Generalized P-values and confidence intervals: a novel approach for analyzing lognormally distributed exposure data

Systematic review with meta-analysis of relative risk of prolonged times to tracheal extubation with desflurane versus sevoflurane or isoflurane

The objective of this systematic review was to estimate the relative risk of prolonged times to tracheal extubation with desflurane versus sevoflurane or isoflurane. Prolonged times are defined as ≥15 min from end of surgery (or anesthetic discontinuation) to extubation in the operating room. They are associated with reintubations, naloxone and flumazenil administration, longer times from procedure end to operating room exit, greater differences between actual and scheduled operating room times, longer times from operating room exit to next case start, longer durations of the workday, and more operating room personnel idle while waiting for extubation. Published randomized clinical trials of humans were included. Generalized pivotal methods were used to estimate the relative risk of prolonged extubation for each study from reported means and standard deviations of extubation times. The relative risks were combined using DerSimonian-Laird random effects meta-analysis with Knapp-Hartung adjustment. From 67 papers, there were 78 two-drug comparisons, including 5167 patients. Studies were of high quality (23/78) or moderate quality (55/78), the latter due to lack of blinding of observers to group assignment and/or patient attrition because patients were extubated after operating room exit. Desflurane resulted in a 65% relative reduction in the incidence of prolonged extubation compared with sevoflurane (95% confidence interval 49% to 76%, P < .0001) and in a 78% relative reduction compared with isoflurane (58% to 89%, P = .0001). There were no significant associations between studies' relative risks and quality, industry funding, or year of publication (all six meta-regressions P ≥ .35). In conclusion, when emergence from general anesthesia with different drugs are compared with sevoflurane or isoflurane, suitable benchmarks quantifying rapidity of emergence are reductions in the incidence of prolonged extubation achieved by desflurane, approximately 65% and 78%, respectively. These estimates give realistic context for interpretation of results of future studies that compare new anesthetic agents to current anesthetics.

Exceedance Probabilities of Log-normal Distributions for One Group, Two Groups, and Meta-analysis of Multiple Two-group Studies, With Application to Analyses of Prolonged Times to Tracheal Extubation

Many randomized trials measure means and standard deviations of anesthesia recovery time (e.g., times to tracheal extubation). We show how to use generalized pivotal methods to compare the probabilities of exceeding a tolerance limit (e.g., > 15 min, prolonged times to tracheal extubation). The topic is important because the economic benefits of faster anesthesia emergence depend on reducing variability, not means, especially prevention of very long recovery times. Generalized pivotal methods are applied using computer simulation (e.g., using two Excel formulas for one group and three formulas for two group comparisons). The endpoint for each study with two groups is the ratio between groups of the probabilities of times exceeding a threshold or the ratio of the standard deviations. Confidence intervals and variances for the incremental risk ratio of the exceedance probabilities and for ratios of standard deviations are calculated using studies' sample sizes, sample means in the time scale of recovery times, and sample standard deviations in the time scale. Ratios are combined among studies using the DerSimonian-Laird estimate of the heterogeneity variance estimate, with Knapp-Hartung adjustment for the relatively small (N = 15) numbers of studies in the meta-analysis. We show larger absolute variability among studies' results when analyzed based on exceedance probabilities rather than standard deviations. Therefore, if an investigator's primary goal is to quantify reductions in the variability of recovery times (e.g., times until patients are ready for post-anesthesia care unit discharge), we recommend analyzing the standard deviations. When exceedance probabilities themselves are relevant, they can be analyzed from the original studies' summary measures.

Shrinkage estimation of long-term water ingestion rates

BACKGROUND

Water consumption is a necessity for human life, though it also presents an opportunity for exposure to harmful chemicals and toxins. In order to gain a better understanding of the potential levels of chronic exposure, accurate estimates of long-term water consumption are needed.

OBJECTIVE

The objective of this study is to estimate long-term water consumption using a nationally representative sample of the US population.

METHODS

In this study, we use a random effects model to obtain shrinkage estimates of average daily water consumption for National Health and Nutrition Examination Survey (NHANES) participants from 2005 to 2010, and compare to their empirical 2-day averages.

RESULTS

Our results demonstrate that the shrinkage estimates yielded a reduction in estimated mean water consumption. The 95th percentile was reduced from 3292 to 2529 ml/day. In addition, standard deviation of water consumption for this group decreased from 1052 to 688 ml/day. Similar reductions in the mean and variance were observed stratifying by age and race.

