Bonferroni Procedure Research Articles

In Vitro Evaluation of Root Surface Temperature Using Different Endodontic Filling Techniques

Depending on the obturation technique, the tooth and surrounding tissues may heat up during root canal filling, particularly with warm methods. This study aimed to analyze the temperature increase in the periradicular and -apical region during various warm obturation techniques with a present simulated periodontal blood flow. Seventy-five extracted human teeth were shortened to 11 mm (cut-grinder Primus diamond cutting device; Walter Messner GmbH, Oststeinbek, Germany) and prepared using the ProTaper Gold system (Dentsply Sirona Inc., Charlotte, NC, USA) ISO size 40/.06. Specimens were prepared to ensure stable fluid circulation in an artificially created periodontal space, and the procedure was recorded with a thermal infrared camera (VarioCAM HD; InfraTec GmbH Infrarotsensorik und Messtechnik, Dresden, Germany). The following obturation methods were applied: I, cold single-cone obturation (control group); II, gutta-percha-coated rigid carrier technique (GuttaFusion); III, squirting technique (injection technique); IV, continuous wave technique; and V, Schilder technique. Statistical analysis was performed using the Kruskal–Wallis test, followed by the Mann–Whitney pairwise test using the sequential Bonferroni procedure for significant differences (p < 0.05). The Schilder technique with 0 mL/min showed the lowest temperature change, with a median of 0.00 °C (max. 0.00 °C, min. 0.00 °C, IQR 0.00 °C). In contrast, the continuous wave technique at a circulation rate of 2.6 mL/min exhibited the highest temperature change, with a median of 3.76 °C (max. 5.33 °C, min. 2.42 °C, IQR 1.46 °C). Although warm obturation techniques can increase surface temperature, none of the methods produced changes that were potentially damaging to the periodontium or surrounding bone.

On limiting behaviors of stepwise multiple testing procedures

AbstractStepwise multiple testing procedures have attracted several statisticians for decades and are also quite popular with statistics users because of their technical simplicity. The Bonferroni procedure has been one of the earliest and most prominent testing rules for controlling the familywise error rate (FWER). A recent article established that the FWER for the Bonferroni method asymptotically (i.e., when the number of hypotheses becomes arbitrarily large) approaches zero under any positively equicorrelated multivariate normal framework. However, similar results for the limiting behaviors of FWER of general stepwise procedures are nonexistent. The present work addresses this gap in a unified manner by elucidating that, under the multivariate normal setups with some correlation structures, the probability of rejecting one or more null hypotheses approaches zero asymptotically for any step-down procedure. Consequently, the FWER and power of the step-down procedures also tend to be asymptotically zero. We also establish similar limiting zero results on FWER of other popular multiple testing rules, e.g., Hochberg’s and Hommel’s procedures. It turns out that, within our chosen asymptotic framework, the Benjamini–Hochberg method can hold the FWER at a strictly positive level asymptotically under the equicorrelated normality.

Multiple testing of interval composite null hypotheses using randomized p-values

Equivalence tests are statistical hypothesis testing procedures that aim to establish practical equivalence rather than the usual statistical significant difference. These testing procedures are frequent in “bioequivalence studies," where one would wish to show that, for example, an existing drug and a new one under development have comparable therapeutic effects. In this article, we propose a two-stage randomized (RAND2) p-value that depends on a uniformly most powerful (UMP) p-value and an arbitrary tuning parameter c∈[0,1]\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$c\\in [0,1]$$\\end{document} for testing an interval composite null hypothesis. We investigate the behavior of the distribution function of the two p-values under the null hypothesis and alternative hypothesis for a fixed significance level t∈(0,1)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$t\\in (0,1)$$\\end{document} and varying sample sizes. We evaluate the performance of the two p-values in estimating the proportion of true null hypotheses in multiple testing. We conduct a family-wise error rate control using an adaptive Bonferroni procedure with a plug-in estimator to account for the multiplicity that arises from our multiple hypotheses under consideration. The various claims in this research are verified using a simulation study and real-world data analysis.

