Statistical methods for hazards and health.

Abstract

The objective of this article is to document the need for further development of statistical methodology, training of more statisticians and improved communication between statisticians and the many other disciplines engaged in environmental research. Discussion of adequacy of the current statistical methodology requires the use of examples, which will hopefully not be offensive to the authors. Reference is made to recent developments and areas of unsolved problems delineated in three broad areas: enumeration data and adjusted rates; time series; and multiple regression.A brief outline of the ideas behind current methods of analyzing discrete data is followed by a demonstration of their utility using an example of the effects of exposure, sex, and education on bronchitis rates. Examples are listed of the ubiquity of the time component when relating pollution effects to each other and to health effects. An artificial example is used to emphasize the effects of time-dependent autocorrelations, trends, and cycles. References are given to a variety of new developments in time-series analysis.Discussion of the pitfalls in multiple regression analysis, and possible alternative approaches is largely based on two recent reviews and includes references to recent developments of robust techniques.

Time-Series Studies of Particulate Matter

“…In 1971, the EPA established a 24-h average NAAQS for TSP of 260 µg/m 3 and an annual average of 75 µg/m 3 (38). In 1987, the EPA replaced the TSP standards with requirements for PM 10 : a 24-h average of 150 µg/m 3 and an annual average of 50 µg/m 3 averaged over three years (39). This change reflected an evolving understanding of the dosimetry of particles in the respiratory tract and improving measurement capability.…”

“…A Washington D.C. Circuit Court found that PM 10 is not an appropriate indicator for coarse particles and that the regulation of both PM 10 and PM 2.5 constitutes double regulation because the matter in PM 2.5 would also be a part of PM 10. The EPA recently called for a riskanalysis plan for PM 10-2.5 (the "coarse fraction" between 2.5 µm and 10 µm) and PM 2.5 and may revise the NAAQS to include a standard for the coarse fraction rather than PM 10 .…”

“…As such high levels became less frequent, more formal time-series analysis was recognized as a useful tool for the study of air pollution and health (10). Many of these studies utilized growing public databases on health outcomes, weather variables, and pollution.…”

“…Thus, the key health implications of results remain unchanged (22). Reanalysis of the National Morbidity, Mortality, and Air Pollution Study (NMMAPS) work indicates that daily mortality from all causes is increased 0.21% per 10-µg/m 3 increase in PM 10 , rather than the original estimate of 0.4% generated using S-plus default parameters (61). Other research was reanalyzed as well, and results are summarized in a Health Effects Institute report (61).…”

Estimation of reproduction number and non stationary spectral analysis of dengue epidemic

“…Temperature and rain fall plays key role in its life cycle such as its breeding, biting frequency and extrinsic incubation period [22]. Spectral analysis methods such as cross correlations and Fourier analysis has been used to study analyze correlates of epidemiological and environmental variables, for example to understand aggravation of asthma symptoms and daily minimum temperature [5], air pollution and mortality [16], and large-scale climatic oscillations and cholera epidemic [30]. In this work, we analyzed the cross correlation of Dengue with rainfall and temperature, and found that there is a lag of 9 weeks (20 weeks) between the peak of rainfall (average temperature) and peak of the Dengue incidences.…”