M. Analysing Data of Childhood Acute Lymphoid Leukaemia.pdfVIP

Analysing Data of Childhood Acute Lymphoid Leukaemia by Seasonal Time Series Methods Maria Fazekas (University of Debrecen, Hungary kiss@thor.agr.unideb.hu) Abstract: We examined the periodicity of the childhood leukaemia in Hungary using seasonal decomposition time series. Between 1988 and 2000 the number of annually diagnosed leukaemia (incidence) was analysed. The time series of the number of patients between the age of 0 and 18 years and the data series divided at the median were analysed. From the time series the seasonal components, trends, the seasonally adjusted series, the moving averages and the data series of the random components were examined. The seasonal components of the dates of diagnosis revealed that a higher percent of the peaks fell within the winter months than in the other seasons. This proves the seasonal occurrence of the childhood leukaemia in Hungary. These data seem to highlight the role of the environmental effects (viral infections, epidemics, etc.) on the onset of the disease. Keywords: time series analysis, seasonal decomposition time series method, acute childhood lymphoid leukaemia Category: G 1 Introduction The method of seasonal time series analysis can be used in various fields of the medicine. With such time series one can detect the periodic trend of the occurrence of a certain disease [Barnett-Dobson, 2004], [Cani et al., 2001], [Fleming et al. 2000], [Gallerani et al., 2004], [Oberg et al., 2000], [Pereira, 2004], [Saynajakangas et al., 2001]. Among other diseases, the seasonal periodicity of the childhood lymphoid leukaemia was also analysed using statistical methods [Cohen, 1987], [Harris-Harrel, 1987], [Meltzer et al., 1996], [Sorenson-Pedersen, 2001], [Vienna-Polan, 1976]. The importance of this theme was indicated that in the last few years in many international publications were discussed with the seasonal variations of childhood leukemia/lymphoma and the acute lymphoblastic leuk