Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Business
Scoring Rules And Decision Analysis Education, J. Eric Bickel
Scoring Rules And Decision Analysis Education, J. Eric Bickel
Eric Bickel
Experiential learning is perhaps the most effective way to teach. One example is the scoring procedure used for exams in some decision analysis programs. Under this grading scheme, students take a multiple-choice exam, but rather than simply marking which answer they think is correct, they must assign a probability to each possible answer. The exam is then scored with a special scoring rule, under which students’ best strategy is to avoid guessing and instead assign their true beliefs. Such a scoring function is known as a strictly proper scoring rule. In this paper, we discuss several different scoring rules and …
Discretization, Simulation, And Swanson’S (Inaccurate) Mean, J. Eric Bickel
Discretization, Simulation, And Swanson’S (Inaccurate) Mean, J. Eric Bickel
Eric Bickel
Swanson’s Mean (SM) is heavily used within the oil and gas industry to approximate continuous probability distributions such as the lognormal. In this paper, we document the errors induced by this practice, which, as we show, has no theoretical justification for any distribution other than the normal. In parallel, we review methods to discretize continuous distributions and compare these methods to Monte Carlo simulation. We demonstrate that the best discretization methods have an accuracy equivalent to that of tens of thousands of Monte Carlo trials.
Comparing Nws Pop Forecasts To Third-Party Providers, J. Eric Bickel, Eric Floehr, Seong Dae Kim
Comparing Nws Pop Forecasts To Third-Party Providers, J. Eric Bickel, Eric Floehr, Seong Dae Kim
Eric Bickel
In this paper, the authors verify probability of precipitation (PoP) forecasts provided by the National Weather Service (NWS), The Weather Channel (TWC), and CustomWeather (CW). The n-day-ahead forecasts, where n ranges from 1 to 3 for the NWS, from 1 to 9 for TWC, and from 1 to 14 for CW, are analyzed. The dataset includes almost 13 million PoP forecasts, or about 500 000 PoPs per provider per day of lead time. Data were collected over a 2-yr period (1 November 2008–31 October 2010) at 734 observation stations across the contiguous United States. In addition to verifying these PoP …