SIGNIFICANCE

Random effects models may provide a more accurate measure of daily water consumption and could be utilized for future exposure and risk assessments.

A Bayesian approach to construct confidence intervals for comparing the rainfall dispersion in Thailand

Natural disasters such as drought and flooding are the consequence of severe rainfall fluctuation, and rainfall amount data often contain both zero and positive observations, thus making them fit a delta-lognormal distribution. By way of comparison, rainfall dispersion may not be similar in enclosed regions if the topography and the drainage basin are different, so it can be evaluated by the ratio of variances. To estimate this, credible intervals using the highest posterior density based on the normal-gamma prior (HPD-NG) and the method of variance estimates recovery (MOVER) for the ratio of delta-lognormal variances are proposed. Monte Carlo simulation was used to assess the performance of the proposed methods in terms of coverage probability and relative average length. The results of the study reveal that HPD-NG performed very well and was able to meet the requirements in various situations, even with a large difference between the proportions of zeros. However, MOVER is the recommended method for equal small sample sizes. Natural rainfall datasets for the northern and northeastern regions of Thailand are used to illustrate the practical use of the proposed credible intervals.

A simple method for assessing occupational exposure via the one-way random effects model

A one-way random effects model is postulated for the log-transformed shift-long personal exposure measurements, where the random effect in the model represents an effect due to the worker. Simple closed-form confidence intervals are proposed for the relevant parameters of interest using the method of variance estimates recovery (MOVER). The performance of the confidence bounds is evaluated and compared with those based on the generalized confidence interval approach. Comparison studies indicate that the proposed MOVER confidence bounds are better than the generalized confidence bounds for the overall mean exposure and an upper percentile of the exposure distribution. The proposed methods are illustrated using a few examples involving industrial hygiene data.

Occupational exposure to asthmagens and adult onset wheeze and lung function in people who did not have childhood wheeze: A 50-year cohort study

BACKGROUND

There are few prospective studies that relate the development of adult respiratory disease with exposure to occupational asthmagens.

OBJECTIVE

To evaluate the risk of adult onset wheeze (AOW) and obstructive lung function associated with occupational exposures over 50years.

METHODS

A population-based randomly selected cohort of children who had not had asthma or wheezing illness, recruited in 1964 at age 10-15years, was followed-up in 1989, 1995, 2001 and 2014 by spirometry and respiratory questionnaire. Occupational histories were obtained in 2014 and occupational exposures determined with an asthma-specific job exposure matrix. The risk of AOW and lung function impairment was analysed in subjects without childhood wheeze using logistic regression and linear mixed effects models.

RESULTS

All 237 subjects (mean age: 61years, 47% male, 52% ever smoked) who took part in the 2014 follow-up had completed spirometry. Among those who did not have childhood wheeze, spirometry was measured in 93 subjects in 1989, in 312 in 1995 and in 270 subjects in 2001 follow-up. For longitudinal analysis of changes in FEV1 between 1989 and 2014 spirometry records were available on 191 subjects at three time points and on 45 subjects at two time points, with a total number of 663 records. AOW and FEV1<LLN were associated with occupational exposure to food-related asthmagens (adjusted odds ratios (adjORs) 95% CI: 2.7 [1.4, 5.1] and 2.9 [1.1, 7.7]) and biocides/fungicides (adjOR 95% CI: 1.8 [1.1, 3.1] and 3.4 [1.1, 10.8]), with evident dose-response effect (p-trends<0.05). Exposure to food-related asthmagens was also associated with reduced FEV1, FVC and FEF25-75% (adjusted regression coefficients 95% CI: -7.2 [-12.0, -2.4], -6.2 [-10.9, -1.4], and -13.3[-23.4, -3.3]). Exposure to wood dust was independently associated with AOW, obstructive lung function and reduced FEF25-75%. Excess FEV1 decline of 6-8ml/year was observed with occupational exposure to any asthmagen, biocides/fungicides and food-related asthmagens (p<0.05).

CONCLUSIONS

This longitudinal study confirmed previous findings of increased risks of adult onset wheezing illness with occupational exposure to specific asthmagens. A novel finding was the identification of food-related asthmagens and biocides/fungicides as potential new occupational risk factors for lung function impairment in adults without childhood wheeze.

