Random forests for survival data: which methods work best and under what conditions?

Few systematic comparisons of methods for constructing survival trees and forests exist in the literature. Importantly, when the goal is to predict a survival time or estimate a survival function, the optimal choice of method is unclear. We use an extensive simulation study to systematically investigate various factors that influence survival forest performance - forest construction method, censoring, sample size, distribution of the response, structure of the linear predictor, and presence of correlated or noisy covariates. In particular, we study 11 methods that have recently been proposed in the literature and identify 6 top performers. We find that all the factors that we investigate have significant impact on the methods' relative accuracy of point predictions of survival times and survival function estimates. We use our results to make recommendations for which methods to use in a given context and offer explanations for the observed differences in relative performance.

Causal pathways to health-related quality of life in children with juvenile idiopathic arthritis: results from the ReACCh-Out cohort

OBJECTIVE

Structural equation modelling was applied to data from the Research in Arthritis in Canadian Children emphasizing Outcomes (ReACCh-Out) cohort to help elucidate causal pathways to decreased health-related quality of life (HRQoL) in children with JIA.

METHODS

Based on published literature and clinical plausibility, a priori models were constructed with explicit root causes (disease activity, treatment intensity) and mediators (pain, disease symptoms, functional impairments) leading to HRQoL [measured by the Quality of my Life (QoML) scale and the Juvenile Arthritis Quality of Life Questionnaire (JAQQ)] at five disease stages: (i) diagnosis, (ii) 3-9 months after diagnosis, (iii) flare, (iv) remission on medications, (v) remission off medications. Following structural equation modelling, a posteriori models were selected based on data fit and clinical plausibility.

RESULTS

We included 561, 887, 137, 186 and 182 patients at each stage, respectively. In a posteriori models for active disease stages, paths from disease activity led through pain, functional impairments, and disease symptoms, directly or through restrictions in participation, to decreased QoML scores. Treatment intensity had detrimental effects through psychosocial domains; while treatment side effects had a lesser role. Pathways were similar for QoML and JAQQ, but JAQQ models provided greater specificity. Models for remission stages were not supported by the data.

CONCLUSION

Our findings support disease activity and treatment intensity as being root causes of decreased HRQoL in children with JIA, with pain, functional impairments, and participation restrictions being mediators for disease activity; they support psychosocial effects and side effects as being mediators for treatment intensity.

Determinants of staff commitment to hip protectors in long-term care: A cross-sectional survey

BACKGROUND

If worn, certain models of hip protectors are highly effective at preventing hip fractures from falls in residents of long-term care, but modest acceptance and adherence have limited the effectiveness of hip protectors. Residents of long-term care are more likely to accept the initial offer of hip protectors and to adhere to recommendations concerning the use of hip protectors when staff are committed to supporting the application of hip protectors. Yet, we know very little about the nature of and factors associated with staff commitment to hip protectors in long-term care.

OBJECTIVE

To identify factors associated with staff commitment to hip protectors in long-term care.

DESIGN

A cross-sectional survey.

SETTING

Thirteen long-term care homes (total beds = 1816) from a single regional health district in British Columbia, Canada.

PARTICIPANTS

A convenience sample of 535 paid staff who worked most of their time (>50% of work hours) at a participating long-term care home, for at least one month, and for at least 8 h per week. We excluded six (1.1%) respondents who were unaware of hip protectors. Of the remaining 529 respondents, 90% were female and 55% were health care assistants.

METHODS

Respondents completed the Commitment to Hip Protectors Index to indicate their commitment to hip protectors. We used Bayesian Model Averaging logistic regression to model staff commitment as a function of personal variables, experiences with hip protectors, intraorganizational communication and influence, and organizational context.

