Statistical approaches to environmental monitoring: Did we teach the wrong things?

Two statistical topics that are frequently 'missed' at the level of an applied statistics course or workshop are presented here, along with examples of their use in natural resource monitoring. The first topic deals with use of correlated observations in calculations of variance estimates for a regional mean, required sample size determination, and confidence intervals. Even if correlation values are known only approximately, one can still obtain information on the effect of correlation on the aforementioned computations. The second topic concerns the use of Bayesian techniques in hypothesis testing. Although many authors have advocated its use, Bayesian analysis can be quite complex. Some Bayesian techniques are translated into graphical form that can be readily used by the reader. Both topics represent areas of statistical expertise that can be explored at a very theoretical level; however, there is enough applied material that merits translation for use by those in natural resource monitoring.

Incidence of exercise-induced asthma in children.

The incidence of exercise-induced asthma (EIA) was studied in 134 asthmatic and 102 nonasthmatic atopic children and compared to that in 56 nonatopic children. Pulmonary function tests measuring forced vital capacity (FVC) and 1-sec forced expiratory volume (FEV1) were performed on each child prior to and serially for 20 min following free running exercise. The incidences of EIA among the asthmatic and atopic nonasthmatic children were 63% and 41%, respectively. This phenomenon is widespread among allergic children and cannot be accurately predicted from the history. A simple and easily performed outpatient procedure is described for the diagnosis of EIA.

The gating currents of sodium channels: pore-population-size effects.

Sodium-channel behavior has been modeled in order to determine the answer to the following question: How large must a population of "on-off" sodium pores be before the inherently random behavior of the individual channels becomes smoothed to yield the expected gating current-conductance relationships which would be predicted from an infinite pore array? Results of this analysis show that for the "opening" situation, an excellent fit was obtained whenever more than about 10 pores were considered. Significant discrepancies were observed in the "closing" situation, however, for pore arrays of 50 or less. Marked hysteresis is apparent in the behavior of small port populations.