Abstract PO4-02-13: Parity and age first full term pregnancy affects the age of breast cancer diagnosis in breast cancer subtypes defined by estrogen receptor and human epidermal growth factor receptor 2

Abstract Background: Reproductive factors like parity and age at first full term pregnancy (FTP1) are found to have an impact on the occurrence of breast cancer (BC) in many epidemiological studies. Importantly, since the 70s, an ongoing trend to postpone FTP1 and have less children is observed. Additionally, there is an increasing trend for breast cancer incidence in young women in the past several decades, which may match the changing exposures to reproductive factors over time. To our knowledge, few studies focus on the association between parity, FTP1 and the age of breast cancer diagnosis. In this study, we aimed at studying the association between age at breast cancer diagnosis and reproductive factors (parity and FTP1) in each of the four breast cancer subtypes defined by estrogen receptor (ER) and human epidermal growth factor receptor 2 (HER2). Patients and method: We considered patients who were >34 years old and were diagnosed and/or treated for early BC in University Hospitals Leuven between January 2000 and November 2020. Patient and tumor characteristics were extracted from the patient files. Missing values were filled in by multiple imputation. A linear mixed model with birth cohorts as random effects was built for premenopausal and postmenopausal patients separately to investigate the association between two reproductive factors (parity and age at first full term pregnancy) and age at diagnosis in each of four breast cancer subtypes defined by ER and HER2. ER positivity was defined as >1% of cells staining positive and reflex fluorescence in situ hybridization (FISH) testing was performed for samples that immunohistochemically (IHC) stained for HER2 with IHC score of 2+ or 3+. Parous women are classified into low parity (1 or 2 children) and high parity (≥ 3 children) and FTP1 was divided into < or ≥ 27 years of age. BMI was considered a possible confounder and was corrected for. We first excluded nulliparous people and compared the mean ages at diagnosis in different parity groups and FTP1 groups separately. We created new variable reproductive patterns by taking intersection of parity categories and FTP1 categories. Then the mean ages at diagnosis in parous groups could be compared with the mean age at diagnosis in nulliparous patients. Step down Bonferroni procedure is applied to correct for multiple comparisons. Result: 3039 premenopausal patients and 6569 postmenopausal patients at breast cancer diagnosis were included in the study. Patients with early age at FTP1 have older age at diagnosis in case of ER+HER2+ BC in both premenopausal and postmenopausal group as compared to patients with late FTP1 (Table 1). For premenopausal patients with ER-HER2+, early age at FTP1 was associated with older age at diagnosis in comparison to late age at FTP1. Premenopausal patients with ER+HER2- BC that had low parity and late FTP1 were diagnosed 0.66 years later than nulliparous patients (p= 0,01). Conclusion: In both premenopausal and postmenopausal parous patients with early FTP1, an older age at diagnosis was observed in HER2+ cases only. When compared to nulliparous patients, the combination of low parity and late FTP1 was associated with older age at diagnosis for premenopausal patients with ER+ HER2- BC. Table 1 Differences in mean age at diagnosis between FTP1 groups in parous patients Menopause Subtype Comparison Estimate (difference in mean age at diagnosis) p-value pre ER+HER2+ <27 vs >=27 1,2030 0,0045 ER+HER2- <27 vs >=27 -0,0548 0,7468 ER-HER2+ <27 vs >=27 1,3519 0,0334 ER-HER2- <27 vs >=27 0,4023 0,3326 post ER+HER2+ <27 vs >=27 1,1764 0,0175 ER+HER2- <27 vs >=27 0,0743 0,7069 ER-HER2+ <27 vs >=27 -0,3750 0,6023 ER-HER2- <27 vs >=27 0,3862 0,3815 Citation Format: Jiumeng Zhang, Zhao Liu, Karen Van Baelen, Maja Vangoitsenhoven, Hans Wildiers, Adelheid Soubry, Patrick Neven. Parity and age first full term pregnancy affects the age of breast cancer diagnosis in breast cancer subtypes defined by estrogen receptor and human epidermal growth factor receptor 2 [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO4-02-13.

Efficacy and safety of ocrelizumab in patients with relapsing multiple sclerosis: Real-world experience of two Swiss multiple sclerosis centers

BackgroundOcrelizumab (OCR) is a humanized monoclonal antibody directed against CD-20 positive lymphocytes, mainly B-lymphocytes. OCR is approved for treatment of primary progressive (PPMS) and relapsing multiple sclerosis (RMS). This study aims to provide real-world safety and efficacy data of people with RMS treated with OCR in two Swiss Multiple Sclerosis (MS) centers. MethodsWe have conducted a retrospective data analysis using the patient cohorts from the Cantonal Hospital Aarau and Bern University Hospital (RMS: n = 235). Statistical analyses were performed with Mann–Whitney U-Test, Chi-squared test and Spearman-Rho-Correlation. Adjustment for multiple testing was performed by Bonferroni procedure. ResultsAfter initiation of OCR, there was a decrease in disease activity in RMS patients. In our study, 152/190 (80.0 %) RMS patients fulfilled the criteria for NEDA-3 12 months and 88/104 (84.6 %) showed NEDA-3 24 months after OCR initiation. The most frequent adverse events (AEs) in our study were infections, taking place in 78/235 (33.2 %) RMS patients. COVID-19 was the most common infection, followed by urinary infections and other respiratory infections and infectious adverse events occurred significantly more frequent in patients with reduced IgG serum concentration. ConclusionsOur real-world study showed OCR being associated with low rates of any type of MS disease activity as indicated by NEDA-3. The adverse event profile is comparable to the known events especially infections and an association between infections and reduced IgG serum concentration was found.