RESULTS

Staff commitment was negatively related to organizational tenure >20 years (posterior probability = 97%; logistic regression coefficient = -0.28; 95% confidence interval = -0.48, -0.08), and awareness of a padded hip fracture (100%; -0.57; -0.69, -0.44). Staff commitment was positively related to the existence of a champion of hip protectors within the home (100%; 0.24; 0.17, 0.31), perceived quality of intraorganizational communication (100%; 0.04; 0.02, 0.05), extent of mutual respect between residents and staff and perceived contribution to quality of life of the residents they serve (100%; 0.10; 0.05, 0.15), and frequency of transformational leadership practices by respondents' primary supervisors (100%; 0.01; 0.01, 0.02).

CONCLUSIONS

We provide novel insight into the factors governing staff commitment to hip protectors in long-term care. Targeting of these factors could improve acceptance and adherence with hip protectors, thereby contributing to enhanced effectiveness of hip protectors to prevent hip fractures in long-term care.

Beef longissimus lumborum, biceps femoris, and deep pectoralis Warner-Bratzler shear force is affected differently by endpoint temperature, cooking method, and USDA quality grade

Effects of endpoint temperature, cooking method, and quality grade on Warner-Bratzler shear force (WBSF) of beef longissimus lumborum (LL), biceps femoris (BF), and deep pectoralis (DP) muscles were evaluated. Eighteen of all three subprimals were selected from USDA Select and 18 from USDA Choice (Certified Angus Beef) carcasses for the respective muscles. Muscles were vacuum packaged and held at 1 °C for 14 days, frozen (-29 °C), sawed into 2.54-cm thick steaks, vacuum packaged, and stored frozen until cooking. Thawed steaks were cooked by either a Magikitch'n(®) electric belt-grill (BG) at 93 °C, or a water-bath at 93 °C, to one of nine endpoint temperatures: 40, 45, 50, 55, 60, 65, 70, 75, or 80 °C. Belt-grill cooking was much faster and resulted in distinctly less cooking loss than water-bath cooking. Water-bath cooking resulted in higher (P<0.0001) Instron(®) WBSF (31.92 N) than BG (28.25 N) for LL. The combination of Select quality grade and higher endpoint temperatures resulted in higher (P<0.05) WBSF for LL. Two distinct phases of tenderization/toughening occurred for BF. Between 40 and 60 °C, WBSF decreased from 43.95 to 38.16 N (P<0.01), whereas between 60 and 70 °C, WBSF increased from 38.16 N to 44.44 N (P<0.05). Water-bath cooling resulted in higher (P=0.0001) DP WBSF (71.12 N) than BG (59.25 N). The DP had a distinct (P<0.0001) decline in WBSF between 45 and 65 °C, irrespective of the cooking method, followed by an increase between 65 and 80 °C (P<0.01).

Geographic variation in rodent-flea relationships in the presence of black-tailed prairie dog colonies

We characterized the relationship between fleas and their rodent hosts in the presence of prairie dog colonies and compared them to adjacent assemblages away from colonies. We evaluated the rodent-flea relationship by quantifying prevalence, probability of infestation, flea load, and intensity of fleas on rodents. As prairie dog burrows provide refugia for fleas, we hypothesized that prevalence, flea load, and intensity would be higher for rodents that are associated with black-tailed prairie dog colonies. Rodents were trapped at off- and on-colony grids, resulting in the collection of 4,509 fleas from 1,430 rodents in six study areas. The rodent community composition varied between these study areas. Flea species richness was not different between prairie dog colonies and the surrounding grasslands (p = 0.883) but was positively correlated with rodent species richness (p = 0.055). Prairie dog colonies did not increase the prevalence of fleas (p > 0.10). Flea loads on rodents did not vary between off- and on-colony grids at three of the study areas (p > 0.10). Based on the prevalence, infestation rates, and flea loads, we identified Peromyscus maniculatus, Onychomys leucogaster, and two Neotoma species as important rodent hosts for fleas and Aetheca wagneri, Orchopeus leucopus, Peromyscopsylla hesperomys, Pleochaetis exilis, and Thrassisfotus as the most important fleas associated with these rodents. Prairie dog colonies did not seem to facilitate transmission of fleas between rodent hosts, and the few rodent-flea associations exhibited significant differences between off- and on-colony grids.

