Edwards Test Research Articles

A Class of Multiplicity Adjusted Tests for Spatial Clustering Based on Case–Control Point Data

A class of tests with quadratic forms for detecting spatial clustering of health events based on case-control point data is proposed. It includes Cuzick and Edwards's test statistic (1990, Journal of the Royal Statistical Society, Series B 52, 73-104). Although they used the property of asymptotic normality of the test statistic, we show that such an approximation is generally poor for moderately large sample sizes. Instead, we suggest a central chi-square distribution as a better approximation to the asymptotic distribution of the test statistic. Furthermore, not only to estimate the optimal value of the unknown parameter on the scale of cluster but also to adjust for multiple testing due to repeating the procedure by changing the parameter value, we propose the minimum of the profile p-value of the test statistic for the parameter as an integrated test statistic. We also provide a statistic to estimate the areas or cases which make large contributions to significant clustering. The proposed methods are illustrated with a data set concerning the locations of cases of childhood leukemia and lymphoma and another on early medieval grave site locations consisting of affected and nonaffected grave sites.

Does the time of diagnosis of Type 2 diabetes have a seasonal variation?

AbstractThis prospective, observational study from 1987 to 1990 inclusive, set in hospital diabetes clinics in Leicester City, England (population 287,000), sought to establish whether or not Type 2 diabetes has a seasonal variation in incidence. The dates of diagnosis of 833 newly diagnosed Type 2 diabetic patients were recorded and total monthly incidence over the four year period calculated. Seasonal incidence was assessed by the Edward's test and the test for uniformity on a circle. No seasonal variation in the incidence of Type 2 diabetes was demonstrated, X2=4.32, p=0.11 and X2=3.32, p=0.19 respectively. These findings suggest that, unlike Type 1 diabetes, seasonality plays no significant role in the presentation of Type 2 diabetes. No increase in health care provision is required to cope with seasonal variation in Type 2, unlike that for Type 1 diabetes.

A circadian distribution to febrile episodes in neutropenic patients.

Four-hourly temperature charts relating to 63 febrile neutropenic episodes in 32 patients were assessed for a circadian distribution to the onset of fever (> 37.5 degrees C) using the Edward's test. A highly significant distribution was found with the maximum incidence of febrile events between the hours of 5 p.m. and midnight (acrophase 9.30 p.m.). Patients were 5.53 times more likely to develop fever at 9.30 p.m. that 9.30 a.m.

Seasonal Distribution of Births in Alzheimer's Disease

We obtained season-of-birth data in 727 autopsy-confirmed cases of Alzheimer's Disease (AD) and compared these data with expected general population birth rates. There were no significant differences between quarterly birth rates in the AD group and expected quarterly birth rates. Edward's test for cyclical trends did not establish a peak period of birth in the AD sample. No significant differences between observed and expected quarterly birth rates were found when data were analyzed with regard to either family history of dementia or to gender. Edward's test for peak quarter was significant for AD females, however, with the peak period occurring early in the first quarter. These negative findings between observed and expected quarterly birth rates, based on the large number of autopsy-confirmed AD cases in this study, suggest that a season-of-birth effect in AD is highly unlikely.

Seasonality of symptomatic bacterial urinary infections in women.

Bacterial infections of the female urinary tract (UTI) are a frequent clinical problem. A chance observation, supported by a one year survey reported from another country, suggested that UTI presented to the general practitioner more frequently in the summer. A retrospective survey, covering three consecutive years, was carried out to test this observation. The records of all women reported as attending this practice with a UTI showed that 213 culture positive episodes occurred in the third calendar quarter of each year. Edward's test for cyclic variation showed a significant peaking in August. These results indicate a definite seasonal fluctuation in the frequency with which symptomatic UTIs present to general practitioners in this practice. The clinical and epidemiological significance of this phenomenon remains to be determined.

Watson's UN2 statistic for a discrete distribution

A general method is given for obtaining approximate percentiles of the asymptotic distribution of Watson's UN2 for testing goodness of fit to a completely specified discrete distribution. The method is applied to a particular distribution arising in data on seasonal incidence. Monte Carlo simulations give estimates of percentiles which are generally consistent with those obtained by the approximate method. The asymptotic results approximate well for sample sizes as small as 25. The power of UN2 is estimated and compared to that of Kuiper's VN and Edwards's test.