We identify 10 common errors and problems in the statistical analysis, design, interpretation, and reporting of obesity research and discuss how they can be avoided. The 10 topics are: 1) misinterpretation of statistical significance, 2) inappropriate testing against baseline values, 3) excessive and undisclosed multiple testing and “p-value hacking,” 4) mishandling of clustering in cluster randomized trials, 5) misconceptions about nonparametric tests, 6) mishandling of missing data, 7) miscalculation of effect sizes, 8) ignoring regression to the mean, 9) ignoring confirmation bias, and 10) insufficient statistical reporting. We hope that discussion of these errors can improve the quality of obesity research by helping researchers to implement proper statistical practice and to know when to seek the help of a statistician.

The impact of additional structured outdoor playtime on preschoolers' physical activity (PA) level is unclear. The purpose of this pilot study was to explore the effects of increasing structured outdoor playtime on preschoolers' PA levels. Eight full-day classrooms (n 0134 children) from two preschool programmes were randomised into a treatment (STRUCT, n 04) or control (CON, n 04) condition. Both groups received an additional 30 minutes of outdoor playtime three days per week for four weeks. The STRUCT intervention consisted of previously tested structured outdoor playtime activities/games. The CON intervention consisted of free outdoor playtime. Children were individually recruited (n075) for the objective assessment of PA levels. The PA levels of 67 children (age, 4.190.8 years; STRUCT, n038; CON, n 029) were assessed at baseline and during week four for seven consecutive days using Actigraph accelerometers. Data were analysed using mixed-model analysis of variance. Time spent in vigorous PA significantly increased during the 30-minute intervention time for the STRUCT group compared with the CON group (group )time interaction: F(1, 36) 04.91, p00.04). Compared with baseline, a significant increase was observed in the STRUCT group's time spent engaged in moderate-to-vigorous PA (MVPA) during the intervention time, but this increase was not significant compared with the CON group (baseline: STRUCT, 1.792.0 min; CON, 1.992.4 min; week four: STRUCT, 4.993.1 min; CON, 3.392.5 min). Compared with the CON group, the STRUCT group spent a significantly greater percentage of time engaged in MVPA and a

Numerous meta-analyses have been conducted to summarize the growing numbers of trials addressing the effects of exercise on blood pressure (BP), yet it is unclear how well they have satisfied contemporary methodological standards. We applied an augmented version of the Assessment of Multiple Systematic Reviews (AMSTARExBP) scale to 33 meta-analyses retrieved from searches of electronic databases. Qualifying reports used meta-analytic procedures; examined controlled exercise training trials; had BP as a primary outcome; and had exercise or physical activity interventions independently or combined with other lifestyle interventions. AMSTARExBP scores averaged near the middle of the scale (Mean = 56.0% ± 21.4% of total items possible); co-authored and more recent meta-analyses had higher quality scores. Common deficits were failures to disclose full search details (30% did), gauge the quality of included trials (48% did), use duplicate study selection and data extraction (55% did), or incorporate study quality in formulating results (35% did). Nearly all (91%) meta-analyses observed that exercise significantly lowered BP; fewer (58%) found that such effects depended on exercise or patient characteristics but these patterns often conflicted. Meta-analyses are often pillars of clinical recommendations and guidelines, yet only 58% addressed the clinical translations of their findings. In sum, meta-analyses have contributed less than ideally to our understanding of how exercise may impact BP, or how these BP effects may be moderated by patient or exercise characteristics. Future meta-analyses that better satisfy contemporary standards offer considerable promise to understand how and for whom exercise impacts BP.

The evidence regarding recommendations of calorie restriction as part of a comprehensive lifestyle intervention to promote weight loss in obese older adults has remained equivocal for more than a decade. The older adult population is the fastest growing segment of the US population and a greater proportion of them are entering old age obese. These older adults require treatments based on solid evidence. Therefore the purpose of this review is three-fold: 1) to provide a more current status of the knowledge regarding recommendations of calorie restriction as part of a comprehensive lifestyle intervention to promote weight loss in obese older adults 2) to determine what benefits and/or risks calorie restriction adds to exercise interventions in obese older adults and 3) to consider not only outcomes related to changes in body composition, bone health, cardiometabolic disease risk, markers of inflammation, and physical function, but, also patient-centered outcomes that evaluate changes in cognitive status, quality of life, out-of-pocket costs, and mortality. Seven randomized controlled trials were identified that examined calorie restriction while controlling for exercise intervention effects. Overall, the studies found that calorie restriction combined with exercise is effective for weight loss. Evidence was mixed regarding other outcomes. The risk-benefit ratio regarding calorie restriction in older adults remains uncertain. Greater long-term follow-up is necessary, and complementary effectiveness studies are needed to identify strategies currently used by obese older adults in community settings.