Confidence interval for random-effects calibration curves with left-censored data

2009 ◽  
Vol 20 (2) ◽  
pp. 181-189 ◽  
Author(s):  
Subhash Aryal ◽  
Dulal K. Bhaumik ◽  
Sourav Santra ◽  
Robert D. Gibbons
Keyword(s):  
Confidence Interval ◽  
Random Effects ◽  
Censored Data ◽  
Calibration Curves

Wide-Awake Local Anesthesia No Tourniquet (WALANT) versus Local or Intravenous Regional Anesthesia with Tourniquet in Atraumatic Hand Cases in Orthopedics: A Systematic Review and Meta-Analysis

2019 ◽  
Vol 24 (04) ◽  
pp. 469-476 ◽  
Author(s):  
Ted Matthew P. Evangelista ◽  
John Hubert C. Pua ◽  
Mara Therese P. Evangelista-Huber
Keyword(s):  
Systematic Review ◽  
Patient Satisfaction ◽  
Confidence Interval ◽  
Local Anesthesia ◽  
Regional Anesthesia ◽  
Random Effects ◽  
Complication Rates ◽  
Pain Scores ◽  
Intravenous Regional Anesthesia ◽  
Post Operative Pain

Background: To compare outcomes of atraumatic hand surgeries using the WALANT technique versus intravenous regional anesthesia or local anesthesia with tourniquet. Methods: We conducted a comprehensive literature search using PubMed, MEDLINE, Embase, and Cochrane Library from inception to October 2018. All randomized or quasi-randomized trials and cohort studies comparing WALANT procedure versus local anesthesia or intravenous regional anesthesia with tourniquet among atraumatic hand surgeries were included. Methodological quality and risk of bias of eligible studies were assessed by three independent reviewers. The random effects model was used due to both statistical and clinical heterogeneity among studies. Results: The search yielded 496 records, of which 9 studies were included in the systematic review. We were able to pool findings for operative time, post-operative pain scores, patient satisfaction, and complication rates. On the average, the WALANT group had longer operative times by 2.06 minutes (pooled mean difference, random effects, 95% confidence interval 0.46 to 3.67 minutes, p = 0.01, I2 0%, p = 0.66). The post-operative pain scores were lower in the WALANT group by an average of two VAS points (random effects, pooled mean difference −2.40, 95% confidence interval −3.41 to −1.38, p < 0.00001; I2 0% p = 0.99). We had insufficient evidence to demonstrate a difference in terms of patient satisfaction (random effects, pooled risk ratio 0.98, 95% confidence interval 0.93 to 1.03, p = 0.36, I2 0%, p = 0.64) and complication rates (random effects, pooled risk ratio 0.40, 95% confidence interval 0.07 to 2.18, p = 0.29, I2 60% p = 0.08) between WALANT versus conventional methods. Conclusions: The WALANT group reported lower post-operative pain scores, but had slightly longer operative times. There are no significant differences between WALANT and conventional methods in terms of patient satisfaction and complication rates.

scholarly journals Health-Related Quality of Life in Athletes: A Systematic Review With Meta-Analysis

2016 ◽  
Vol 51 (6) ◽  
pp. 442-453 ◽  
Author(s):  
Megan N. Houston ◽  
Matthew C. Hoch ◽  
Johanna M. Hoch
Keyword(s):  
Quality Of Life ◽  
Confidence Interval ◽  
Random Effects ◽  
Meta Analysis ◽  
Collegiate Athletes ◽  
Health Related Quality ◽  
Related Quality ◽  
Health Related ◽  
History Of

Context: Assessment of health-related quality of life (HRQOL) after injury is important. Differences in HRQOL between nonathletes and athletes and between injured and uninjured athletes have been demonstrated; however, the evidence has not been synthesized. Objective: To answer the following questions: (1) Does HRQOL differ among adolescent and collegiate athletes and nonathletes? (2) Does HRQOL differ between injured adolescent and collegiate athletes or between athletes with a history of injury and uninjured athletes or those without a history of injury? Data Sources: We systematically searched CINAHL, MEDLINE, SPORTDiscus, and PubMed. A hand search of references was also conducted. Study Selection: Studies were included if they used generic instruments to compare HRQOL outcomes between athletes and nonathletes and between uninjured and injured athletes. Studies were excluded if they did not use a generic instrument, pertained to instrument development, or included retired athletes or athletes with a chronic disease. Data Extraction: We assessed study quality using the modified Downs and Black Index Tool. Bias-corrected Hedges g effect sizes and 95% confidence intervals (CIs) were calculated. The Strength of Recommendation Taxonomy (SORT) was used to determine the overall strength of the recommendation. A random-effects meta-analysis was performed for all studies using the composite or total score. Data Synthesis: Eight studies with modified Downs and Black scores ranging from 70.6% to 88.4% were included. For question 1, the overall random-effects meta-analysis was weak (effect size = 0.27, 95% confidence interval = 0.14, 0.40; P &lt; .001). For question 2, the overall random-effects meta-analysis was moderate (effect size = 0.68, 95% confidence interval = 0.42, 0.95; P &lt; .001). Conclusions: Grade A evidence indicates that athletes reported better HRQOL than nonathletes and that uninjured athletes reported better HRQOL than injured athletes. However, the overall effect for question 1 was weak, suggesting that the differences between athletes and nonathletes may not be clinically meaningful. Clinicians should monitor HRQOL after injury to ensure that all dimensions of health are appropriately treated.

