Towards Improving Transparency of Count Data Regression Models for Health Impacts of Air Pollution

In studies on the health impacts of air pollution, regression analysis continues to advance far beyond classical linear regression, which many scientists may have become familiar with in an introductory statistics course. With each new level complexity, less transparent, even analyst working data. This be especially true count data models, where response variable (typically given symbol y) is (i.e., takes values 0, 1, 2, …). such normal distribution (the bell-shaped curve) for residuals differences between observed and predicted by model) no longer applies. Unless care taken correctly specify just how those are distributed, tendency accept untrue hypotheses greatly increased. The aim this paper present a simple histogram (POCH), which, while rarely found environmental literature but presented authoritative statistical texts, can dramatically reduce risk accepting hypotheses. POCH also increase transparency models analysts themselves scientific community general.