Assessing regression to the mean effects in health care initiatives

Linden, Ariel

doi:10.1186/1471-2288-13-119

Cited by 153 publications

(128 citation statements)

References 39 publications

Supporting

Mentioning

127

Contrasting

Order By: Relevance

“…Regression to the mean can be mitigated when multiple baseline observations are taken, as this narrows the variability around the true mean (Linden, 2013). As such, the fact that physical activity data were obtained over the course of five days, and that dietary intake data were collected over two days at both time points may have helped reduce the potential for regression to the mean.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

“Monkey see, monkey do”: Peers' behaviors predict preschoolers' physical activity and dietary intake in childcare centers

Ward

Bélanger

Donovan

et al. 2017

Preventive Medicine

View full text Add to dashboard Cite

Preschoolers observe and imitate the behaviors of those who are similar to them. Therefore, peers may be important role models for preschoolers' dietary intake and physical activity in childcare centers. This study examined whether peers' behaviors predict change in preschoolers' dietary intake and physical activity in childcare centers over 9 months.A total of 238 preschoolers (3 to 5 years old) from 23 childcare centers in two Canadian provinces provided data at the beginning (October 2013 and 2014) and the end (June 2014 and 2015) of a 9-month period for this longitudinal study. Dietary intake was collected at lunch using weighed plate waste and digital photography on two consecutive weekdays. Physical activity was assessed using accelerometers over five days. Multilevel linear regressions were used to estimate the influence of peers' behaviors on preschoolers' change in dietary intake and physical activity over 9 months.Results showed that preschoolers whose dietary intake or physical activity level deviated the most from those of their peers at the beginning of the year demonstrated greater change in their intakes and activity levels over 9 months (all p values<0.05), which enabled them to become more similar to their peers. This study suggests that preschoolers' dietary intake and physical activity may be influenced by the behaviors of their peers in childcare centers. Since peers could play an important role in promoting healthy eating behaviors and physical activity in childcare centers, future studies should test interventions based on positive role modeling by children.4

show abstract

Section: Discussionmentioning

confidence: 99%

“…Aside from the potential interpretations provided, regression to the mean may also explain some of the observed changes. This is a statistical phenomenon where individuals or groups with extreme initial values are likely to have values that will be closer to the overall sample mean in the follow up score (Linden, 2013).…”

Section: Discussionmentioning

confidence: 99%

“Monkey see, monkey do”: Peers' behaviors predict preschoolers' physical activity and dietary intake in childcare centers

Ward

Bélanger

Donovan

et al. 2017

Preventive Medicine

View full text Add to dashboard Cite

show abstract

“…The natural history of these clinical disorders is that symptoms substantially ebb and flow rather than remain static [174]. As it is most common for patients to enroll in research studies when their symptoms are particularly high, it is possible that much of any clinical improvements noted reflect “regression to the mean” rather than a discrete treatment effect [175]. Further, the act of participating in a trial and being studied may lead to symptomatic improvement that is not specific to any particular intervention.…”

Section: Post Hoc Fallacymentioning

confidence: 99%

Neuroimaging of Central Sensitivity Syndromes: Key Insights from the Scientific Literature

Walitt

Čeko²,

Gracely³

et al. 2016

CRR

View full text Add to dashboard Cite

Central sensitivity syndromes are characterized by distressing symptoms, such as pain and fatigue, in the absence of clinically obvious pathology. The scientific underpinnings of these disorders are not currently known. Modern neuroimaging techniques promise new insights into mechanisms mediating these postulated syndromes. We review the results of neuroimaging applied to five central sensitivity syndromes: fibromyalgia, chronic fatigue syndrome, irritable bowel syndrome, temporomandibular joint disorder, and vulvodynia syndrome. Neuroimaging studies of basal metabolism, anatomic constitution, molecular constituents, evoked neural activity, and treatment effect are compared across all of these syndromes. Evoked sensory paradigms reveal sensory augmentation to both painful and non-painful stimulation. This is a transformative observation for these syndromes, which were historically considered to be completely of hysterical or feigned in origin. However, whether sensory augmentation represents the cause of these syndromes, a predisposing factor, an endophenotype, or an epiphenomenon cannot be discerned from the current literature. Further, the result from cross-sectional neuroimaging studies of basal activity, anatomy, and molecular constituency are extremely heterogeneous within and between the syndromes. A defining neuroimaging “signature” cannot be discerned for any of the particular syndromes or for an over-arching central sensitization mechanism common to all of the syndromes. Several issues confound initial attempts to meaningfully measure treatment effects in these syndromes. At this time, the existence of “central sensitivity syndromes” is based more soundly on clinical and epidemiological evidence. A coherent picture of a “central sensitization” mechanism that bridges across all of these syndromes does not emerge from the existing scientific evidence.

show abstract

“…blood pressure 5 , heights of fathers and sons 6 , and medical costs 7 ) or count data (sex acts, sex partners 8 ). However, little has been written about RTM in the context of binary measures (e.g.…”

Section: Introductionmentioning

confidence: 99%

Regression to the mean and changes in risk behavior following study enrollment in a cohort of U.S. women at risk for HIV

Haley

Frew

Golin

et al. 2015

Annals of Epidemiology

View full text Add to dashboard Cite

Purpose Reductions in risk behaviors are common following enrollment in HIV prevention studies. We develop methods to quantify the proportion of change in risk behaviors that can be attributed to regression to the mean versus study participation and other factors. Methods A novel model that incorporates both regression to the mean and study participation effects is developed for binary measures. The model is used to estimate the proportion of change in the prevalence of “unprotected sex in the past 6 months” that can be attributed to study participation versus regression to the mean in a longitudinal cohort of women at risk for HIV infection who were recruited from ten US communities with high rates of HIV and poverty. HIV risk behaviors were evaluated using audio computer-assisted self-interviews at baseline and every 6 months for up to 12 months. Results The prevalence of “unprotected sex in the past 6 months” declined from 96% at baseline to 77% at 12 months. However, this change could be almost completely explained by regression to the mean. Conclusions Analyses that examine changes over time in cohorts selected for high or low risk behaviors should account for regression to the mean effects.

show abstract

Assessing regression to the mean effects in health care initiatives

Cited by 153 publications

References 39 publications

“Monkey see, monkey do”: Peers' behaviors predict preschoolers' physical activity and dietary intake in childcare centers

“Monkey see, monkey do”: Peers' behaviors predict preschoolers' physical activity and dietary intake in childcare centers

Neuroimaging of Central Sensitivity Syndromes: Key Insights from the Scientific Literature

Regression to the mean and changes in risk behavior following study enrollment in a cohort of U.S. women at risk for HIV

Contact Info

Product

Resources

About