Standardized likelihood ratio test for comparing several log-normal means and confidence interval for the common mean

Standardized likelihood ratio test (SLRT) for testing the equality of means of several log-normal distributions is proposed. The properties of the SLRT and an available modified likelihood ratio test (MLRT) and a generalized variable (GV) test are evaluated by Monte Carlo simulation and compared. Evaluation studies indicate that the SLRT is accurate even for small samples, whereas the MLRT could be quite liberal for some parameter values, and the GV test is in general conservative and less powerful than the SLRT. Furthermore, a closed-form approximate confidence interval for the common mean of several log-normal distributions is developed using the method of variance estimate recovery, and compared with the generalized confidence interval with respect to coverage probabilities and precision. Simulation studies indicate that the proposed confidence interval is accurate and better than the generalized confidence interval in terms of coverage probabilities. The methods are illustrated using two examples.

Comparison of means of two lognormal distributions based on samples with multiple detection limits

The problem of comparing the means of two lognormal distributions based on samples with multiple detection limits is considered. Tests and confidence intervals for the ratio of the two means, based on pivotal quantities involving the maximum likelihood estimators, are proposed. The merits of the proposed approaches are evaluated by Monte Carlo simulation. Simulation study indicates that the procedures are satisfactory in terms of coverage probabilities of confidence intervals, and powers of tests. The proposed approach can also be applied to find confidence intervals for the difference between the means of the two lognormal distributions. Illustrative examples with a real data set and with a simulated data set are given.

The symmetric-range accuracy under a one-way random model with balanced or unbalanced data

The symmetric-range accuracy A of a sampler is defined as the fractional range, symmetric about the true concentration, that includes a specified proportion of sampler measurements. In this article, we give an explicit expression for A assuming that the sampler measurements follow a one-way random model so as to capture different components of variability, for example, variabilities among and within different laboratories or variabilities among and within exposed workers. We derive an upper confidence limit for A based on the concept of a 'generalized confidence interval'. A convenient approximation is also provided for computing the upper confidence limit. Both balanced and unbalanced data situations are investigated. Monte Carlo evaluation indicates that the proposed upper confidence limit is satisfactory even for small samples. The statistical procedures are illustrated using an example.

Retrospective assessment of occupational exposure to whole-body vibration for a case-control study

Occupational whole-body vibration is often studied as a risk factor for conditions that may arise soon after exposure, but only rarely have studies examined associations with conditions arising long after occupational exposure has ceased. We aimed to develop a method of constructing previous occupational whole-body vibration exposure metrics from self-reported data collected for a case-control study of Parkinson's disease. A detailed job history and exposure interview was administered to 808 residents of British Columbia, Canada (403 people with Parkinson's disease and 405 healthy controls). Participants were prompted to report exposure to whole-body vibrating equipment. We limited the data to exposure reports deemed to be above background exposures and used the whole-body vibration literature (typically reporting on seated vector sum measurements) to assign intensity (acceleration) values to each type of equipment reported. We created four metrics of exposure (duration of exposure, most intense equipment exposure, and two dose metrics combining duration and intensity) and examined their distributions and correlations. We tested the role of age and gender in predicting whole-body vibration exposure. Thirty-six percent of participants had at least one previous occupational exposure to whole-body vibrating equipment. Because less than half of participants reported exposure, all continuous metrics exhibited positively skewed distributions, although the distribution of most intense equipment exposure was more symmetrically distributed among the exposed. The arithmetic mean of duration of exposure among those exposed was 14.0 (standard deviation, SD: 14.2) work years, while the geometric mean was 6.8 (geometric SD, GSD: 4.5). The intensity of the most intense equipment exposure (among the exposed) had an arithmetic mean of 0.9 (SD: 0.3) m·s(-2) and a geometric mean of 0.8 (GSD: 1.4). Male gender and older age were both associated with exposure, although the effect of age was attenuated after adjustment for gender. The methods developed allowed us to create continuous metrics of whole-body vibration retrospectively, displaying useful variance for epidemiologic studies.

Upper limits for exceedance probabilities under the one-way random effects model

In this article, we propose statistical methods for setting upper limits on (i) the probability that the mean exposure of an individual worker exceeds the occupational exposure limit (OEL) and (ii) the probability that the exposure of a worker exceeds the OEL. The proposed method for (i) is obtained using the generalized variable approach, and the one for (ii) is based on an approximate method for constructing one-sided tolerance limits in the one-way random effects model. Even though tolerance limits can be used to assess the proportion of exposure measurements exceeding the OEL, the upper limits on these probabilities are more informative than tolerance limits. The methods are conceptually as well as computationally simple. Two data sets involving industrial exposure data are used to illustrate the methods.