Background
Intention-to-treat analysis requires all randomised individuals to be included in the analysis in the groups to which they were randomised. However, there is confusion about how intention-to-treat analysis should be performed in the presence of missing outcome data.
Purpose
To explain, justify and illustrate an intention-to-treat analysis strategy for randomised trials with incomplete outcome data.
Methods
We consider several methods of analysis and compare their underlying assumptions, plausibility, and numbers of individuals included. We illustrate the intention-to-treat analysis strategy using data from the UK700 trial in the management of severe mental illness.
Results
Depending on the assumptions made about the missing data, some methods of analysis that include all randomised individuals may be less valid than methods that do not include all randomised individuals. Further, some methods of analysis that include all randomised individuals are essentially equivalent to methods that do not include all randomised individuals.
Limitations
This work assumes that the aim of analysis is to obtain an accurate estimate of the difference in outcome between randomised groups, not to obtain a conservative estimate with bias against the experimental intervention.
Conclusions
Clinical trials should employ an intention-to-treat analysis strategy, comprising a design that attempts to follow up all randomised individuals, a main analysis that is valid under a stated plausible assumption about the missing data, and sensitivity analyses which include all randomised individuals in order to explore the impact of departures from the assumption underlying the main analysis. Following this strategy recognises the extra uncertainty arising from missing outcomes and increases the incentive for researchers to minimise the extent of missing data.
Dropout in randomised controlled trials is common and threatens the validity of results, as completers may differ from people who drop out. Differing dropout rates between treatment arms is sometimes called differential dropout or attrition. Although differential dropout can bias results, it does not always do so. Similarly, equal dropout may or may not lead to biased results. Depending on the type of missingness and the analysis used, one can get a biased estimate of the treatment effect with equal dropout rates and an unbiased estimate with unequal dropout rates. We reinforce this point with data from a randomised controlled trial in patients with renal cancer and a simulation study.
Any alcohol use among HIV-infected persons with a history of alcohol problems is associated with worse HAART adherence. Addressing alcohol use in HIV-infected persons may improve antiretroviral adherence and ultimately clinical outcomes.
Missing data are a recurring problem that can cause bias or lead to inefficient analyses. Development of statistical methods to address missingness have been actively pursued in recent years, including imputation, likelihood and weighting approaches. Each approach is more complicated when there are many patterns of missing values, or when both categorical and continuous random variables are involved. Implementations of routines to incorporate observations with incomplete variables in regression models are now widely available. We review these routines in the context of a motivating example from a large health services research dataset. While there are still limitations to the current implementations, and additional efforts are required of the analyst, it is feasible to incorporate partially observed values, and these methods should be utilized in practice.
WHAT'S KNOWN ON THIS SUBJECT: Eating disorder not otherwise specified (EDNOS) is the most common eating disorder diagnosis. Binge eating disorder, 1 type of EDNOS, is associated with obesity among adults. Little is known about the health outcomes associated with other types of EDNOS.
WHAT THIS STUDY ADDS:This is the first study to evaluate the prospective association of full and subthreshold bulimia nervosa, binge eating disorder, purging disorder, and other EDNOSs with specific mental and physical health outcomes. abstract OBJECTIVE: Anorexia nervosa and bulimia nervosa (BN) are rare, but eating disorders not otherwise specified (EDNOS) are relatively common among female participants. Our objective was to evaluate whether BN and subtypes of EDNOS are predictive of developing adverse outcomes.
METHODS:This study comprised a prospective analysis of 8594 female participants from the ongoing Growing Up Today Study. Questionnaires were sent annually from 1996 through 2001, then biennially through 2007 and 2008. Participants who were 9 to 15 years of age in 1996 and completed at least 2 consecutive questionnaires between 1996 and 2008 were included in the analyses. Participants were classified as having BN ($weekly binge eating and purging), binge eating disorder (BED; $weekly binge eating, infrequent purging), purging disorder (PD; $weekly purging, infrequent binge eating), other EDNOS (binge eating and/or purging monthly), or nondisordered.RESULTS: BN affected ∼1% of adolescent girls; 2% to 3% had PD and another 2% to 3% had BED. Girls with BED were almost twice as likely as their nondisordered peers to become overweight or obese (odds ratio [OR]: 1.9 [95% confidence interval: 1.0-3.5]) or develop high depressive symptoms (OR: 2.3 [95% confidence interval: 1.0-5.0]). Female participants with PD had a significantly increased risk of starting to use drugs (OR: 1.7) and starting to binge drink frequently (OR: 1.8).CONCLUSIONS: PD and BED are common and predict a range of adverse outcomes. Primary care clinicians should be made aware of these disorders, which may be underrepresented in eating disorder clinic samples. Efforts to prevent eating disorders should focus on cases of subthreshold severity. Pediatrics 2012;130:e289-e295
Among patients who have a history of alcohol problems and are receiving antiretroviral treatment, alcohol consumption was associated with higher HIV RNA levels and lower CD4 counts. No comparable association was found for similar patients who were not receiving HAART. Addressing alcohol use in HIV-infected patients, especially those who are receiving HAART, may have a substantial impact on HIV disease progression.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.