Ordinary Linear Regression Analysis Research Articles

Options as a predictor of common stock price changes

Since rather novel techniques such as neural nets allow investigation of nonlinear model specification previously untested, it may be that traditional models of price formation underperform through misspecification rather than market efficiency. This paper explores whether a multilayer backpropagation model offers exploitable profit opportunities for some limited period. Using an intradaytransaction dataset obtained from the European Options Exchange (Amsterdam), We attempted to predict the return on Philips. Two neural nets are contrasted to ordinary linear regression analysis on the basis of three benchmarks (MSE, and net realized returns). An adaptively trained 33-14-1 architecture scored best on all criteria and yielded an annualized 11% return following a simple one-period trading strategy.

Effects of infection with bovine virus diarrhoea virus on health and reproductive performance in 213 dairy herds in one county in Sweden

Bulk tank milk samples, collected twice with a 1 year interval, from 213 Swedish dairy herds with no vaccination programme against bovine virus diarrhoea virus (BVDV), were tested for antibodies to BVDV using an indirect enzyme-linked immunosorbent assay. The herds were classified into four different BVDV groupings based on changes in the estimated prevalence of BVDV antibody-positive cows in the herds. The estimated mean prevalences of BVDV antibody-positive cows were maintained as > 80% in 58 (27.2%) and as < 10% in 84 (39.4%) of the herds. A recent introduction of the infection was deemed to have occurred in seven (3.3%) of the herds studied. The BVDV groups were compared with regard to parameters related to disease and fertility at herd level. Relationships were assessed using logistic and ordinary linear regression analyses. The risks for clinical mastitis, retained placenta and oestrus-stimulating treatments were higher and the calving intervals were longer in BVDV infected herds, i.e. those herds with an increasing or maintained high prevalence of BVDV antibody-positive cows.

Relationships between herd bovine leukemia virus infection status and reproduction, disease incidence, and productivity in Swedish dairy herds

A program has been initiated in Sweden to eradicate bovine leukemia virus (BLV) infections in dairy and beef cattle. As the first step, all dairy herds were screened in order to identify those with BLV-infected animals. The objective of this study was to ascertain possible relationships between herd BLV infection status and measures describing disease incidence, reproduction and production. BLV infection status was determined in 14 424 herds, using an enzyme-linked immunosorbent assay (ELISA) test applied to bulk-milk samples. Relationships were assessed with logistic and ordinary linear regression analyses. There were many statistically significant associations between herd BLV infection status and measures of disease incidence, reproduction and production, but most were of low magnitude. The risk for diseases with infectious etiology seemed to be greater among BLV-infected herds, while the risk for non-infectious diseases did not differ. The culling rate was higher and milk production was lower in BLV-infected vs. BLV-free herds. The effect of BLV infection on fertility was only minor.