Simultaneous confidence intervals for contrasts of quantiles.

Skewed distributions and inferences concerning quantiles are common in the health and social science researches. And most standard simultaneous inference procedures require the normality assumption. For example, few methods exist for comparing the medians of independent samples or quantiles of several distributions in general. To our knowledge, there is no easy-to-use method for constructing simultaneous confidence intervals for multiple contrasts of quantiles in a one-way layout. In this paper, we develop an asymptotic method for constructing such intervals both for differences and ratios of quantiles and extend the idea to that of right-censored time-to-event data in survival analysis. Small-sample performance of the proposed method and a bootstrap method were assessed in terms of coverage probabilities and average widths of the simultaneous confidence intervals. Good coverage probabilities were observed for most of the distributions considered in our simulations. The proposed methods have been implemented in an R package and are used to analyze two motivating datasets.

Prevalence of thermoduric bacteria and spores in nonfat dry milk powders of Midwest origin.

Samples of nonfat dry milk powder were analyzed for the presence of heat-resistant bacteria. The samples were collected from Midwest manufacturing companies and were evaluated for the presence of spores, thermoduric bacteria, and the total bacterial count. Three companies were included in this study, and results showed differences between each of the companies in the heat-resistant microbial groups tested. Company 3 had the highest levels of total spores and thermoduric bacteria: 3.6±0.14 and 3.5±0.13 log cfu/g, respectively. Interestingly, this company did not have the highest total bacterial count but rather the second lowest total bacterial count for the group, perhaps because of the higher proportion of thermophiles present in the powders from this company. The average level of total bacterial counts was 2.57±0.07 log cfu/g. Isolates obtained from the samples were identified by mass spectrometry, and all of the companies showed Bacillus licheniformis as the most prevalent bacterial species identified.

Prevalence of thermoduric bacteria and spores on 10 Midwest dairy farms.

Thermoduric bacteria (TDB), including sporeformers and their spores, can be present in milk and dairy products even after pasteurization. They have the potential to adversely affect the quality and shelf life of products. The objectives of this study were to identify the origin and common species of heat-resistant bacteria occurring during summer and winter on Midwest dairy farms. Bulk tank milk samples were taken from 10 dairy farms located along the South Dakota section of Interstate 29, with herd sizes ranging from 650 to 3,500 lactating dairy cows. Milk samples were profiled for the prevalence of TDB and spore counts (SC). Corn silage samples and swabs of the milking clusters were also taken at the dairies to further profile the potential sources of TDB and SC. The samples were taken 3 times during 2 seasons [winter (January-March) and summer (June-August)] to track seasonal changes in the farm bacterial flora. During winter, the average TDB counts in bulk tank milk were 2.61 log compared with 2.76 log TDB counts in the summer. The SC was 1.08 log in the winter, which was half the 2.06 log SC present in the summer season. Corn silage sampled in winter contained a 7.57 log TDB count compared with an increased 10.77 log TDB count during summer sampling. Concentrations of SC in corn silage reached an average of 6.3 log in winter compared with 11.81 log for summer. The seasonal effect was evident with an increase in summer counts across the board for TDB and SC, both in the feed and bulk tank milk samples. Bacillus licheniformis was the predominant species identified in 62.4% of winter (85 total) and 49.4% of summer (83 total) samples. Bacillus subtilis made up 9.4% of the remaining winter isolates, followed by Bacillus sonorensis at 8.2%. Conversely, B. sonorensis made up 12% of the summer isolates followed by Bacillus pumilus at 10.8%. Bacillus licheniformis is a ubiquitous microbe and was isolated from both TDB and sporeformer categories in all 3 sample types. There were larger increases in SC than TDB, indicating that summer temperatures and conditions may favor proliferation of sporeforming bacteria over that of TDB. In conclusion, samples from bulk tank milk, milking cluster swabs, and corn silage samples at each of the 10 sites indicated that B. licheniformis was the major contaminant species, regardless of season. In this experiment, corn silage was the major environmental source of both TDB and SC with higher concentrations in summer when compared with winter.

