Inferential, non-parametric statistics to assess quality of probabilistic forecast systems

Many statistical forecast systems are available to interested users. In order to be useful for decision-making, these systems must be based on evidence of underlying mechanisms. Once causal connections between the mechanism and their statistical manifestation have been firmly established, the forecasts must also provide some quantitative evidence of `quality’. However, the quality of statistical climate forecast systems (forecast quality) is an ill-defined and frequently misunderstood property. Often, providers and users of such forecast systems are unclear about what ‘quality’ entails and how to measure it, leading to confusion and misinformation. Here we present a generic framework to quantify aspects of forecast quality using an inferential approach to calculate nominal significance levels (p-values) that can be obtained either by directly applying non-parametric statistical tests such as Kruskal-Wallis (KW) or Kolmogorov-Smirnov (KS) or by using Monte-Carlo methods (in the case of forecast skill scores). Once converted to p-values, these forecast quality measures provide a means to objectively evaluate and compare temporal and spatial patterns of forecast quality across datasets and forecast systems. Our analysis demonstrates the importance of providing p-values rather than adopting some arbitrarily chosen significance levels such as p < 0.05 or p < 0.01, which is still common practice. This is illustrated by applying non-parametric tests (such as KW and KS) and skill scoring methods (LEPS and RPSS) to the 5-phase Southern Oscillation Index classification system using historical rainfall data from Australia, The Republic of South Africa and India. The selection of quality measures is solely based on their common use and does not constitute endorsement. We found that non-parametric statistical tests can be adequate proxies for skill measures such as LEPS or RPSS. The framework can be implemented anywhere, regardless of dataset, forecast system or quality measure. Eventually such inferential evidence should be complimented by descriptive statistical methods in order to fully assist in operational risk management.

From inferential statistics to climate knowledge

Climate variability and change are risk factors for climate sensitive activities such as agriculture. Managing these risks requires "climate knowledge", i.e. a sound understanding of causes and consequences of climate variability and knowledge of potential management options that are suitable in light of the climatic risks posed. Often such information about prognostic variables (e.g. yield, rainfall, run-off) is provided in probabilistic terms (e.g. via cumulative distribution functions, CDF), whereby the quantitative assessments of these alternative management options is based on such CDFs. Sound statistical approaches are needed in order to assess whether difference between such CDFs are intrinsic features of systems dynamics or chance events (i.e. quantifying evidences against an appropriate null hypothesis). Statistical procedures that rely on such a hypothesis testing framework are referred to as "inferential statistics" in contrast to descriptive statistics (e.g. mean, median, variance of population samples, skill scores). Here we report on the extension of some of the existing inferential techniques that provides more relevant and adequate information for decision making under uncertainty.

Using harvest statistics to monitor temporal variation in kangaroo density and harvest rate

Management of the commercial harvest of kangaroos relies on quotas set annually as a proportion of regular estimates of population size. Surveys to generate these estimates are expensive and, in the larger states, logistically difficult; a cheaper alternative is desirable. Rainfall is a disappointingly poor predictor of kangaroo rate of increase in many areas, but harvest statistics (sex ratio, carcass weight, skin size and animals shot per unit time) potentially offer cost-effective indirect monitoring of population abundance (and therefore trend) and status (i.e. under-or overharvest). Furthermore, because harvest data are collected continuously and throughout the harvested areas, they offer the promise of more intensive and more representative coverage of harvest areas than aerial surveys do. To be useful, harvest statistics would need to have a close and known relationship with either population size or harvest rate. We assessed this using longterm (11-22 years) data for three kangaroo species (Macropus rufus, M. giganteus and M. fuliginosus) and common wallaroos (M. robustus) across South Australia, New South Wales and Queensland. Regional variation in kangaroo body size, population composition, shooter efficiency and selectivity required separate analyses in different regions. Two approaches were taken. First, monthly harvest statistics were modelled as a function of a number of explanatory variables, including kangaroo density, harvest rate and rainfall. Second, density and harvest rate were modelled as a function of harvest statistics. Both approaches incorporated a correlated error structure. Many but not all regions had relationships with sufficient precision to be useful for indirect monitoring. However, there was no single relationship that could be applied across an entire state or across species. Combined with rainfall-driven population models and applied at a regional level, these relationships could be used to reduce the frequency of aerial surveys without compromising decisions about harvest management.