Person:

Brookhart, M

Background: Edwards's method is a widely used approach for fitting a sine curve to a time-series of monthly frequencies. From this fitted curve, estimates of the seasonal intensity of occurrence (i.e., peak-to-low ratio of the fitted curve) can be generated. Methods: We discuss various approaches to the estimation of seasonal intensity assuming Edwards's periodic model, including maximum likelihood estimation (MLE), least squares, weighted least squares, and a new closed-form estimator based on a second-order moment statistic and non-transformed data. Through an extensive Monte Carlo simulation study, we compare the finite sample performance characteristics of the estimators discussed in this paper. Finally, all estimators and confidence interval procedures discussed are compared in a re-analysis of data on the seasonality of monocytic leukemia. Results: We find that Edwards's estimator is substantially biased, particularly for small numbers of events and very large or small amounts of seasonality. For the common setting of rare events and moderate seasonality, the new estimator proposed in this paper yields less finite sample bias and better mean squared error than either the MLE or weighted least squares. For large studies and strong seasonality, MLE or weighted least squares appears to be the optimal analytic method among those considered. Conclusion: Edwards's estimator of the seasonal relative risk can exhibit substantial finite sample bias. The alternative estimators considered in this paper should be preferred.

Objective: To examine trends in osteoporosis drug prescribing after hip fracture from 1995 to 2004. Methods: We conducted a population-based study of enrollees in the Pennsylvania Pharmaceutical Assistance Contract for the Elderly. Hip fractures were identified using Medicare hospital claims between January 1, 1995, and June 30, 2004. Osteoporosis treatment comprised oral bisphosphonates, calcitonin, hormone therapy, raloxifene, and/or teriparatide. Kaplan-Meier methods were used to estimate the probability of treatment within 6 months of fracture, censoring patients on their date of death or 6 months postfracture. Results: Treatment within 6 months after hip fracture improved from 7% in 1995 to 31% in 2002, and then remained stable through 2004. Similar patterns were observed among new users, with treatment increasing from 4% in 1995 to 17% in 2002, with no subsequent increase through 2004. Bisphosphonates led other treatments in the frequency of prescribing, except during 1997–99, when calcitonin was the most common. Among women, hormone therapy prescribing decreased from 22% of those treated in 1995 to 4% in 2004, and raloxifene prescribing remained relatively constant (4%–10%) since its introduction (p for trend = 0.15). Of patients treated before and after hip fracture, 18% changed therapy postfracture. Significantly more patients changed therapy following fracture if a different physician prescribed treatment (26%) compared to those treated by the same physician pre- and postfracture (13%; p < 0.0001). Conclusion: Prescribing practices changed substantially over the 10 years of study. The proportion of hip fracture patients treated with osteoporosis drugs has increased, but remains low, with fewer than one-third receiving pharmacotherapy.