Modifying the false discovery rate procedure based on the information theory under arbitrary correlation structure and its performance in high-dimensional genomic data

BackgroundControlling the False Discovery Rate (FDR) in Multiple Comparison Procedures (MCPs) has widespread applications in many scientific fields. Previous studies show that the correlation structure between test statistics increases the variance and bias of FDR. The objective of this study is to modify the effect of correlation in MCPs based on the information theory. We proposed three modified procedures (M1, M2, and M3) under strong, moderate, and mild assumptions based on the conditional Fisher Information of the consecutive sorted test statistics for controlling the false discovery rate under arbitrary correlation structure. The performance of the proposed procedures was compared with the Benjamini–Hochberg (BH) and Benjamini–Yekutieli (BY) procedures in simulation study and real high-dimensional data of colorectal cancer gene expressions. In the simulation study, we generated 1000 differential multivariate Gaussian features with different levels of the correlation structure and screened the significance features by the FDR controlling procedures, with strong control on the Family Wise Error Rates.ResultsWhen there was no correlation between 1000 simulated features, the performance of the BH procedure was similar to the three proposed procedures. In low to medium correlation structures the BY procedure is too conservative. The BH procedure is too liberal, and the mean number of screened features was constant at the different levels of the correlation between features. The mean number of screened features by proposed procedures was between BY and BH procedures and reduced when the correlations increased. Where the features are highly correlated the number of screened features by proposed procedures reached the Bonferroni (BF) procedure, as expected. In real data analysis the BY, BH, M1, M2, and M3 procedures were done to screen gene expressions of colorectal cancer. To fit a predictive model based on the screened features the Efficient Bayesian Logistic Regression (EBLR) model was used. The fitted EBLR models based on the screened features by M1 and M2 procedures have minimum entropies and are more efficient than BY and BH procedures.ConclusionThe modified proposed procedures based on information theory, are much more flexible than BH and BY procedures for the amount of correlation between test statistics. The modified procedures avoided screening the non-informative features and so the number of screened features reduced with the increase in the level of correlation.

Characteristics of Design and Analysis of Ophthalmic Randomized Controlled Trials: A Review of Ophthalmic Papers 2020-2021.

To evaluate the recent practice of design and statistical analysis of ophthalmic randomized clinical trials (RCTs). Review of 96 ophthalmic RCTs. Two authors (R.D., G.S.Y.) reviewed primary result papers published from January 2020 through December 2021 in Ophthalmology, JAMA Ophthalmology, American Journal of Ophthalmology, and British Journal of Ophthalmology. Data were extracted and analyzed for the characteristics of design (1-eye design, 2-eye design, paired-eye design, and subject design), sample size and power, and statistical analysis for intereye correlation adjustment, missing data, and correction for multiplicity. Characteristics of trial design and statistical analysis. Among 96 RCTs, 50 (52%) used 1-eye design, 21 (22%) 2-eye design, 10 (10%) paired-eye design, and 15 (16%) subject design. In 31 trials of 2-eye design or paired-eye design, 18 (58%) trials had suboptimal analysis of data from both eyes by analyzing data from 1 eye (n= 10), taking the average of 2 eyes (n= 2), analyzing 2 eyes separately (n= 1), ignoring intereye correlation (n= 3), or not specifying how 2-eye data were analyzed (n= 2), and 13 trials (42%) properly adjusted the intereye correlation by using the mixed-effects model (n= 6), paired t test (n= 5), generalized estimating equations (n= 1), or marginal Cox regression model (n= 1). Among 96 trials, 75 (78%) provided both sample size and statistical power estimation, and 16 (17%) trials described statistical test for sample size or power estimation. Missing data in primary outcome occurred in 86 (90%) trials with a median missing data rate of 8%, 32 (37%) trials applied statistical methods for missing data, including last value carried forward (n= 10), multiple imputation (n= 14), or other approaches (n= 8). Among 25 trials with > 2 arms, 16 (64%) corrected for multiplicity using the Bonferroni procedure (n= 8), Hochberg procedure (n= 2), Gatekeeping procedure (n= 2), or hierarchical procedure (n= 4). Among 16 trials with multiple primary outcomes, 4 (25%) corrected for multiplicity by the Bonferroni procedure. There are opportunities for improvement in the design and statistical analyses of ophthalmic trials, particularly in the aspects of adjustment for intereye correlation, missing data, and multiplicity. Continuing education in ophthalmology and vision research community may improve the quality of ophthalmic trials. Proprietary or commercial disclosure may be found after the references.

