Computer-intensive methods in statistical analysis

As far back as the late 1970s, the impact of affordable, high-speed computers on the theory and practice of modern statistics was recognized by Efron (1979, 1982). As a result, the bootstrap and other computer-intensive statistical methods (such as subsampling and the jackknife) have been developed extensively since that time and now constitute very powerful (and intuitive) tools to do statistics with. This article provides a readable, self-contained introduction to the bootstrap and jackknife methodology for statistical inference; in particular, the focus is on the derivation of confidence intervals in general situations. A guide to the available bibliography on bootstrap methods is also offered     

A GENERALIZED BLOCK BOOTSTRAP FOR SEASONAL TIME SERIES

When time‐series data contain a periodic/seasonal component, the usual block bootstrap procedures are not directly applicable. We propose a modification of the block bootstrap – the generalized seasonal block bootstrap (GSBB) – and show its asymptotic consistency without undue restrictions on the relative size of the period and block size. Notably, it is exactly such restrictions that limit the applicability of other proposals of block bootstrap methods for time series with periodicities. The finite‐sample performance of the GSBB is also illustrated by means of a small simulation experiment.     

Expression of urokinase plasminogen activator receptor in resting and activated bovine neutrophils

Changes in urokinase-plasminogen activator (u-PA) and u-PA receptor (u-PAR) expression at the protein and mRNA level in resting neutrophils and in neutrophils activated by phorbol myristate acetate (PMA) were examined. Low amounts of u-PA were found intracellularly or membrane-bound in resting neutrophils. However, incubation of resting neutrophils with purified exogenous u-PA (10 IU/ml) revealed extensive binding of u-PA to cell membranes. Excess amino-terminal fragment of the u-PA molecule, a proteolytically inactive fragment of u-PA (amino acids 1-135) blocked binding of exogenous u-PA to the cell membrane. These results, collectively, indicate that the binding of u-PA is specific and that resting neutrophils have unoccupied u-PA receptors on their cell membrane. Addition of PMA led to an increase (P < 0.01) in total cell-associated, membrane-bound u-PA activity and u-PA mRNA expression by bovine neutrophils. In contrast. PMA increased u-PAR mRNA levels but this was accompanied by a decrease (2.5-fold; P < 0.01) in free, unoccupied u-PA binding sites. No significant effects on total cell-associated or membrane-bound u-PA were found when neutrophils were treated with 4-phorbol 12,13 didecanoate, a phorbol ester that does not activate protein kinase C (PKC). Furthermore, addition of 1-(5-isoquinolinesylphonyl)-2-methlylpiperazine dihydrochloride (H-7), a potent PKC inhibitor, blocked the effect of PMA on total cell-associated u-PA activity. Thus, PKC plays a role in the modulation of u-PA and u-PAR by PMA in bovine neutrophils.     

Effect of vitamin E supplementation on neutrophil function, milk composition and plasmin activity in dairy cows in a commercial herd

Fifty-six Holstein dairy cows from a commercial dairy herd in the Northern part of Greece were used to determine the effect of vitamin E supplementation on immune parameters, milk composition and milk quality. Cows were assigned to one of two experimental groups: control (no vitamin E supplementation) and vitamin E supplementation. Supplementation of vitamin E started 4 weeks prior to and continued up to 12 weeks after parturition. Supplementation included daily oral administration of vitamin E at 3000 i.u./cow prepartum and was reduced to 1000 i.u./cow post partum. Blood samples were collected weekly for 8 weeks starting 4 weeks before parturition, neutrophils were isolated and the following parameters were determined in neutrophils activated by phorbol myristate acetate: total cell-associated and membrane-bound urokinase plasminogen activator (u-PA) activity and superoxide production. Milk samples were collected weekly and fat, protein, lactose, somatic cell count (SCC), plasmin and plasminogen-derived activity were determined. Activated neutrophils isolated from cows that received supplemental vitamin E had higher (P<0.01) total and membrane-bound u-PA activities during the first 3 weeks after parturition and higher (P<0.01) superoxide production during week 1 prepartum and week 1 post partum compared with the corresponding values of activated neutrophils isolated from control cows. Vitamin E supplementation had no effect (P=0.28) on plasminogen-derived activity in milk. Milk obtained from cows that received supplemental vitamin E had SCC lower by 25% (P<0.05) and plasmin lower by 30% (P<0.01) than corresponding values in milk obtained from control cows. The reduction in plasmin as a result of vitamin E supplementation is very beneficial to the dairy industry because plasmin reduces the cheese-yielding capacity of milk, affects the coagulating properties of milk and its overall ability to withstand processing during cheesemaking. In conclusion, vitamin E supplementation had positive effects on the function of bovine neutrophils and milk quality in a commercial dairy herd.     

Environmental factors affecting plasmin activity in milk

A total of 367 milk samples were collected from 43 individual Holstein cows during 1 yr. Samples were analyzed for plasmin activity, total casein, alpha s-casein (alpha s1-casein + alpha s2-casein), beta-casein, kappa-casein, and SCC. Least squares analyses showed that SCC in milk were positively related (r = .62) to plasmin activity. An increase of SCC from 100,000 to 1,300,000/ml was associated with a 2.3-fold increase in plasmin activity (100 vs. 230 x 10(-6) units/ml). Increased plasmin activity was associated with advancing stage of lactation and older cows after appropriate adjustments were made for the effects of milk yield and SCC. Milk samples obtained in fall and winter were higher, but not significantly, in plasmin activity. Plasmin activity was also associated with major casein components and milk pH. Correlations coefficients between plasmin and alpha s-casein, beta-casein, and pH were -.14, -.27, and .19.     

Banded and tapered estimates for autocovariance matrices and the linear process bootstrap

We address the problem of estimating the autocovariance matrix of a stationary process. Under short range dependence assumptions, convergence rates are established for a gradually tapered version of the sample autocovariance matrix and for its inverse. The proposed estimator is formed by leaving the main diagonals of the sample autocovariance matrix intact while gradually down‐weighting off‐diagonal entries towards zero. In addition, we show the same convergence rates hold for a positive definite version of the estimator, and we introduce a new approach for selecting the banding parameter. The new matrix estimator is shown to perform well theoretically and in simulation studies. As an application, we introduce a new resampling scheme for stationary processes termed the linear process bootstrap (LPB). The LPB is shown to be asymptotically valid for the sample mean and related statistics. The effectiveness of the proposed methods are demonstrated in a simulation study.     

Effect on production traits of bovine somatotropin for up to three consecutive lactations.

Thirteen (control) cows were injected daily with saline and 22 with bST (12 at 10.3 mg/d and 10 at 20.6 mg/d) through wk 5 to 42 of lactation. Nine of the treated cows had received bST in the previous lactation, and 7 cows received bST in the previous two lactations. All control cows and 6 treated cows had not previously received bST. Treatment with bST caused substantial increases in milk production, feed intake, and efficiency of feed conversion in the current lactation, which is consistent with previous trials. Increases in feed intake were established fully within 9 wk of starting bST administration, somewhat earlier than usually reported. Treatment with bST in one or two previous lactations caused a statistically significant 14% reduction in production and 8% reduction in efficiency of feed conversion during the first 9 wk of bST treatment in the current lactation; reductions observed later in lactation were not statistically significant. Differences for other traits were not statistically significant. In combination with earlier trials, these results suggest that, although bST has beneficial effects on production and efficiency traits, these benefits may be considerably lower in the second and subsequent lactations of bST use. However, carry-over effects on cows not receiving bST in the current lactation were not explored in this trial.