Assessing pitcher and catcher influences on base stealing in Major League Baseball

A formal statistical analysis is performed to determine the extent to which pitchers and catchers can influence stolen-base attempts and successes. Two response proportions, attempt/opportunity and success/attempt, are modelled separately using mixed-effects logistic regression models applied to situations with a runner on first and other bases empty. Data include the first innings of all Major League Baseball games played between 1978 and 1990, which encompasses over 48,000 opportunities and 9000 attempts. Pitchers and catchers are entered as random effects and various other factors thought to influence stolen-base attempts and successes are entered as fixed effects. Variance components are estimated and hypotheses tests indicate that the population variance components for both pitchers and catchers are significant for both response proportions. The presence of variation among players at the respective positions is interpreted as evidence that stolen-base defence is a real skill exhibited to varying extents by different players. Furthermore, the variance component for pitchers is greater than that for catchers for both response proportions, indicating that pitchers have greater potential to affect stolen-base attempts and successes. Under usual conditions, it is estimated that 95% of pitchers have first-inning stolen-base success/attempt probabilities between 0.50 and 0.84, while 95% of catchers have probabilities between 0.59 and 0.79.

Efficacy of Bauveria bassiana for red flour beetle when applied with plant essential oils or in mineral oil and organosilicone carriers

The carriers mineral oil and Silwet L-77 and the botanical insecticides Neemix 4.5 and Hexacide were evaluated for their impacts on the efficacy of Beauveria bassiana (Balsamo) Vuillemin conidia against red flour beetle, Tribolium castaneum (Herbst), larvae. The dosages of liquid treatments were quantified by both conidia concentration in the spray volume and conidia deposition on the target surface. The latter approach allowed comparison with dry, unformulated conidia. The median lethal concentrations of B. bassiana in 0.05% Silwet L-77 solution or without a carrier were approximately double that for conidia in mineral oil. Carriers had highly significant effects on the efficacy of B. bassiana. The lower efficacy of conidia in aqueous Silwet L-77 may have been the result of conidia loss from the larval surface because of the siloxane's spreading properties. Neemix 4.5 (4.5% azadirachtin) delayed pupation and did not reduce the germination rate of B. bassiana conidia, but it significantly reduced T. castaneum mortality at two of four tested fungus doses. Hexacide (5% rosemary oil) caused significant mortality when applied without B. bassiana, but it did not affect pupation, the germination rate of conidia, or T. castaneum mortality when used in combination with the fungus.

Beef quadriceps hot boning and modified-atmosphere packaging influence properties of injection-enhanced beef round muscles1,2

Two experiments were conducted to examine the effects of hot boning, modified atmosphere packaging, and injection enhancement on the oxidative and sensory properties of beef round muscles. The beef knuckle (quadriceps muscles) was partially hot boned within 1.5 h postmortem from one randomly selected side of each beef carcass (n = 14), whereas the quadriceps on the opposite side remained intact throughout a 48-h chilling period. At 5 d postmortem, biceps femoris, semimembranosus, vastus lateralis, and rectus femoris muscles from both hot- and cold-boned sides were injected with an enhancement solution consisting of water, salt, phosphate, and natural flavorings (rosemary) at either 6 (Exp. 1) or 10% (Exp. 2) of fresh muscle weight. Enhanced muscles were then processed into 2.54-cm-thick steaks, which were allotted randomly to high-oxygen (HiOx; 80% O2:20% CO2) or ultra-low oxygen (LoOx; 80% N2:20% CO2) modified atmosphere packaging. Regardless of hot boning or enhancement, steaks packaged in LoOx had lower thiobarbituric acid-reactive substances values (P < 0.05), more beef flavor intensity (P < 0.05), fewer off flavors (P < 0.05), and were more tender (P < 0.05) than steaks packaged in HiOx. Hot boning the knuckle had no effect on oxidative (P > or = 0.99) and sensory properties (P > or = 0.85). Increasing the level of injection enhancement from 6 to 10% introduced more rosemary and phosphate into the muscles, thereby decreasing the extent of oxidation, but also imparting a nontypical beef flavor. Packaging in LoOx atmosphere offered the optimal result of decreased oxidation and improved tenderness, without detriment to flavor. Injection enhancement (both 6 and 10%) created off-flavors attributable to the enhancement solution; however, the 10% injection seemed to offer more resistance to lipid oxidation.