Exploring the Clinical Feasibility of Alternative Word-Understanding Measures for Autistic Children With Minimal Spoken Language.

The primary aim of this study was to explore the clinical feasibility of using alternate word-understanding assessment modalities for autistic children who have minimal verbal skills. Specifically, assessment duration, occurrence of disruptive behavior, and no-response trials were examined across three word-understanding assessment conditions: a low-tech condition, a touchscreen condition, and a condition that used real-object stimuli. A secondary aim was to examine the relationship between disruptive behavior and assessment outcomes. Twenty-seven autistic children between the ages of 3 and 12 years who had minimal verbal skills completed 12 test items on the three assessment conditions. Repeated-measures analyses of variance with post hoc Bonferroni procedures were used to describe and compare assessment duration, occurrence of disruptive behavior, and no-response trials across conditions. A Spearman rank-order correlation coefficient was used to examine the relationship between disruptive behavior and assessment outcomes. The real-object assessment condition took significantly longer than the low-tech and touchscreen conditions. Participants engaged in disruptive behavior most frequently during the low-tech condition; however, differences among conditions were not significant. There were significantly more no-response trials in the low-tech condition than in the touchscreen condition. There was a significant, weak negative correlation between disruptive behavior and experimental assessment outcomes. Results show there is promise in using real objects and touchscreen devices to assess word understanding in autistic children who have minimal verbal skills.

Contrast-enhanced mammography in the assessment of residual disease after neoadjuvant treatment.

To investigate the utility of contrast-enhanced mammography (CEM) as an alternative to breast MRI for the evaluation of residual disease after neoadjuvant treatment (NAT). This prospective study enrolled consecutive women undergoing NAT for breast cancer from July 2017-July 2019. Breast MRI and CEM exams performed after completion of NAT were read independently by two breast radiologists. Residual disease and lesion size on MRI and CEM recombined (RI) and low-energy images (LEI) were compared. Histopathology was considered the reference standard. Statistical analysis was performed using McNemar's and Leisenring's tests. Multiple comparison adjustment was made using Bonferroni procedure. Lesion sizes were correlated using Kendall's tau coefficient. There were 110 participants with 115 breast cancers. Residual disease (invasive cancer or ductal carcinoma in situ) was detected in 83/115 (72%) lesions on pathology, 71/115 (62%) on MRI, 55/115 (48%) on CEM RI, and 75/115 (65%) on CEM LEI. When using multiple comparison adjustment, no significant differences were detected between MRI combined with CEM LEI and CEM RI combined with CEM LEI, in terms of accuracy (MRI: 77%, CEM: 72%; p ≥ 0.99), sensitivity (MRI: 88%, CEM: 81%; p ≥ 0.99), specificity (MRI: 47%, CEM: 50%; p ≥ 0.99), PPV (MRI: 81%, CEM: 81%; p ≥ 0.99), or NPV (MRI: 60%, CEM: 50%; p ≥ 0.99). Size correlation between pathology and both MRI combined with CEM LEI and CEM RI combined with CEM LEI was moderate: τ = 0. 36 vs 0.33 (p ≥ 0.99). Contrast-enhanced mammography is an acceptable alternative to breast MRI for the detection of residual disease after neoadjuvant treatment.

An assessment of differential supplier category performance in the agro processing industry: A case for supplier development in the Zimbabwean tobacco industry

This study sought to determine whether farm categories influence the key agro business supply chain metric of crop yield. The investigated farm categories are the communal farms, A1 farms, A2 farms, and commercial farms that reflect the agricultural structure that emerged from the post-fast-track land reform programme in Zimbabwe. Secondary data for crop yield was collected from the Tobacco Industry and Marketing Board publications of a five-year period spanning from 2014-2018. Tobacco Industry and Marketing Board is the regulatory authority of the Zimbabwean tobacco industry. The study used One-way ANOVA to test the specified hypotheses. A post hoc test was conducted using the Bonferroni procedure. The results indicated that crop yield is a function of the farm category. Communal farms had low crop yield, while A1 farm models proved to be very productive as evidenced by higher crop yield than any other farm category. A2 farms and commercial farms had unexpectedly low crop yield. The study recommended consolidation and transformation of communal areas into small-to-medium plots for the purposes of improving their agricultural viability, while at the same time downsizing the redundant A2 and commercial farms into small scale plots for the purposes of improving their efficiency. The study also recommended entering into resource-providing contract farming with A2 farmers whose current low yield might be due to lack of adequate input resources.

