Controlled pattern imputation for sensitivity analysis of longitudinal binary and ordinal outcomes with nonignorable dropout

Tang, Yongqiang

doi:10.1002/sim.7583

Cited by 18 publications

(68 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is not straightforward to define the transformed variable

y_{i j}^{*}

for ordinal or nominal outcomes or when there are nonlinear predictors. By noting that the IRLS algorithm is equivalent to Fisher's score algorithm, Tang proposes to sample the candidate

{bold-italicβ}_{j}^{*}

from

{bold-italicβ}_{j}^{*} \sim N ([], β_{j} + normalΣ false(β_{j} false) false(boldU false(β_{j} false) + R_{j} v_{j} false), normalΣ false(β_{j} false)) .

The proposal distributions and are similar especially when the prior for β j is noninformative. We will use the latter one.…”

Section: Mda Algorithmmentioning

confidence: 99%

“…If the imputation contains only the normal linear models with the conditional mean

normalE false(y_{i j} false| y_{i 1}, …, y_{i j - 1} false) = \sum_{k = 1}^{q} x_{i k} α_{j k} + \sum_{k = 1}^{j - 1} β_{j k} y_{i k}

, the MH sampler for y i c becomes a Gibbs sampler ( A j y ≡1) and the proposed algorithm reduced to the MDA algorithm for multivariate normal data (except that the priors may be different). For longitudinal binary or ordinal outcomes, the above algorithm is identical to that of Tang …”

Section: Mda Algorithmmentioning

confidence: 99%

“…There is no restriction on the order of the response variables. The MDA algorithms of Tang are special cases of the proposed algorithm when the data contain only one type of response variable (continuous, binary, or ordinal). Section 2.2 extends the algorithm to incorporate the skew‐normal and skew‐t regressions for nonnormal continuous outcomes and discusses the potential extension to include other types of regression models.…”

Section: Introductionmentioning

confidence: 99%

“…The regulatory guidelines and a FDA‐mandated panel report from the National Research Council recommend sensitivity analysis under missing not at random (MNAR) in the sense that the response profiles for subjects who withdraw are systematically different from those who remain on the treatment. The controlled pattern imputations, pioneered by Little and Yau, assume that the treatment effect reduces or disappears after the treatment discontinuation by taking into account of the treatment actually received after dropout . These methods have become increasingly popular in clinical trials because the underlying MNAR assumption is clinically plausible and easy to interpret.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A monotone data augmentation algorithm for multivariate nonnormal data: With applications to controlled imputations for longitudinal trials

Tang

2018

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

An efficient monotone data augmentation (MDA) algorithm is proposed for missing data imputation for incomplete multivariate nonnormal data that may contain variables of different types and are modeled by a sequence of regression models including the linear, binary logistic, multinomial logistic, proportional odds, Poisson, negative binomial, skew‐normal, skew‐t regressions, or a mixture of these models. The MDA algorithm is applied to the sensitivity analyses of longitudinal trials with nonignorable dropout using the controlled pattern imputations that assume the treatment effect reduces or disappears after subjects in the experimental arm discontinue the treatment. We also describe a heuristic approach to implement the controlled imputation, in which the fully conditional specification method is used to impute the intermediate missing data to create a monotone missing pattern, and the missing data after dropout are then imputed according to the assumed nonignorable mechanisms. The proposed methods are illustrated by simulation and real data analyses. Sample SAS code for the analyses is provided in the supporting information

show abstract

“…However, it is not straightforward to define the transformed variable

y_{i j}^{*}

for ordinal or nominal outcomes or when there are nonlinear predictors. By noting that the IRLS algorithm is equivalent to Fisher's score algorithm, Tang proposes to sample the candidate

{bold-italicβ}_{j}^{*}

from

{bold-italicβ}_{j}^{*} \sim N ([], β_{j} + normalΣ false(β_{j} false) false(boldU false(β_{j} false) + R_{j} v_{j} false), normalΣ false(β_{j} false)) .