Physical activity minimizes the association of body fatness with abdominal obesity in white, premenopausal women: Results from the Third National Health and Nutrition Examination Survey

This study explored the association of physical activity with body fatness and abdominal obesity in 1,004 premenopausal white women who participated in the Third National Health and Nutrition Examination Survey. Physical activity was classified into four levels based on fitness criteria from the American College of Sports Medicine. Standard protocols were used for measuring body mass index (BMI), percent body fat, and waist-to-hip ratio (WHR). Means for BMI, percent body fat, and WHR were calculated for each physical activity level. Analysis of variance procedures were performed, followed by pair-wise comparisons, to determine differences among means and for trends. Mean BMI, percent body fat, and WHR were significantly less ( P < .001) at each higher physical activity level except between Levels 0 and 1. The ability of increased daily physical activity to minimize age-related increases in abdominal obesity could be a strong incentive for women approaching menopause to become more physically active.

Mechanical probes can predict tenderness of cooked beef longissimus using uncooked measurements1

Two experiments were conducted to determine the effectiveness of using mechanical probes and objective color measurement on beef LM to predict cooked tenderness. In Exp. 1, sharp needle (SN), sharp blade (SB), blunt needle (BN), blunt blade (BB), and plumb bob (PB) probes were used to measure uncooked LM (n = 29) at 2 d postmortem in both a perpendicular and parallel orientation to the long axis of the strip loin. Additionally, instrumental color measurements were measured on uncooked muscle at 2 d postmortem. Steaks for trained sensory panel (TSP) and Warner-Bratzler shear force (WBSF) measurements were aged 14 d postmortem before cooking. Probe measurements taken perpendicular to the long axis of the LM were not correlated (P = 0.22 to 0.82) to TSP tenderness. Probe measurements (BB, BN, SN, SB, and PB) taken parallel to the long axis were correlated to TSP tenderness (r = -0.57, -0.40, -0.77, -0.52, and -0.53, respectively). A regression equation using the SN probe to predict TSP tenderness had a R2 value of 0.74. The SB probe combined with L* accounted for 45% of the variation in TSP tenderness, whereas the PB probe combined with L* accounted for 56% of the variation in TSP tenderness. A second experiment (n = 24) was conducted using the SN, SB, and PB probes on uncooked sections at 2 d and on cooked steaks at 14 d postmortem. Probe measurements on cooked steaks were not correlated to TSP tenderness. New regression equations were calculated using the probe measurements on uncooked steaks from both experiments. Prediction equations formulated with L* values and either SN, SB, or PB probes accounted for 49, 50, and 47% of the variability in TSP tenderness scores, respectively. An equation using WBSF of cooked steaks to predict TSP tenderness had an R2 of 0.58. Of the steaks predicted to be tender (predicted tenderness > 5.0) by the equations using the SN, SB, and PB probes on uncooked steaks and WBSF on cooked steaks, 85, 88, 80, and 84%, respectively, were actually tender (TSP tenderness > 5.0). Mechanical probe measurements of uncooked steaks at 2 d postmortem can potentially classify strip loins into groups based on tenderness, as well as WBSF measurements, which are more costly and time consuming.

Testing for Marginal Independence between Two Categorical Variables with Multiple Responses

Questions that ask respondents to "choose all that apply" from a set of items occur frequently in surveys. Categorical variables that summarize this type of survey data are called both pick any/c variables and multiple-response categorical variables. It is often of interest to test for independence between two categorical variables. When both categorical variables can have multiple responses, traditional Pearson chi-square tests for independence should not be used because of the within-subject dependence among responses. An intuitively constructed version of the Pearson statistic is proposed to perform the test using bootstrap procedures to approximate its sampling distribution. First- and second-order adjustments to the proposed statistic are given in order to use a chi-square distribution approximation. A Bonferroni adjustment is proposed to perform the test when the joint set of responses for individual subjects is unavailable. Simulations show that the bootstrap procedures hold the correct size more consistently than the other procedures.