Corrigendum to "Prevalence of thermoduric bacteria and spores on 10 Midwest dairy farms".

Thermoduric bacteria (TDB), including sporeformers and their spores, can be present in milk and dairy products even after pasteurization. They have the potential to adversely affect the quality and shelf life of products. The objectives of this study were to identify the origin and common species of heat-resistant bacteria occurring during summer and winter on Midwest dairy farms. Bulk tank milk samples were taken from 10 dairy farms located along the South Dakota section of Interstate 29, with herd sizes ranging from 650 to 3,500 lactating dairy cows. Milk samples were profiled for the prevalence of TDB and spore counts (SC). Corn silage samples and swabs of the milking clusters were also taken at the dairies to further profile the potential sources of TDB and SC. The samples were taken 3 times during 2 seasons [winter (January­March) and summer (June­August)] to track seasonal changes in the farm bacterial flora. During winter, the average TDB counts in bulk tank milk were 1.83 log compared with 1.89 log TDB counts in the summer. The SC was 0.85 log in the winter, which was about half the 1.37 log SC present in the summer season. Corn silage sampled in winter contained 4.09 log TDB count compared with an increased 5.85 log TDB count during summer sampling. Concentrations of SC in corn silage reached an average of 3.60 log in winter compared with 6.33 log for summer. The seasonal effect was evident with an increase in summer counts across the board for TDB and SC, both in the feed and bulk tank milk samples. Bacillus licheniformis was the predominant species identified in 62.4% of winter (85 total) and 49.4% of summer (83 total) samples. Bacillus subtilis made up 9.4% of the remaining winter isolates, followed by Bacillus sonorensis at 8.2%. Conversely, B. sonorensis made up 12% of the summer isolates followed by Bacillus pumilus at 10.8%. Bacillus licheniformis is a ubiquitous microbe and was isolated from both TDB and sporeformer categories in all 3 sample types. There were larger increases in SC than TDB, indicating that summer temperatures and conditions may favor proliferation of sporeforming bacteria over that of TDB. In conclusion, samples from bulk tank milk, milking cluster swabs, and corn silage samples at each of the 10 sites indicated that B. licheniformis was the major contaminant species, regardless of season. In this experiment, corn silage was the major environmental source of both TDB and SC with higher concentrations in summer when compared with winter.

A ratio-to-control Williams-type test for trend.

Under certain conditions, many multiple contrast tests based on the difference of treatment means can also be conveniently expressed in terms of ratios. In this paper, a Williams test for trend is defined as ratios-to-control for ease of interpretation and to obtain directly comparable confidence intervals. Simultaneous confidence intervals for percentages are particularly helpful for interpretations in the case of multiple endpoints. Methods for constructing simultaneous confidence intervals are discussed under both homogeneous and heterogeneous error variances. This approach is available in the R extension package mratios. The proposed method is used to test for trend in an immunotoxicity study with several endpoints as an example.

Equivalence tests for shelf life and average drug content in stability studies.

Stability testing is a procedure frequently used in the pharmaceutical industry to estimate the shelf life of a drug. Hereby, a standard problem of interest is whether or not to pool a given number of batches to assign a single shelf life for the combined batches. In this paper, we propose two modified methods for the pooling process. One is based on the relative average drug contents of batches at a target shelf life, which basically involves specification of thresholds in relative terms, and the other is tests for the equivalence of shelf lives (using ratios of shelf lives) at a specified lower acceptance criteria of label claim. For both approaches, marginal and simultaneous confidence intervals are established. The methods will be illustrated using two different stability data. A simulation study is conducted to investigate the coverage probability of the proposed methods.

Expression of estrus before fixed-time AI affects conception rates and factors that impact expression of estrus and the repeatability of expression of estrus in sequential breeding seasons.