Simultaneous detection of novel genes and SNPs by adaptive p-value combination.

Combining SNP p-values from GWAS summary data is a promising strategy for detecting novel genetic factors. Existing statistical methods for the p-value-based SNP-set testing confront two challenges. First, the statistical power of different methods depends on unknown patterns of genetic effects that could drastically vary over different SNP sets. Second, they do not identify which SNPs primarily contribute to the global association of the whole set. We propose a new signal-adaptive analysis pipeline to address these challenges using the omnibus thresholding Fisher's method (oTFisher). The oTFisher remains robustly powerful over various patterns of genetic effects. Its adaptive thresholding can be applied to estimate important SNPs contributing to the overall significance of the given SNP set. We develop efficient calculation algorithms to control the type I error rate, which accounts for the linkage disequilibrium among SNPs. Extensive simulations show that the oTFisher has robustly high power and provides a higher balanced accuracy in screening SNPs than the traditional Bonferroni and FDR procedures. We applied the oTFisher to study the genetic association of genes and haplotype blocks of the bone density-related traits using the summary data of the Genetic Factors for Osteoporosis Consortium. The oTFisher identified more novel and literature-reported genetic factors than existing p-value combination methods. Relevant computation has been implemented into the R package TFisher to support similar data analysis.

Role of sortilin 1 (SORT1) on fatty acid-mediated cholesterol metabolism in primary calf hepatocytes.

Ketosis is a common metabolic disorder in peripartal dairy cows that is caused by excessive mobilization of fat and incomplete hepatic metabolism of fatty acids (FFA). Recent data in nonruminant models revealed that sortilin 1 (SORT1) is involved in a variety of lipid metabolism-related diseases. It plays important roles in the regulation of triglyceride (TAG) and total cholesterol (TC) levels. In this study, we first used liver biopsies from healthy cows (serum β-hydroxybutyrate concentration <0.6 mM) and cows diagnosed with clinical ketosis (serum β-hydroxybutyrate concentration >3.0 mM) to assess alterations in cholesterol synthesis, transport, and excretion. Then, to assess mechanistic links between SORT1 and fatty acid-mediated cholesterol metabolism, hepatocytes isolated from 4 healthy female calves (1 d old, 35-45 kg) were challenged with or without a mixture of free fatty acids (FFA; 1.2 mM) to induce metabolic stress. Hepatocytes were then treated with empty adenovirus vectors (with green fluorescent protein; Ad-GFP) or with SORT1-overexpressing adenovirus (Ad-SORT1) for 6 h or with SORT1 inhibitor (SORT1i) for 2 h, followed by a challenge with (Ad-GFP+FFA, Ad-SORT1+FFA, or SORT1i+FFA) or without (Ad-GFP, Ad-SORT1, or SORT1i) 1.2 mM FFA mixture for 12 h. Data analysis of calf hepatocyte treatment comparisons were assessed by 2-way ANOVA, and multiplicity for each experiment was adjusted using the Bonferroni procedure. Expression levels of factors related to cholesterol synthesis, transport, and excretion in liver tissue of cows with ketosis was lower. Hepatocytes challenged with FFA had lower concentrations of TC and mRNA and protein abundances of sterol regulatory element-binding protein 2 (SREBF2), acetyl acyl coenzyme A-cholesterol acyltransferase 2 (ACAT2), ATP-binding cassette transporter A1 (ABCA1), ABC subfamily G member 5 (ABCG5), and ABC subfamily G member 8 (ABCG8). Compared with FFA challenge alone, SORT1i + FFA led to greater protein abundance of 3-hydroxy-3-methyl-glutaryl coenzyme A reductase (HMGCR), ACAT2, and ABCG5, and greater mRNA abundance of ABCG5. Compared with FFA challenge alone, SORT1 overexpression led to lower protein abundance of SREBF2. In contrast, protein abundance of ABCA1 was greater. Overall, our data suggested that exogenous FFA induced abnormal cholesterol metabolism in hepatocytes, whereas a high abundance of SORT1 affected cholesterol esterification and potentially influx into bile. Thus, downregulation of hepatic SORT1 might be a cholesterol-regulated protective mechanism in the presence of a marked increase in FFA.