Effects of postexsanguination vascular infusion of carcasses with calcium chloride or a solution of saccharides, sodium chloride, and phosphates on beef display-color stability

Hereford x Angus crossbred steers (n = 36) were stunned, exsanguinated, and infused via the carotid artery either with an aqueous solution containing 98.52% water, 0.97% saccharides, 0.23% sodium chloride, and 0.28% phosphates (MPSC; n = 12) or with 0.3 M CaCl2 (n = 12). The remaining 12 steers served as noninfused controls. At 48 h postmortem, the quadriceps muscles and subcutaneous fat were removed from the carcasses, frozen, and later made into ground beef (18 to 20% fat). The longissimus lumborum (LL), semimembranosus, and psoas major (PM) also were removed, vacuum packaged, aged until 14 d postmortem, and then one steak was sliced from each muscle for visual and instrumental color evaluations. The inside (ISM) and outside (OSM) portions of the SM were evaluated separately. The LL and OSM steaks from MPSC-infused carcasses had a lighter red (P < 0.05) initial appearance than steaks from the other treatments. The LL steaks from noninfused carcasses had the most (P < 0.05) uniform color; the MPSC treatment was intermediate, and the CaCl2 treatment was the most two-toned. Steaks from both infusion treatments had higher (P < 0.05) L* values for the LL, ISM, and OSM muscles compared with noninfused carcasses. In general, the LL from CaCl2-infused carcasses had lower (P < 0.05) a* values, saturation indices, and 630 nm to 580 nm reflectance values, and had larger (P < 0.05) hue angles. Infusion with MPSC increased (P < 0.05) hue angles in the LL and OSM. Display color stability was lowest (P < 0.05) for LL steaks from CaCl2-infused carcasses, whereas steaks from MPSC-infused carcasses were lighter red in initial color, but otherwise had display color stability similar to those from noninfused carcasses. No differences (P > 0.05) due to infusion were found for any color traits for the PM muscle and ground beef. Carotid artery vascular infusion of carcasses with CaCl2 resulted in undesirable meat colors, whereas the MPSC solution lightened loin and inside round color in a desirable way, but the color stability was slightly less compared to muscle from noninfused carcasses. Infusion effects were not consistent among muscles, and further research will be needed to determine what caused these differences.

Testing for conditional multiple marginal independence

Survey respondents are often prompted to pick any number of responses from a set of possible responses. Categorical variables that summarize this kind of data are called pick any/c variables. Counts from surveys that contain a pick any/c variable along with a group variable (r levels) and stratification variable (q levels) can be marginally summarized into an r x c x q contingency table. A question that may naturally arise from this setup is to determine if the group and pick any/c variable are marginally independent given the stratification variable. A test for conditional multiple marginal independence (CMMI) can be used to answer this question. Since subjects may pick any number out of c possible responses, the Cochran (1954, Biometrics 10, 417-451) and Mantel and Haenszel (1959, Journal of the National Cancer Institute 22, 719-748) tests cannot be used directly because they assume that units in the contingency table are independent of each other. Therefore, new testing methods are developed. Cochran's test statistic is extended to r x 2 x q tables, and a modified version of this statistic is proposed to test CMMI. Its sampling distribution can be approximated through bootstrapping. Other CMMI testing methods discussed are bootstrap p-value combination methods and Bonferroni adjustments. Simulation findings suggest that the proposed bootstrap procedures and the Bonferroni adjustments consistently hold the correct size and provide power against various alternatives.

On the first-order Rao-Scott correction of the Umesh-Loughin-Scherer statistic

Decady and Thomas (2000, Biometrics 56, 893-896) propose a first-order corrected Umesh-Loughin-Scherer statistic to test for association in an r x c contingency table with multiple column responses. Agresti and Liu (1999, Biometrics 55, 936-943) point out that such statistics are not invariant to the arbitrary designation of a zero or one to a positive response. This paper shows that, in addition, the proposed testing procedure does not hold the correct size when there are strong pairwise associations between responses.