scholarly journals Odds of Getting Adequate Physical Activity by Dog Walking

2015 ◽  
Vol 12 (s1) ◽  
pp. S102-S109 ◽  
Author(s):  
Jesus Soares ◽  
Jacqueline N. Epping ◽  
Chantelle J. Owens ◽  
David R. Brown ◽  
Tina J. Lankford ◽  
...  
Keyword(s):  
Physical Activity ◽  
Confidence Interval ◽  
Random Effects ◽  
Odds Ratio ◽  
Systematic Search ◽  
Moderate Intensity ◽  
Random Effects Model ◽  
Unadjusted Odds Ratio ◽  
Dog Walking ◽  
Dog Owners

Background:We aimed to determine the likelihood that adult dog owners who walk their dogs will achieve a healthy level of moderate-intensity (MI) physical activity (PA), defined as at least 150 mins/wk.Methods:We conducted a systematic search of 6 databases with data from 1990–2012 on dog owners’ PA, to identify those who achieved MIPA. To compare dog-walkers’ performance with non-dog walkers, we used a random effects model to estimate the unadjusted odds ratio (OR) and corresponding 95% confidence interval (CI).Results:We retrieved 9 studies that met our inclusion criterion and allowed OR calculations. These yielded data on 6980 dog owners aged 18 to 81 years (41% men). Among them, 4463 (63.9%) walked their dogs. Based on total weekly PA, 2710 (60.7%) dog walkers, and 950 (37.7%) non-dog walkers achieved at least MIPA. The estimated OR was 2.74 (95% CI 2.09–3.60).Conclusion:Across 9 published studies, almost 2 in 3 dog owners reported walking their dogs, and the walkers are more than 2.5 times more likely to achieve at least MIPA. These findings suggest that dog walking may be a viable strategy for dog owners to help achieve levels of PA that may enhance their health.

Bias and Precision of Alternate Estimators in Meta-Analysis: Benefits of Blending Schmidt-Hunter and Hedges Approaches

2017 ◽  
Vol 22 (2) ◽  
pp. 490-514 ◽  
Author(s):  
Michael T. Brannick ◽  
Sean M. Potter ◽  
Bryan Benitez ◽  
Scott B. Morris
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Confidence Interval ◽  
Root Mean Square Error ◽  
Random Effects ◽  
Meta Analysis ◽  
Size Distributions ◽  
Mean Square ◽  
The Mean

We describe a new estimator (labeled Morris) for meta-analysis. The Morris estimator combines elements of both the Schmidt-Hunter and Hedges estimators. The new estimator is compared to (a) the Schmidt-Hunter estimator, (b) the Schmidt-Hunter estimator with variance correction for the number of studies (“ k correction”), (c) the Hedges random-effects estimator, and (d) the Bonett unit weights estimator in a Monte Carlo simulation. The simulation was designed to represent realistic conditions faced by researchers, including population random-effects distributions, numbers of studies, and skewed sample size distributions. The simulation was used to evaluate the estimators with respect to bias, coverage of the 95% confidence interval of the mean, and root mean square error of estimates of the population mean. We also evaluated the quality of credibility intervals. Overall, the new estimator provides better coverage and slightly better credibility values than other commonly used methods. Thus it has advantages of both commonly used approaches without the apparent disadvantages. The new estimator can be implemented easily with existing software; software used in the study is available online, and an example is included in the appendix in the Supplemental Material available online.

scholarly journals Trends in Concussion Return-to-Play Timelines Among High School Athletes From 2007 Through 2009

2013 ◽  
Vol 48 (6) ◽  
pp. 836-843 ◽  
Author(s):  
Jennifer M. Medina McKeon ◽  
Scott C. Livingston ◽  
Ashley Reed ◽  
Robert G. Hosey ◽  
Williams S. Black ◽  
...  
Keyword(s):  
High School ◽  
Confidence Interval ◽  
Censored Data ◽  
Return To Play ◽  
Prognostic Indicators ◽  
High School Athletes ◽  
Time To Event ◽  
Interscholastic Sports ◽  
Probability Estimates ◽  
Recovery Times

Context: Whereas guidelines about return-to-play (RTP) after concussion have been published, actual prognoses remain elusive. Objective: To develop probability estimates for time until RTP after sport-related concussion. Design: Descriptive epidemiology study. Setting: High school. Patients or Other Participants: Injured high school varsity, junior varsity, or freshman athletes who participated in 1 of 13 interscholastic sports at 7 area high schools during the 2007–2009 academic years. Intervention(s): Athletic trainers employed at each school collected concussion data. The athletic trainer or physician on site determined the presence of a concussion. Athlete-exposures for practices and games also were captured. Main Outcome Measure(s): Documented concussions were categorized by time missed from participation using severity outcome intervals (same-day return, 1- to 2-day return, 3- to 6-day return, 7- to 9-day return, 10- to 21-day return, &gt;21-day return, no return [censored data]). We calculated Kaplan-Meier time-to-event probabilities that included censored data to determine the probability of RTP at each of these time intervals. Results: A total of 81 new concussions were documented in 478 775 athlete-exposures during the study period. After a new concussion, the probability of RTP (95% confidence interval) was 2.5% (95% confidence interval = 0.3, 6.9) for a 1- to 2-day return, 71.3% (95% confidence interval = 59.0, 82.9) for a 7- to 9-day return, and 88.8% (95% confidence interval = 72.0, 97.2) for a 10- to 21-day return. Conclusions: For high school athletes, RTP within the first 2 days after concussion was unlikely. After 1 week, the probability of return rose substantially (approximately 71%). Prognostic indicators are used to educate patients about the likely course of disease. Whereas individual symptoms and recovery times vary, prognostic time-to-event probabilities allow clinicians to provide coaches, parents, and athletes with a prediction of the likelihood of RTP within certain timeframes after a concussion.

Sign in / Sign up

Export Citation Format

Share Document