Mathematical modelling of Hass avocado firmness by using destructive and non-destructive devices at different maturity stages and under two storage conditions

Abstract Devices which are used to determine firmness of non-destructive nature do not penetrate the skin or damage the underlying flesh of the fruit and do provide real-time results, avoid raw biomass loss and allow the testing of every individual fruit and repeated testing of the same fruit, thus providing many advantages for researchers and the industry alike. Contrarily, destructive methods puncture the fruit and thus only a subsample, selected to represent all fruit, can be tested. In addition, different operators can generate quite different values for the same fruit using a hand-held penetrometer. Hass avocado from two commercial orchards was collected, and fruit firmness was measured at harvest, during two storage conditions controlled atmosphere (CA) and regular air (RA), during shelf-life and at the ready-to-eat stage using both destructive (Fruit Pressure Tester, mod. FT327, Wagner Instruments, Greenwich, USA) and non-destructive devices (Model TA.XT plusC, Stable Micro Systems Ltd, England). Then, the mathematical relationship between these two devices was assessed using Spearman Correlation coefficient (rho) and p-values adjusted by Benjamini-Hochberg and Bonferroni procedures. Thus, 3,200 fruits were evaluated during two harvests and two subsequent seasons. A moderate and positive association between destructive and non-destructive devices was found (rho coefficient ranging from 0.41 to 0.51). The variance explained by the regression models ranged from 0.53 to 0.63; all of them were significant with good accuracies (i.e., 0.79; 0.78; 0.73; 0.76). The results prompt us to conclude that a non-destructive texture analyser device can be used to accurately predict firmness measured by a penetrometer in Hass avocado fruit and contribute to avoiding fruit discards.

Controlling the familywise error rate when performing multiple comparisons in a linear latent variable model

In latent variable models (LVMs) it is possible to analyze multiple outcomes and to relate them to several explanatory variables. In this context many parameters are estimated and it is common to perform multiple tests, e.g. to investigate outcome-specific effects using Wald tests or to check the correct specification of the modeled mean and variance using a forward stepwise selection (FSS) procedure based on Score tests. Controlling the family-wise error rate (FWER) at its nominal level involves adjustment of the p-values for multiple testing. Because of the correlation between test statistics, the Bonferroni procedure is often too conservative. In this article, we extend the max-test procedure to the LVM framework for Wald and Score tests. Depending on the correlation between the test statistics, the max-test procedure is equivalent or more powerful than the Bonferroni procedure while also providing, asymptotically, a strong control of the FWER for non-iterative procedures. Using simulation studies, we assess the finite sample behavior of the max-test procedure for Wald and Score tests in LVMs. We apply our procedure to quantify the neuroinflammatory response to mild traumatic brain injury in nine brain regions.

Is the amino acid pattern in medical nutrition therapy crucial for successfully attenuating muscle mass loss in adult ICU patients? Secondary analysis of a RCT.

We hypothesized that in long-term immobilized intensive care unit (ICU) patients, both the quantity and quality of protein nutrition are vital in supporting muscle mass maintenance. Hence, the aim of this secondary analysis of our recently performed RCT was to calculate the intake of individual amino acids and to evaluate the potential associations of amino acid patterns with muscle mass loss during the ICU stay. Clinical and nutritional data were collected from a recent RCT conducted in long-term immobilized, critically ill patients receiving medical nutrition therapy with either 1.8g (interventional group) or 1.2g (standard group) of protein/amino acids per kg body weight per day over 4 weeks. Intake of the individual amino acids as well as the sum scores of the indispensable, conditionally indispensable, and dispensable amino acids were calculated for all patients, both group specific (n=21 in each group) and in total (n=42), based on the detailed nutrition protocols; inter-group differences were analyzed by t-tests. Linear regression models were used to test the effects of individual amino acids and the sum scores on the extent of skeletal muscle loss by measuring the quadriceps muscle layer thickness during the study period. The significance level was adjusted for multiple testing according to the Bonferroni procedure (α=0.002). In both groups, the proportion of indispensable amino acids was approximately 41% of the total exogenous protein supply, with the proportion of enteral administration slightly over 50%. The intake of conditionally indispensable amino acids (glutamine, tyrosine, cysteine, histidine, and arginine) accounted for 17% and 18% of the total amino acids in the interventional and standard groups, respectively; glutamine (5% of total amino acids) was exclusively administered enterally. The intake of dispensable amino acid varied widely, with glutamic acid, proline, and asparagine/aspartic acid representing the highest proportions (10%, 8%, and 8% of total amino acids, respectively). For all amino acids, no statistically significant association was observed between the quantitative intake and the skeletal muscle changes after terminating the intervention phase. This secondary analysis of the RCT conducted in routine clinical practice did not support our working hypothesis that the amino acid patterns of medical nutrition therapy have a statistically significant impact on the skeletal muscle loss in long-term immobilized ICU patients. Due to the limited variety of enteral/parenteral products used in this single-center study, the calculated amino acid patterns showed only small differences. Larger multi-center trials with adequate power are needed to evaluate the potential effects of the individual amino acids or defined amino acid patterns on the muscle protein metabolism in further detail. German Clinical Trials Register (http://www.drks.de); DRKS-ID: DRKS00013594.