Effects of dietary fat on growth performance and carcass characteristics of growing-finishing pigs reared in a commercial environment

We conducted two experiments to evaluate the effects of added choice white grease on performance and carcass merit of barrows and gilts reared under commercial conditions. Pigs were housed either 20 (Exp. 1) or 25 (Exp. 2) per pen and were provided 0.67 m2 of pen space per pig. Diets were based on corn and soybean meal and fed in a meal form. The proportion of soybean meal was increased in diets with added fat to maintain the same calorie:lysine ratio in all diets within a weight phase. In Exp. 1, 480 pigs were fed diets with 0, 2, 4, or 6% fat. Total lysine contents of the control diets were 1.21, 0.88, and 0.66% during the weight phases 36 to 59, 59 to 93, and 93 to 120 kg, respectively. Gain:feed was increased linearly (P < 0.01) due to fat addition in all weight intervals and over the total experiment. The effect of added fat on ADG was not consistent among the weight phases; a linear (P < 0.01) improvement was found from 36 to 59 kg, but no effect was found during the heavier weight phases. Over the total experiment, however, ADG was improved (P < 0.01) linearly. Carcass traits were not affected by treatment. Experiment 2 used 900 pigs to evaluate possible carryover effects on performance and carcass merit from feeding 6% fat. The experiment was divided into four phases: 25 to 45, 45 to 70, 70 to 90, and 90 to 115 kg; lysine contents of the control diets fed in each phase were 1.23, 1.05, 0.81, and 0.63%, respectively. The six treatments consisted of no added fat throughout the experiment or 6% added fat fed from 25 to 45 kg, 25 to 70 kg, 25 to 90 kg, 25 to 115 kg, or 45 to 70 and 90 to 115 kg. Carryover effects for ADG and G:F (P < 0.07) were found for the 90- to 115-kg interval and for ADFI and ME intake (P < 0.05) for the 45- to 70- and 70-to 90-kg intervals. When fat was added in the previous weight interval, ADG and G:F were improved and ADFI and ME intake were decreased in the subsequent weight interval. Pigs fed fat from 25 to 115 kg had more (P < 0.05) backfat and lower (P < 0.05) carcass leanness than pigs on the other treatments. These data suggest that fat can be added or removed from diets of growing-finishing pigs without any detrimental carryover effects. In fact, the positive carryover effect on ADG and G:F from 95 to 115 kg suggests that feeding fat from 25 to 95 kg will maximize performance over the total growing-finishing period but minimize any detrimental effects of added fat on carcass leanness.

Exercise mitigates the association of abdominal obesity with high-density lipoprotein cholesterol in premenopausal women: results from the third National Health and Nutrition Examination Survey

OBJECTIVE

To examine the relationship between abdominal obesity, as measured by waist-to-hip ratio (WHR) and high-density lipoprotein cholesterol (HDL-C) level within the context of age, body fatness, exercise, saturated fat intake, and other plasma lipids.

DESIGN/SUBJECTS

Subjects were premenopausal, white, non-Hispanic women from the third National Health and Nutrition Examination Survey. Smokers, heavy drinkers, and women who took lipid-altering drugs were excluded. Of 1,188 subjects who met the inclusion criteria, complete data were available for 435 women.

STATISTICAL ANALYSES

Means were calculated using all subjects for each variable, then F-protected t tests and linear contrasts were performed to test differences in means between subgroups. A P < .05 was considered significant.

RESULTS

Age was not significantly associated with HDL-C level. Comparisons of HDL-C by WHR, percentage body fat (%BF), and exercise level revealed that HDL-C level was significantly lower at the higher levels of WHR and %BF and higher at the highest levels of exercise. Higher levels of HDL-C were generally accompanied by lower levels of triacylglycerol. When HDL-C was compared by exercise level within each WHR tertile and %BF tertile, the association of exercise with HDL-C diminished. Saturated fat intake was not associated with HDL-C.

