Conditional Exceedance Probabilities

Mason, Simon J.; Galpin, Jacqueline S.; Goddard, Lisa; Graham, Nicholas E.; Rajartnam, Balakanapathy
February 2007
Monthly Weather Review;Feb2007, Vol. 135 Issue 2, p363
Academic Journal
Probabilistic forecasts of variables measured on a categorical or ordinal scale, such as precipitation occurrence or temperatures exceeding a threshold, are typically verified by comparing the relative frequency with which the target event occurs given different levels of forecast confidence. The degree to which this conditional (on the forecast probability) relative frequency of an event corresponds with the actual forecast probabilities is known as reliability, or calibration. Forecast reliability for binary variables can be measured using the Murphy decomposition of the (half) Brier score, and can be presented graphically using reliability and attributes diagrams. For forecasts of variables on continuous scales, however, an alternative measure of reliability is required. The binned probability histogram and the reliability component of the continuous ranked probability score have been proposed as appropriate verification procedures in this context, but are subject to some limitations. A procedure is proposed that is applicable in the context of forecast ensembles and is an extension of the binned probability histogram. Individual ensemble members are treated as estimates of quantiles of the forecast distribution, and the conditional probability that the observed precipitation, for example, exceeds the amount forecast [the conditional exceedance probability (CEP)] is calculated. Generalized linear regression is used to estimate these conditional probabilities. A diagram showing the CEPs for ranked ensemble members is suggested as a useful method for indicating reliability when forecasts are on a continuous scale, and various statistical tests are suggested for quantifying the reliability.


Related Articles

  • Complete Convergence for Weighted Sums of Sequences of Negatively Dependent Random Variables. Qunying Wu // Journal of Probability & Statistics;2011, p1 

    Applying to the moment inequality of negatively dependent random variables the complete convergence for weighted sums of sequences of negatively dependent random variables is discussed. As a result, complete convergence theorems for negatively dependent sequences of random variables are extended.

  • A Comparative Analysis of the Value of Information in a Continuous Time Market Model with Partial Information: The Cases of Log-Utility and CRRA. Zhaojun Yang; Ewald, Christian-Oliver; Wen-Kai Wang // Journal of Probability & Statistics;2011, p1 

    We study the question what value an agent in a generalized Black-Scholes model with partial information attributes to the complementary information. To do this, we study the utility maximization problems from terminal wealth for the two cases partial information and full information. We assume...

  • The geometrical interpretation of statistical tests in multivariate linear regression. Langsrud, Øyvind // Statistical Papers;Jan2004, Vol. 45 Issue 1, p111 

    A geometrical interpretation of the classical tests of the relation between two sets of variables is presented. One of the variable sets may be considered as fixed and then we have a multivariate regression model. When the Wilks' lambda distribution is viewed geometrically it is obvious that the...

  • Bayesian Inference on the Shape Parameter and Future Observation of Exponentiated Family of Distributions. Dey, Sanku; Maiti, Sudhansu S. // Journal of Probability & Statistics;2011, p1 

    The Bayes estimators of the shape parameter of exponentiated family of distributions have been derived by considering extension of Jeffreys' noninformative as well as conjugate priors under different scale-invariant loss functions, namely, weighted quadratic loss function, squared-log error loss...

  • Regularized Logistic Models for Probabilistic Forecasting and Diagnostics. Bröcker, Jochen // Monthly Weather Review;Feb2010, Vol. 138 Issue 2, p592 

    Logistic models are studied as a tool to convert dynamical forecast information (deterministic and ensemble) into probability forecasts. A logistic model is obtained by setting the logarithmic odds ratio equal to a linear combination of the inputs. As with any statistical model, logistic models...

  • Identification of models using failure rate and mean residual life of doubly truncated random variables. Sankaran, P. G.; Sunoj, S. M. // Statistical Papers;Jan2004, Vol. 45 Issue 1, p97 

    In this paper, we study the relationship between the failure rate and the mean residual life of doubly truncated random variables. Accordingly, we develop characterizations for exponential, Pareto II and beta distributions. Further, we generalize the identities for the Pearson and the...

  • Analysis of the fiber length dependence of its strength by using the weakest-link approach 1. A family of weakest-link distribution functions. Paramonov, Yu.; Andersons, J. // Mechanics of Composite Materials;Sep2008, Vol. 44 Issue 5, p479 

    This paper presents a summary and further development of the ideas proposed in the previous papers of the authors, which were dedicated to investigating the fiber scale effect (strength-length relation). In the first part of the paper, some theoretical aspects of the problem are considered; in...

  • The size of random fragmentation trees. Janson, Svante; Neininger, Ralph // Probability Theory & Related Fields;Nov2008, Vol. 142 Issue 3/4, p399 

    We consider the random fragmentation process introduced by Kolmogorov, where a particle having some mass is broken into pieces and the mass is distributed among the pieces at random in such a way that the proportions of the mass shared among different daughters are specified by some given...

  • Asymptotic distribution of the sample average value-at-risk. Stoyanov, Stoyan V.; Rachev, Svetlozar T. // Journal of Computational Analysis & Applications;Oct2008, Vol. 10 Issue 4, p465 

    In this paper, we prove a result for the asymptotic distribution of the sample average value-at-risk (AVaR) under certain regularity assumptions. The asymptotic distribution can be used to derive asymptotic confidence intervals when AVaRϵ(X) is calculated by the Monte Carlo method which is...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics