37
    Date: 2016
  3. By: Rodrigues, Joao; Thurlow, James; Landman, Willem; Ringler, Claudia; Robertson, Richard D.; Zhu, Tingju
    Abstract: There is growing interest within the climate change and development community in using seasonal forecast information to reduce the losses to agriculture resulting from climate variability, especially within food-insecure countries. However, forecast systems are expensive to establish and maintain, and therefore gauging the potential economic return to investments in forecast systems is crucial. Most studies that evaluate seasonal forecasts focus on developed countries and/or overlook agriculture’s economywide linkages. Yet forecasts may be more valuable in developing regions such as East Africa, where climate is variable and agriculture has macroeconomic importance. We use computable general equilibrium and process-based crop models to estimate the potential economywide value of national seasonal forecast systems in Kenya, Malawi, Mozambique, Tanzania, and Zambia. Stochastic seasonal simulations produce value distributions for forecasts of varying accuracy and varying levels of farm coverage. A timely and accurate forecast adopted by all farmers generates average regional income gains of US$113 million per year. Gains are much higher during extreme climate events and are generally pro-poor. The forecast value falls when forecast skill and farm coverage decline. National economic and trading structures, including the importance of agricultural exports, are found to be major determinants of forecast value. Economywide approaches are therefore needed to complement farm-level analysis when evaluating forecast systems in low-income agrarian economies.
    Keywords: EAST AFRICA, AFRICA SOUTH OF SAHARA, AFRICA, forecasting, climate change, modeling, economic value, mathematical models, general equlibrium, seasonal forecasts, stochastic modeling, D58 Computable and Other Applied General Equilibrium Models, Q15 Land Ownership and Tenure, Land Reform, Land Use, Irrigation, Agriculture and Environment, Q54 Climate,
    Date: 2016
  4. By: Vanella, Patrizio
    Abstract: Demographic change is one of the greatest challenges faced by Germany as well as a large part of Europe today. One of the main drivers of this change is the low fertility level, often referred to as the Total Fertility Rate (TFR), since the early 1970s. Therefore, on the one hand, while the total population is expected to decline, on the other hand, the relative share of the elderly in the total population is expected to increase. This poses a great challenge for the society in a wide range of aspects, most notably in the statutory pension fund. Therefore, it is important to gain an understanding of the future demographic development, in our case, the course of the TFR. Official forecasts often assume that the TFR will remain at a low level of 1.4 in the long run, which was already proven wrong in the publication of the 2014 data, which shows a TFR of 1.47. However, separate analysis of age-specific fertility lead to expected increases of the future TFR. This study presents a stochastic projection of the TFR based on econometric-statistical modeling of age-specific fertility rates over principal components. Simulation techniques not only generate the expected future TFR until the year 2040, but also provide point-wise prediction intervals which cover the future TFR with a probability of 95\% annually based on the current data set. The age-specific structure of the modeling procedure gives a detailed insight of the future development of the reproductive behavior for women in Germany, and therefore, is very informative with regard to possible political intervention with the scope of increasing the TFR. Moreover, the flexible structure of the model allows more sophisticated estimations of future outcome of certain political measures.
    Keywords: Fertility Projection; Applied Principal Components Analysis; Applied Time Series Analysis
    JEL: C53 J11 J13
    Date: 2016–08

This nep-for issue is ©2016 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.