Expression of estrus after PG and before fixed-time AI has been reported to change the uterine environment, increase accessory sperm numbers, fertilization rates, and overall embryo survival. Thus, expression of estrus can strongly impact overall pregnancy success. Because of variation in percentage of beef females detected in estrus and number of animals per study, it can be difficult to detect a significant effect of estrus on pregnancy success. Thus, a meta-analysis was conducted using data from 10,116 beef females in 22 studies that utilized variations of the 5 most common fixed-time AI protocols (CO-Synch, 7-day CO-Synch+CIDR, 5-day CIDR, PG 6-day CIDR, and the 14-day CIDR protocols) to examine the effect of detection in standing estrus on subsequent fixed-time AI pregnancy success. A random-effects model was used to combine the studies/herds. The overall model indicated a positive effect of estrus on conception rates with cows detected in estrus before fixed-time AI having a 27% greater (P<0.05; 95% CI=22-32%) conception rate compared with those not detected in estrus. Next we determined factors that influenced expression of estrus. Data were available on 547 cows synchronized with a CIDR based fixed-time AI protocols and observed for estrus before AI during 2-4 breeding seasons. Analysis of these cows indicated that days postpartum (P=0.22) did not impact estrous expression. In contrast, BCS influenced estrous expression (P=0.04) with cows in a BCS of ≤4 (51±5%) having decreased expression of estrus compared to cows with a BCS>4 (≥70±4%). Initiation of estrous cycles before the breeding season also influenced estrous expression (P=0.03), with anestrous cows having greater expression of estrus compared with estrus-cycling cows (78±5% vs. 70±5%, respectively). In conclusion, among all currently recommended fixed-time AI protocols, cows detected in estrus before fixed-time AI had improved conception rates, with BCS and estrus-cycling status having the greatest influence on expression of estrus.

Structural equation modeling for analyzing erythrocyte fatty acids in Framingham.

Research has shown that several types of erythrocyte fatty acids (i.e., omega-3, omega-6, and trans) are associated with risk for cardiovascular diseases. However, there are complex metabolic and dietary relations among fatty acids, which induce correlations that are typically ignored when using them as risk predictors. A latent variable approach could summarize these complex relations into a few latent variable scores for use in statistical models. Twenty-two red blood cell (RBC) fatty acids were measured in Framingham (N = 3196). The correlation matrix of the fatty acids was modeled using structural equation modeling; the model was tested for goodness-of-fit and gender invariance. Thirteen fatty acids were summarized by three latent variables, and gender invariance was rejected so separate models were developed for men and women. A score was developed for the polyunsaturated fatty acid (PUFA) latent variable, which explained about 30% of the variance in the data. The PUFA score included loadings in opposing directions among three omega-3 and three omega-6 fatty acids, and incorporated the biosynthetic and dietary relations among them. Whether the PUFA factor score can improve the performance of risk prediction in cardiovascular diseases remains to be tested.

Longitudinal effects of fat and lean mass on bone accrual in infants.

There are conflicting reports on the influence of lean and fat mass on bone accrual during childhood. No infant's studies have been reported that describe the influence of changes in body composition with changes in bone accrual during the first year of life. The objective of this research was to test the hypothesis that greater gains in lean mass will have a positive effect on bone mineral content (BMC) accrual, while greater gains in fat mass will have a negative effect on BMC accrual in infants. Longitudinal data from 3 previous infant studies were used. Linear mixed models, adjusting for age, sex, dietary calcium, and length were used to investigate longitudinal and cross-sectional associations between total body BMC and lean and fat mass in the individual studies and in a combined analysis. In both individual and combined analyses, we found that lean and fat mass were positively associated with whole body BMC accrual (all, P<0.001). The cross-sectional association of BMC and dietary calcium was negative in one study (P<0.05). No differences in BMC change between sexes were observed in three studies. Our results showed positive cross-sectional and longitudinal associations between total body BMC and lean mass in infants. In contradiction to our hypothesis for fat mass, we found a positive cross-sectional and longitudinal association between total body BMC and fat mass in infants.