There is extensive literature describing the effect of season on mortality rates, especially in cardiovascular and respiratory disease. This study compares latitude with the extent of seasonal variation of monthly deaths from all causes. In developed countries, there is a peak of deaths in winter and a trough in summer. Monthly numbers of deaths were established in 89 countries in the Northern and Southern Hemisphere. Using cosinor analysis, the extent of seasonal variation (amplitude) was established and correlated with latitude. The amplitude of seasonality was greatest in mid-latitude around 35 degrees, but low or absent near the equator and subpolar regions. The amplitude can differ at the same latitude. The weather in equatorial regions and in habitations near the Arctic Circle is very different, but death has a similar seasonal rhythm. The purpose is to record this epidemiological finding even though no simple explanation is provided. Weather alone cannot explain it, and it is possible that day length (photoperiod) has an important, but complex, underlying role.
Variations in birth frequencies have an impact on activity planning in maternity wards. Previous studies of this phenomenon have commonly included elective births. A Danish study of spontaneous births found that birth frequencies were well modelled by a Poisson process. Somewhat unexpectedly, there were also weekly variations in the frequency of spontaneous births. Another study claimed that birth frequencies follow the Benford distribution. Our objective was to test these results.
We analysed 50,017 spontaneous births at Akershus University Hospital in the period 1999-2014. To investigate the Poisson distribution of these births, we plotted their variance over a sliding average. We specified various Poisson regression models, with the number of births on a given day as the outcome variable. The explanatory variables included various combinations of years, months, days of the week and the digit sum of the date.
The relationship between the variance and the average fits well with an underlying Poisson process. A Benford distribution was disproved by a goodness-of-fit test (p
The purpose of this article is to draw attention to the possible need for inclusion of interaction effects between regions and age groups in mapping studies. We propose a simple model for including such an interaction in order to develop a test for its significance. The assumption of an absence of such interaction effects is a helpful simplifying one. The measure of relative risk related to a particular region becomes easily and neatly summarized. Indeed, such a test seems warranted because it is anticipated that the simple model, which ignores such interaction, as is in common use, may at times be adequate. The test proposed is a score test and hence only requires fitting the simpler model. We illustrate our approaches using mortality data from British Columbia, Canada, over the 5-year period 1985-1989. For this data, the interaction effect between age groups and regions is quite large and significant.
Road accident counts are influenced by random variation as well as by various systematic, causal factors. To study these issues, a four-country, segmented data base has been compiled, each segment consisting of monthly accident counts, along with candidate explanatory factors, in the various counties (provinces) of Denmark, Finland, Norway, or Sweden. Using a generalized Poisson regression model, we are able to decompose the variation in accident counts into parts attributable to randomness, exposure, weather, daylight, or changing reporting routines and speed limits. To this purpose, a set of specialized goodness-of-fit measures have been developed, taking explicit account of the inevitable amount of random variation that would be present in any set of accident counts, no matter how well known the accident generating Poisson process. Pure randomness is seen to "explain" a major part of the variation in smaller accident counts (e.g. fatal accidents per county per month), while exposure is the dominant systematic determinant. The relationship between exposure and injury accidents appears to be almost proportional, while it is less than proportional in the case of fatal accidents or death victims. Together, randomness and exposure account for 80% to 90% of the observable variation in our data sets. A surprisingly large share of the variation in road casualty counts is thus explicable in terms of factors not ordinarily within the realm of traffic safety policy. In view of this observation, it may seem unlikely that very substantial reductions in the accident toll can be achieved without a decrease in the one most important systematic determinant: the traffic volume.
We investigated whether the installation of a suicide prevention barrier on Jacques-Cartier Bridge led to displacement of suicides to other jumping sites on Montréal Island and Montérégie, Québec, the 2 regions it connects.
Suicides on Montréal Island and Montérégie were extracted from chief coroners' records. We used Poisson regression to assess changes in annual suicide rates by jumping from Jacques-Cartier Bridge and from other bridges and other sites and by other methods before (1990-June 2004) and after (2005-2009) installation of the barrier.
Suicide rates by jumping from Jacques-Cartier Bridge decreased after installation of the barrier (incidence rate ratio [IRR] = 0.24; 95% confidence interval [CI] = 0.13, 0.43), which persisted when all bridges (IRR = 0.39; 95% CI = 0.27, 0.55) and all jumping sites (IRR = 0.66; 95% CI = 0.54, 0.80) in the regions were considered.
Little or no displacement to other jumping sites may occur after installation of a barrier at an iconic site such as Jacques-Cartier Bridge. A barrier's design is important to its effectiveness and should be considered for new bridges with the potential to become symbolic suicide sites.
Using the Swedish Family-Cancer Database covering over 11.5 million individuals, estimated relative risks (RRs) for colorectal adenoma were using Poisson's regression. The RR of colorectal adenoma was found to be increased among first-degree relatives of patients with colorectal cancer (2.72; 95% confidence interval=2.46-3.00) and among the offspring and siblings of patients with endometrial and prostate cancers. We also found an increased risk of colorectal adenoma for the offspring of individuals with stomach cancer and leukaemia, and for siblings of those with pancreatic cancer and multiple myeloma. Our results suggest that colorectal adenoma may share a genetic aetiology with cancer even at extracolorectal sites. Increases of colorectal adenoma in families affected by prostate cancer and acute leukaemia cannot be attributed to known cancer syndromes, although the play of chance cannot be excluded.
This paper demonstrates the application of full Bayes multivariate linear intervention models to evaluate the impact of the Signal Head Upgrade Program in the City of Surrey, British Columbia. The program was implemented by the Insurance Corporation of British Columbia (ICBC) and is aimed at reducing the number of collisions by improving signal visibility. Specific improvements include: upgrading signal lens size, installing new backplates, adding reflective tapes to existing backplates, and installing additional signal heads. The evaluation utilizes full Bayes multivariate linear intervention models with a multiple regression links representing time, treatment, and interaction effects as well as the traffic volumes effects. The models were utilized to determine the safety impacts of the program on each combination of collision severity and collision time of occurrence (i.e. severe/day-time, severe/night-time, PDO/day-time, PDO/night-time) in the City of Surrey. The results indicated the effectiveness of the program in improving the safety of the treated intersections as there were reductions in all types of collisions at the treated sites after the improvement. However, such reductions were statistically significant only for night-time severe collisions and day-time PDO collisions.
The aim of this study was to examine whether shared and open-plan offices are associated with more days of sickness absence than cellular offices.
The analysis was based on a national survey of Danish inhabitants between 18-59 years of age (response rate 62%), and the study population consisted of the 2403 employees that reported working in offices. The different types of offices were characterized according to self-reported number of occupants in the space. The log-linear Poisson model was used to model the number of self-reported sickness absence days depending on the type of office; the analysis was adjusted for age, gender, socioeconomic status, body mass index, alcohol consumption, smoking habits, and physical activity during leisure time.
Sickness absence was significantly related to having a greater number of occupants in the office (P6 persons) had 62% more days of sickness absence (RR 1.62, 95% CI 1.30-2.02).
Occupants sharing an office and occupants in open-plan offices (>6 occupants) had significantly more days of sickness absence than occupants in cellular offices.
Comment In: Scand J Work Environ Health. 2011 Sep;37(5):359-6221814705