Acetylcarnitine Is Associated With Cardiovascular Disease Risk in Type 2 Diabetes Mellitus.

ObjectiveThis study aimed to identify the association between specific short-chain acylcarnitines and cardiovascular disease (CVD) in type 2 diabetes mellitus (T2DM).MethodWe retrieved 1,032 consecutive patients with T2DM who meet the inclusion and exclusion criteria from the same tertiary care center and extracted clinical information from electronic medical records from May 2015 to August 2016. A total of 356 T2DM patients with CVD and 676 T2DM patients without CVD were recruited. Venous blood samples were collected by finger puncture after 8 h fasting and stored as dried blood spots. Restricted cubic spline (RCS) analysis nested in binary logistic regression was used to identify possible cutoff points and obtain the odds ratios (ORs) and 95% confidence intervals (CIs) of short-chain acylcarnitines for CVD risk in T2DM. The Ryan–Holm step-down Bonferroni procedure was performed to adjust p-values. Stepwise forward selection was performed to estimate the effects of acylcarnitines on CVD risk.ResultThe levels of C2, C4, and C6 were elevated and C5-OH was decreased in T2DM patients with CVD. Notably, only elevated C2 was still associated with increased CVD inT2DM after adjusting for potential confounders in the multivariable model (OR = 1.558, 95%CI = 1.124–2.159, p = 0.008). Furthermore, the association was independent of previous adjusted demographic and clinical factors after stepwise forward selection (OR = 1.562, 95%CI = 1.132–2.154, p = 0.007).ConclusionsElevated C2 was associated with increased CVD risk in T2DM.

In Vitro Evaluation of the Effectiveness of Dental Bleaching with Carbamide Peroxide and Violet Light.

Objective: The aim of the current study was to use the CIELab system to evaluate the performance of the whitening treatment involving violet light-emitting diode (LED) combined with a home 10% and 22% carbamide peroxide dental bleaching technique on dental enamel. Methods: Fifty blocks of bovine dental enamel were divided into five groups: control group (control), receiving only LED irradiation; Whitening 10%, receiving 10% carbamide peroxide treatment; Whitening 10%+VL, receiving 10% carbamide peroxide treatment combined with LED irradiation; Whitening 22%, receiving 22% carbamide peroxide treatment; and Whitening 22%+VL, receiving 22% carbamide peroxide treatment combined with violet LED irradiation. Color tests were performed before the protocols, after 1 week and after 2 weeks of treatment by using a spectrophotometer and the CIELab parameters: L*, (a*) and (b*). The Whitening 10%, Whitening 10%+VL, Whitening 22% and Whitening 22%+VL groups were submitted to 10% and 22% carbamide peroxide 8 h per day for 14 days, whereas the Control was only stored in artificial saliva. For irradiation in the Control, Whitening 10%+VL, and Whitening 22%+VL groups, we used violet LED at a wavelength of 405-410 nm activated for 60 permanent seconds and 30 sec of pause once per week. As all data exhibited normal distribution, the comparisons were performed by using two-way repeated-measures analysis of variance. A post hoc t-test was employed, followed by the Ryan-Holm stepdown Bonferroni procedure. Results: After 1 week, the Whitening 22%+VL group differed significantly from all other groups in relation to hue, while no difference was found between the remaining groups (p < 0.05). Analyzing lightness, the Whitening 22%+VL and Whiteness10%+VL groups differed from the other groups (p > 0.05). In the 2nd week, the Whitening 22%+VL groups differed significantly from all other groups (p < 0.05) in hue, chroma, and lightness. The comparative analysis of bleaching times within the same group revealed significant differences in the Whitening 22%+VL group between baseline and week 1, baseline and week 2, as well as weeks 1 and 2 in terms of hue (p > 0.05). In the Whitening 22%+VL group, significant differences (p < 0.05) were found between baseline and week 2 as well as between weeks 1 and 2 in chroma (p > 0.05). In the Whitening 22%+VL group, statistically significant differences (p < 0.05) were found between baseline and week 1, baseline and week 2, as well as between weeks 1 and 2 in lightness. In the Whitening 10%+VL group, statistically significant differences (p < 0.05) were found between baseline and week 1, between baseline and week 2, as well as between weeks 1 and 2 in lightness. Conclusions: Tooth whitening treatment involving 10% and 22% carbamide peroxide combined with violet light promoted changes in the three axes of color (ΔH, ΔC, and ΔL) of the specimens evaluated. The use of the gel bleach alone was more efficient when the higher concentration was used. When violet light was combined with the gel, the lower concentration was more efficient.

