A smoothed ANOVA model for multivariate ecological regression

2013 ◽  
Vol 28 (3) ◽  
pp. 695-706 ◽  
Author(s):  
Marc Marí-Dell’Olmo ◽  
Miguel A. Martinez-Beneito ◽  
Mercè Gotsens ◽  
Laia Palència
2020 ◽  
Vol 7 (Supplement_1) ◽  
pp. S577-S578
Author(s):  
Yi Kee Poon ◽  
Ricardo M La Hoz ◽  
James Sanders ◽  
Linda S Hynan ◽  
Marguerite Monogue

Abstract Background Treatment options for nontuberculous mycobacteria (NTM) infections are limited by the long-term tolerability of antimicrobials. The oxazolidinones, linezolid and tedizolid, display in vitro activity against many NTM species and demonstrate excellent oral bioavailability. This study compares the hematologic safety profile of linezolid versus tedizolid for the treatment of NTM in solid organ transplant (SOT) recipients. Methods This retrospective cohort study included adult SOT recipients who received linezolid or tedizolid as part of a multi-drug regimen to treat NTM between January 1, 2010 to August 31, 2019. The primary endpoint was the hematologic effects of linezolid versus tedizolid from therapy initiation to week seven. This time frame was chosen based on the median duration of therapy. A mixed-effects ANOVA model was used to assess the effects of linezolid and tedizolid on platelet counts (PLT), absolute neutrophil counts (ANC), and hemoglobin (Hgb) across time. Subjects were treated as a random effect. The secondary analysis described the proportion of adverse effects and discontinuation. Results Twenty-four patients were included in the analysis (9 linezolid, 15 tedizolid). Mycobacterium abscessus abscessus was the most common isolate, and pulmonary was the most common site of infection (Table 1). The median duration of therapy was 24 days (range 3 to 164 days) and 48 days (range 11 to 571 days) for linezolid and tedizolid, respectively. All patients in the linezolid group received 600 mg daily or less for the majority of treatment duration. In the mixed-effects ANOVA, the ANC decreased in both groups after seven weeks of therapy (p=0.04). Otherwise, no significant effects for week, treatment group, or interaction between week and treatment group were found (Figure 1). Thrombocytopenia and neutropenia were common in both groups, and around one-fifth of patients in each group discontinued the medication due to adverse effects (Table 2). Table 1. Baseline characteristics of solid organ transplant recipients who received linezolid or tedizolid as part of a multi-drug regimen to treat nontuberculous mycobacteria infections between January 1, 2010 to August 31, 2019 at UT Southwestern Medical Center. Table 2. Adverse drug events and discontinuation of therapy over seven weeks of therapy. Figure 1. Effects of linezolid versus tedizolid during the initial seven weeks of therapy using a mixed-effects ANOVA model, (a) platelet counts, (b) absolute neutrophil counts, and (c) hemoglobin. Conclusion Non-significant statistical differences were found comparing the effects of linezolid versus tedizolid for PLT, ANC, and Hgb using mixed-effects ANOVA models. Larger cohort studies are required to compare the hematologic adverse effect profile of the oxazolidinones for the treatment of NTM infections in SOT recipients. Disclosures All Authors: No reported disclosures


1988 ◽  
Vol 2 (3) ◽  
pp. 304-309 ◽  
Author(s):  
Jerry L. Flint ◽  
Paul L. Cornelius ◽  
Michael Barrett

A model and a proposed method for testing herbicide interactions were modified from an analysis of variance (ANOVA) model for a 2 by 2 factorial experiment. Statistical tests for either synergism, antagonism, or additivity of herbicide combinations were developed through transforming growth data to logarithms followed by significance tests of 2 by 2 contrasts of the form μii- μi0- μ0i+ μ00with respect to the log-transformed data. Using actual experimental data, heterogeneity of variance was less severe on the log scale compared to the original measurement scale. An expedient SAS(R)program for obtaining the desired significance tests was developed.


Drug Research ◽  
2021 ◽  
Author(s):  
Budi Prasaja ◽  
Yahdiana Harahap ◽  
Monika Sandra ◽  
Irene Iskandar ◽  
Windy Lusthom ◽  
...  

AbstractIbuprofen is a widely used and well-tolerated analgesic and antipyretic. It is desirable to have a formulation with a rapid rate of absorption because it is required for rapid pain relief and temperature reduction. Previous studies have described the pharmacokinetic profiles of ibuprofen suppository and the mean peak times of ibuprofen suppository were around 1.8 hours, indicating a slower rate of absorption. The aim of this study is to compare the pharmacokinetic parameters of rectal administration of ibuprofen between enema and suppository form in order to provide evidence for the faster absorption rates of ibuprofen enema. This study was a phase-1 clinical study, open-label, randomized and two-way crossover with one-week washout period comparing the absorption profile of equal dose of ibuprofen administered rectally in two treatment phases: ibuprofen suppository and enema. Blood samples were collected post dose for pharmacokinetic analyses. Tmax was analyzed using a Wilcoxon matched paired test. A standard ANOVA model, appropriate for bioequivalence studies was used and ratios of 90% confidence intervals were calculated. This study showed that Tmax for ibuprofen enema was less than half that of ibuprofen suppository (median 40 min vs. 90 min, respectively; p-value=0.0003). Cmax and AUC0–12 for ibuprofen enema were bioequivalent to ibuprofen suppository, as the ratio of test/reference=104.52%, 90% CI 93.41–116.95% and the ratio of test/reference=98.12%, 90%CI 93.34–103.16%, respectively, which fell within 80–125% bioequivalence limit. The overall extent of absorption was similar to the both, which were all well tolerated. In terms of Tmax, Ibuprofen enema was absorbed twice as quickly as from ibuprofen suppository. Therefore it is expected that an ibuprofen enema may provide faster onset of analgesic and antipyretic benefit.


Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Alexander T Schneider ◽  
Reid Taylor ◽  
Robin Jones ◽  
Roy Nanz ◽  
Edward Jauch

Introduction: After hours stroke coverage in community hospitals is typically provided on-call from home or through telehealth. Lack of immediate on-site stroke expertise may delay door-to-needle (DTN) times for IV alteplase. A 750-bed community hospital that had evening emergency stroke coverage by a neurologist on-call from home transitioned to 24/7 neurohospitalist coverage in October 2015. Methods: Data were obtained from patients treated with alteplase in the ED for ischemic stroke. We evaluated the DTN times at baseline and after intervention of the new care model dichotomized by daytime (7a-5p) and evening (5p-7a). Mortality (death in hospital and discharge (DC) to hospice) was assessed. Data were compared for statistical correlation using a Mood’s Median Test and 2-sample t-test. Results: There were 579 cases from January 2015 through July 2019 treated with alteplase in the ED for ischemic stroke. Patients available for study pre- and post-intervention were 84 and 495, respectively (Table 1). Daytime arrival was more common. Significant improvements in door-to-neurohospitalist at bedside and DTN time were observed regardless of time of day, but the greatest difference seen was in evening hours. Using an ANOVA model, EMS arrival was the most significant factor predicting DTN times. Despite fewer patients arriving via EMS in the post-intervention group (90% vs 94% baseline), the DTN times improved post intervention. Mortality was significantly improved after the intervention. Despite a 44% increase in code stroke arrivals to the ED, the feasibility of the care model over ~4 years was maintained by no loss of any neurohospitalists and the addition of 1 more. Conclusion: In-hospital 24/7 model of neurohospitalist coverage is a feasible model for large community hospitals and is associated with significantly faster DTN times and reduced mortality. We will explore other aspects of the care model and other changes occurring during the study period.


2004 ◽  
pp. 123-143 ◽  
Author(s):  
Bernard Grofman ◽  
Samuel Merrill

2018 ◽  
Vol 51 (2) ◽  
pp. 165-191 ◽  
Author(s):  
A. K. Md. Ehsanes Saleh ◽  
M. Arashi ◽  
M. Norouzirad ◽  
B M Goalm Kibria

This paper considers the estimation of the parameters of an ANOVA model when sparsity is suspected. Accordingly, we consider the least square estimator (LSE), restricted LSE, preliminary test and Stein-type estimators, together with three penalty estimators, namely, the ridge estimator, subset selection rules (hard threshold estimator) and the LASSO (soft threshold estimator). We compare and contrast the L2-risk of all the estimators with the lower bound of L2-risk of LASSO in a family of diagonal projection scheme which is also the lower bound of the exact L2-risk of LASSO. The result of this comparison is that neither LASSO nor the LSE, preliminary test, and Stein-type estimators outperform each other uniformly. However, when the model is sparse, LASSO outperforms all estimators except “ridge” estimator since both LASSO and ridge are L2-risk equivalent under sparsity. We also find that LASSO and the restricted LSE are L2-risk equivalent and both outperform all estimators (except ridge) depending on the dimension of sparsity. Finally, ridge estimator outperforms all estimators uniformly. Our finding are based on L2-risk of estimators and lower bound of the risk of LASSO together with tables of efficiency and graphical display of efficiency and not based on simulation.


2016 ◽  
Vol 62 (5) ◽  
pp. 725-736 ◽  
Author(s):  
Thomas Røraas ◽  
Bård Støve ◽  
Per Hyltoft Petersen ◽  
Sverre Sandberg

Abstract BACKGROUND Good estimates of within-person biological variation, CVI, are essential for diagnosing and monitoring patients and for setting analytical performance specifications. The aim of the present study was to use computer simulations to evaluate the impact of various measurement distributions on different methods for estimating CVI and reference change value (RCV). METHOD Data were simulated on the basis of 3 models for distributions of the within-person effect. We evaluated 3 different methods for estimating CVI: standard ANOVA, ln-ANOVA, and CV-ANOVA, and 3 different methods for calculating RCV: classic, ln-RCV, and a nonparametric method. We estimated CVI and RCV with the different methods and compared the results with the true values. RESULTS The performance of the methods varied, depending on both the size of the CVI and the type of distributions. The CV-ANOVA model performed well for the estimation of CVI with all simulated data. The ln-RCV method performed best if data were ln-normal distributed or CVI was less than approximately 12%. The nonparametric RCV method performed well for all simulated data but was less precise. CONCLUSIONS The CV-ANOVA model is recommended for both calculation of CVI and the step-by-step approach of checking for outliers and homogeneity in replicates and samples. The standard method for calculation of RCV should not be used when using CVs.


Sign in / Sign up

Export Citation Format

Share Document