The use of Poisson regression in the sociological study of suicide

This paper explains how Poisson regression can be used in studies in which the dependent variable describes the number of occurrences of some rare event such as suicide. After pointing out why ordinary linear regression is inappropriate for treating dependent variables of this sort, we go on to present the basic Poisson regression model and show how it fits in the broad class of generalized linear models. Then we turn to discussing a major problem of Poisson regression known as overdispersion and suggest possible solutions, including the correction of standard errors and negative binomial regression. The paper ends with a detailed empirical example, drawn from our own research on suicide.

Negative impact of climate change on the distribution of some conifers

A climate envelope model was run on the distribution of four coniferous species (European silver fir, European larch, Norway spruce, and Swiss pine). The model was supported by EUFORGEN area database, ArcGIS 10 and PAST software, andREMO climate model. Prediction periods were 2011-40 and 2041-70.

The paradox of the binomial Ixodes ricinus activity and the observed unimodal Lyme borreliosis season in Hungary

The change of ambient temperature plays a key role in determining the run of the annual Lyme season. Our aim was to explain the apparent contradiction between the annual unimodal Lyme borreliosis incidence and the bimodal Ixodes ricinus tick activity run – both observed in Hungary – by distinguishing the temperaturedependent seasonal human and tick activity, the temperature-independent factors, and the multiplicative effect of human outdoor activity in summer holiday, using data from Hungary in the period of 1998–2012. This separation was verified by modeling the Lyme incidence based on the separated factors, and comparing the run of the observed and modeled incidence. We demonstrated the bimodality of tick season by using the originally unimodal Lyme incidence data. To model the outdoor human activity, the amount of camping guest nights was used, which showed an irregular run from mid-June to September. The human outdoor activity showed a similar exponential correlation with ambient temperature to that what the relative incidence did. It was proved that summer holiday has great influence on Lyme incidence.

The paradox of the binomial Ixodes ricinus activity and the observed unimodal Lyme borreliosis season in Hungary

The change of ambient temperature plays a key role in determining the run of the annual Lyme season. Our aim was to explain the apparent contradiction between the annual unimodal Lyme borreliosis incidence and the bimodal Ixodes ricinus tick activity run – both observed in Hungary – by distinguishing the temperaturedependent seasonal human and tick activity, the temperature-independent factors, and the multiplicative effect of human outdoor activity in summer holiday, using data from Hungary in the period of 1998–2012. This separation was verified by modeling the Lyme incidence based on the separated factors, and comparing the run of the observed and modeled incidence. We demonstrated the bimodality of tick season by using the originally unimodal Lyme incidence data. To model the outdoor human activity, the amount of camping guest nights was used, which showed an irregular run from mid-June to September. The human outdoor activity showed a similar exponential correlation with ambient temperature to that what the relative incidence did. It was proved that summer holiday has great influence on Lyme incidence.