Defensible inferences from a nested sequence of logistic regressions: a guide for the perplexed

Employing nested sequences of models is a common practice when exploring the extent to which one set of variables mediates the impact of another set. Such an analysis in the context of logistic regression models confronts two challenges: (i) direct comparisons of coefficients across models are generally biased due to the changes in scale that accompany the changes in the set of explanatory variables, (ii) conducting a large number of tests induces a problem of multiplicity that can lead to spurious findings of significance if not heeded. This article aims to illustrate a practical strategy for conducting analyses in the face of these challenges. The challenges—and how to address them—are illustrated using a subset of the findings reported by Braun (Large-scale Assess Educ 6(4):1–52, 2018. 10.1186/s40536-018-0058-x), drawn from the Programme for the International Assessment of Adult Competencies (PIAAC), an international, large-scale assessment of adults. For each country in the dataset, a nested pair of logistic regression models was fit in order to investigate the role of Educational Attainment and Cognitive Skills in mediating the impact of family background and demographic characteristics on the location of an individual’s annual income in the national income distribution. A modified version of the Karlson–Holm–Breen (KHB) method was employed to obtain an unbiased estimate of the true differences in the coefficients between nested logistic models. In order to address the issue of multiplicity, a recent generalization of the Benjamini–Hochberg (BH) False Discovery Rate (FDR)-controlling procedure to hierarchically structured hypotheses was employed and compared to two conventional methods. The differences between the changes in coefficients calculated conventionally and with the KHB adjustment varied from negligible to very substantial. When combined with the actual magnitudes of the coefficients, we concluded that the more proximal factors indeed act as strong mediators for the background factors, but less so for Age, and hardly at all for Gender. With respect to multiplicity, applying the FDR-controlling procedure yielded results very similar to those obtained by applying a standard per-comparison procedure, but quite a few more discoveries in comparison to the Bonferroni procedure. The KHB methodology illustrated here can be applied wherever there is interest in comparing nested logistic regressions. Modifications to account for probability sampling are practicable. The categorization of variables and the order of entry should be determined by substantive considerations. On the other hand, the BH procedure is perfectly general and can be implemented to address multiplicity issues in a broad range of settings.

Generalized mean p-values for combining dependent tests: comparison of generalized central limit theorem and robust risk analysis

The test statistics underpinning several methods for combining p-values are special cases of generalized mean p-value (GMP), including the minimum (Bonferroni procedure), harmonic mean and geometric mean. A key assumption influencing the practical performance of such methods concerns the dependence between p-values. Approaches that do not require specific knowledge of the dependence structure are practically convenient. Vovk and Wang derived significance thresholds for GMPs under the worst-case scenario of arbitrary dependence using results from Robust Risk Analysis (RRA). Here I calculate significance thresholds and closed testing procedures using Generalized Central Limit Theorem (GCLT). GCLT formally assumes independence, but enjoys a degree of robustness to dependence. The GCLT thresholds are less stringent than RRA thresholds, with the disparity increasing as the exponent of the GMP ( r) increases. I motivate a model of p-value dependence based on a Wishart-Multivariate-Gamma distribution for the underlying log-likelihood ratios. In simulations under this model, the RRA thresholds produced tests that were usually less powerful than Bonferroni, while the GCLT thresholds produced tests more powerful than Bonferroni, for all r> − ∞. Above r> − 1, the GCLT thresholds suffered pronounced false positive rates. Above r> − 1/2, standard central limit theorem applied and the GCLT thresholds no longer possessed any useful robustness to dependence. I consider the implications of these results in the context of various interpretations of GMPs, and conclude that the GCLT-based harmonic mean p-value procedure and Simes' (1986) test represent good compromises in power-robustness trade-off for combining dependent tests.

%polynova_2way: A SAS macro for implementation of mixed models for metabolomics data.

The generation of large metabolomic data sets has created a high demand for software that can fit statistical models to one-metabolite-at-a-time on hundreds of metabolites. We provide the %polynova_2way macro in SAS to identify metabolites differentially expressed in study designs with a two-way factorial treatment and hierarchical design structure. For each metabolite, the macro calculates the least squares means using a linear mixed model with fixed and random effects, runs a 2-way ANOVA, corrects the P-values for the number of metabolites using the false discovery rate or Bonferroni procedure, and calculate the P-value for the least squares mean differences for each metabolite. Finally, the %polynova_2way macro outputs a table in excel format that combines all the results to facilitate the identification of significant metabolites for each factor. The macro code is freely available in the Supporting Information.