The proposal distributions and are similar especially when the prior for β j is noninformative. We will use the latter one.…”

Section: Mda Algorithmmentioning

confidence: 99%

“…If the imputation contains only the normal linear models with the conditional mean

normalE false(y_{i j} false| y_{i 1}, …, y_{i j - 1} false) = \sum_{k = 1}^{q} x_{i k} α_{j k} + \sum_{k = 1}^{j - 1} β_{j k} y_{i k}

Section: Mda Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A monotone data augmentation algorithm for multivariate nonnormal data: With applications to controlled imputations for longitudinal trials

Tang

2018

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…Biologists have used the term to model the point of interruption of equilibrium of animal groups, for example, the point when birds form flight flocks or when monkeys join fight groups . For statisticians, a tipping point occurs when missing‐at‐random dropouts and not‐missing‐at random dropouts make a difference in research study results . For sociologists, a tipping point occurs when 10% of the population strongly embraces a specific notion.…”

Section: Introductionmentioning

confidence: 99%

“Tipping point” concept analysis in the family caregiving context

et al. 2019

View full text Add to dashboard Cite

Aim Analyze the concept “tipping point” in the older adult family caregiving context to further knowledge about caregiving families, enhancing transdisciplinary theory, research, and practice. Background While used commonly in some disciplines, how “tipping point” has been used in health care, generally, and in relation to caregiving families, specifically, is less clear. This project was conducted to offer conceptual clarity to tipping point. Design Walker and Avant's framework. Data Source Searches of scholarly literature in PsycINFO, CINAHL, and PubMed using the search term “tipping point” in either title or abstract. Review Methods Definitions used were extracted; instances when the concept was implied but the actual term “tipping point” was not used and contexts where the term was used or implied were identified. Results The composite definition of a caregiving tipping point is a seemingly abrupt, severe, and absolute change event involving either the older adult or caregiver(s), or both that indicates a breakdown in the status quo of the caregiving system. Conclusions Transdisciplinary research, care, and policy should treat caregiving families as complex systems, use longitudinal assessments, and include colloquial communication. Early detection of impending tipping points will provide family‐centered decisional support and enhance families’ quality of life and safety.

show abstract

Reference‐based multiple imputation for missing data sensitivity analyses in trial‐based cost‐effectiveness analysis

et al. 2019

View full text Add to dashboard Cite

Missing data are a common issue in cost‐effectiveness analysis (CEA) alongside randomised trials and are often addressed assuming the data are ‘missing at random’. However, this assumption is often questionable, and sensitivity analyses are required to assess the implications of departures from missing at random. Reference‐based multiple imputation provides an attractive approach for conducting such sensitivity analyses, because missing data assumptions are framed in an intuitive way by making reference to other trial arms. For example, a plausible not at random mechanism in a placebo‐controlled trial would be to assume that participants in the experimental arm who dropped out stop taking their treatment and have similar outcomes to those in the placebo arm. Drawing on the increasing use of this approach in other areas, this paper aims to extend and illustrate the reference‐based multiple imputation approach in CEA. It introduces the principles of reference‐based imputation and proposes an extension to the CEA context. The method is illustrated in the CEA of the CoBalT trial evaluating cognitive behavioural therapy for treatment‐resistant depression. Stata code is provided. We find that reference‐based multiple imputation provides a relevant and accessible framework for assessing the robustness of CEA conclusions to different missing data assumptions.

show abstract

Controlled pattern imputation for sensitivity analysis of longitudinal binary and ordinal outcomes with nonignorable dropout

Cited by 18 publications

References 42 publications

A monotone data augmentation algorithm for multivariate nonnormal data: With applications to controlled imputations for longitudinal trials

A monotone data augmentation algorithm for multivariate nonnormal data: With applications to controlled imputations for longitudinal trials

“Tipping point” concept analysis in the family caregiving context

Reference‐based multiple imputation for missing data sensitivity analyses in trial‐based cost‐effectiveness analysis

Contact Info

Product

Resources

About