FORECASTING WITH PREDICTION INTERVALS FOR PERIODIC ARMA MODELS.

Periodic autoregressive moving average (PARMA) models are indicated for time series whose mean, variance, and covariance function vary with the season. In this paper, we develop and implement forecasting procedures for PARMA models. Forecasts are developed using the innovations algorithm, along with an idea of Ansley. A formula for the asymptotic error variance is provided, so that Gaussian prediction intervals can be computed. Finally, an application to monthly river flow forecasting is given, to illustrate the method.

A case of chronic wasting disease in a captive red deer (Cervus elaphus).

A 22-month-old, female red deer (Cervus elaphus) was submitted to the University of Minnesota Veterinary Diagnostic Laboratory for necropsy and chronic wasting disease (CWD) testing. The deer was found positive for the abnormal prion protein in the obex and the retropharyngeal lymph node by immunohistochemical staining. Microscopic lesions of spongiform encephalopathy and immunohistochemical staining patterns and intensity were similar to those in CWD-positive elk and experimentally infected red deer.

Evaluation of progress made by dairy and beef herds enrolled in the Minnesota Johne's Disease Control Program.

OBJECTIVE: To evaluate progress made by cattle herds in the control of paratuberculosis (Johne's disease) through participation in the Minnesota Johne's Disease Control Program (MNJDCP). DESIGN: Retrospective records analysis. SAMPLE POPULATION: Data for dairy and beef herds participating in the MNJDCP. PROCEDURES: Data for the MNJDCP were collected for analyses. Outcome measures included changes in numbers of participating cattle producers, risk assessment scores, and within-herd seroprevalence of Johne's disease by year of program participation. RESULTS: Results revealed steady increases in program participation by cattle producers in Minnesota over time, with > 30% of dairy producers and 2% of beef producers in the state participating by the end of 2006. Despite risk of introduction of Johne's disease to cattle herds through continued introduction of cattle from other herds, dairy and beef herds in the Management Program of the MNJDCP reduced their on-farm risk assessment scores during the program. Dairy herds in the Management Program reduced their mean within-herd seroprevalence 1.1% during the first year, 2.6% during the first 2 years, and 4.0% during the first 3 years of program participation. Significant within-herd seroprevalence reduction was also detected for beef herds that participated in the Management Program for at least 3 years. CONCLUSIONS AND CLINICAL RELEVANCE: This study revealed a reduction in the risk of withinherd transmission of Johne's disease and seroprevalence over time in dairy and beef herds in the Management Program of the MNJDCP. This is consistent with a positive effect of the program for the control of Johne's disease in cattle.