CONCLUSIONS/APPLICATIONS

Increased exercise is associated with a lower WHR and subsequently a higher HDL-C level. This association between WHR and HDL-C appears to be mediated through %BF. Women exercisers with the highest WHR had consistently more favorable plasma lipid profiles and lower mean body mass index and %BF than nonexercisers. Thus, for women who exhibit abdominal obesity, exercise mitigates the association of WHR with HDL-C level. Vigorous exercise in the premenopausal years may promote a more favorable lipid profile, even in the presence of increased body fat and abdominal girth.

On the bootstrap and monotone likelihood in the cox proportional hazards regression model

Recent literature has provided encouragement for using the bootstrap for inference on regression parameters in the Cox proportional hazards (PH) model. However, generating and performing the necessary partial likelihood computations on multitudinous bootstrap samples greatly increases the chances of incurring problems with monotone likelihood at some point in the analysis. The only symptom of monotone likelihood may be a failure to converge in the numerical maximization procedure, and so the problem might naïvely be dismissed by deleting the offending data set and replacing it with a new one. This strategy is shown to lead to potentially high selection biases in the subsequent summary statistics. This note discusses the importance of keeping track of these monotone likelihood cases and provides recommendations for their use in interpreting bootstrap findings, and for avoiding unwanted biases that may result from high rates of occurrence. In many cases, high monotone likelihood rates indicate that a more highly-specified model may be preferred. Special consideration is given to the problem of high monotone likelihood incidence in Monte Carlo studies of the bootstrap.

Application of recombinant bovine viral diarrhea virus proteins in the diagnosis of bovine viral diarrhea infection in cattle

The National Animal Disease Laboratory (NADL) vaccine strain of bovine viral diarrhea virus (BVDV) genes for gp48 and p80 were expressed in Escherichia coli. The BVDV-NADL gene for gp62 was integrated into a baculovirus genome for expression in Spodoptera frugiperda (Sf-9) insect ovarian cells. The antigenicity of baculovirus expressed BVDV protein was detected by anti-BVDV specific antibodies in an enzyme-linked immunosorbent assay (ELISA), indirect immunofluorescent assay (IFA) and radio-immunoprecipitation (RIP). The recombinant proteins isolated from bacteria showed antigenic properties when analyzed by ELISA and immunoblotting using BVDV antibodies. The recombinant proteins were then used in ELISA or IFA to detect BVDV infection by testing 54 independent bovine serum samples. The baculovirus-expressed BVDV protein was used as an ELISA and IFA antigen, and the bacteria-expressed proteins were used as ELISA antigens. BVDV-NADL-infected Madin-Darby bovine kidney (MDBK) cell monolayers served as a control antigen. Statistical analysis showed a high degree of correlation between the reactivity of recombinants and natural antigens in ELISA using bovine sera. The results of ELISA or IFA proved there is a high degree of correlation with the virus neutralization. In the comparative ELISA assays, the insect-cell-mediated expression revealed greater specificity and sensitivity than the bacterial expression or the natural BVDV antigens produced by cell cultures.

Bootstrapping regression parameters in multivariate survival analysis

Bootstrap methods are proposed for estimating sampling distributions and associated statistics for regression parameters in multivariate survival data. We use an Independence Working Model (IWM) approach, fitting margins independently, to obtain consistent estimates of the parameters in the marginal models. Resampling procedures, however, are applied to an appropriate joint distribution to estimate covariance matrices, make bias corrections, and construct confidence intervals. The proposed methods allow for fixed or random explanatory variables, the latter case using extensions of existing resampling schemes (Loughin, 1995), and they permit the possibility of random censoring. An application is shown for the viral positivity time data previously analyzed by Wei, Lin, and Weissfeld (1989). A simulation study of small-sample properties shows that the proposed bootstrap procedures provide substantial improvements in variance estimation over the robust variance estimator commonly used with the IWM.