Causal Inference from 2K Factorial Designs by Using Potential Outcomes

Dasgupta, Tirthankar; Pillai, Natesh S.; Rubin, Donald B.

doi:10.1111/rssb.12085

Cited by 77 publications

(137 citation statements)

References 28 publications

Supporting

Mentioning

135

Contrasting

Order By: Relevance

“…To ensure self-containment, we first review the randomization-based causal inference framework for completely randomized factorial designs. Although most materials are adapted from Dasgupta et al (2015) and Lu (2016a,b), some are refined for better clarity. For more detailed discussions on factorial designs, see, e.g., Wu and Hamada (2009).…”

Section: Factorial Designsmentioning

confidence: 99%

“…To investigate multiple factors simultaneously, 2 K factorial designs (Fisher 1935;Yates 1937) can be employed. Randomization-based casual inference for factorial designs has deep roots in the experimental design literature (e.g., Kempthrone 1952), and was recently presented using the language of potential outcomes (Dasgupta et al 2015;Mukerjee et al 2016).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On randomization-based causal inference for matched-pair factorial designs

Deng

2017

Statistics & Probability Letters

View full text Add to dashboard Cite

show abstract

Section: Factorial Designsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

On randomization-based causal inference for matched-pair factorial designs

Deng

2017

Statistics & Probability Letters

View full text Add to dashboard Cite

show abstract

“…The calculated sample size was based on detecting the main factorial effects of each factor on Multidimensional Fatigue Inventory (MFI) Physical Fatigue (PF) after completed intervention [32–34]. The target main effect size was determined to be 2, which according to Purcell et al [35] is the minimal clinically important difference for the MFI-PF.…”

Section: Methodsmentioning

confidence: 99%

Design of a randomized controlled trial of physical training and cancer (Phys-Can) – the impact of exercise intensity on cancer related fatigue, quality of life and disease outcome

et al. 2017

View full text Add to dashboard Cite

BackgroundCancer-related fatigue is a common problem in persons with cancer, influencing health-related quality of life and causing a considerable challenge to society. Current evidence supports the beneficial effects of physical exercise in reducing fatigue, but the results across studies are not consistent, especially in terms of exercise intensity. It is also unclear whether use of behaviour change techniques can further increase exercise adherence and maintain physical activity behaviour. This study will investigate whether exercise intensity affects fatigue and health related quality of life in persons undergoing adjuvant cancer treatment. In addition, to examine effects of exercise intensity on mood disturbance, adherence to oncological treatment, adverse effects from treatment, activities of daily living after treatment completion and return to work, and behaviour change techniques effect on exercise adherence. We will also investigate whether exercise intensity influences inflammatory markers and cytokines, and whether gene expressions following training serve as mediators for the effects of exercise on fatigue and health related quality of life.Methods/designSix hundred newly diagnosed persons with breast, colorectal or prostate cancer undergoing adjuvant therapy will be randomized in a 2 × 2 factorial design to following conditions; A) individually tailored low-to-moderate intensity exercise with or without behaviour change techniques or B) individually tailored high intensity exercise with or without behaviour change techniques. The training consists of both resistance and endurance exercise sessions under the guidance of trained coaches. The primary outcomes, fatigue and health related quality of life, are measured by self-reports. Secondary outcomes include fitness, mood disturbance, adherence to the cancer treatment, adverse effects, return to activities of daily living after completed treatment, return to work as well as inflammatory markers, cytokines and gene expression.DiscussionThe study will contribute to our understanding of the value of exercise and exercise intensity in reducing fatigue and improving health related quality of life and, potentially, clinical outcomes. The value of behaviour change techniques in terms of adherence to and maintenance of physical exercise behaviour in persons with cancer will be evaluated.Trial registration NCT02473003, October, 2014.

show abstract

“…Motivated by several relevant discussions in the existing literature (Freedman 2008;Lin 2013;Dasgupta et al 2015;Ding and Dasgupta 2016;Ding 2017), Lu (2016a,b) proved the consistency and asymptotic Normality of the randomization-based estimator in (2), and derived its sampling variance as…”

Section: Otherwise;mentioning

confidence: 99%

Sharpening randomization-based causal inference for 2² factorial designs with binary outcomes

2017

Stat Methods Med Res

View full text Add to dashboard Cite

In medical research, a scenario often entertained is randomized controlled 2 2 factorial design with a binary outcome. By utilizing the concept of potential outcomes, Dasgupta et al.(2015) proposed a randomization-based causal inference framework, allowing flexible and simultaneous estimations and inferences of the factorial effects. However, a fundamental challenge that Dasgupta et al. (2015)'s proposed methodology faces is that the sampling variance of the randomization-based factorial effect estimator is unidentifiable, rendering the corresponding classic "Neymanian" variance estimator suffering from over-estimation. To address this issue, for randomized controlled 2 2 factorial designs with binary outcomes, we derive the sharp lower bound of the sampling variance of the factorial effect estimator, which leads to a new variance estimator that sharpens the finite-population Neymanian causal inference. We demonstrate the advantages of the new variance estimator through a series of simulation studies, and apply our newly proposed methodology to two real-life datasets from randomized clinical trials, where we gain new insights.

show abstract

Causal Inference from 2K Factorial Designs by Using Potential Outcomes

Cited by 77 publications

References 28 publications

On randomization-based causal inference for matched-pair factorial designs

On randomization-based causal inference for matched-pair factorial designs

Design of a randomized controlled trial of physical training and cancer (Phys-Can) – the impact of exercise intensity on cancer related fatigue, quality of life and disease outcome

Sharpening randomization-based causal inference for 2² factorial designs with binary outcomes

Contact Info

Product

Resources

About

Causal Inference from 2K Factorial Designs by Using Potential Outcomes

Cited by 77 publications

References 28 publications

On randomization-based causal inference for matched-pair factorial designs

On randomization-based causal inference for matched-pair factorial designs

Design of a randomized controlled trial of physical training and cancer (Phys-Can) – the impact of exercise intensity on cancer related fatigue, quality of life and disease outcome

Sharpening randomization-based causal inference for 22 factorial designs with binary outcomes

Contact Info

Product

Resources

About

Sharpening randomization-based causal inference for 2² factorial designs with binary outcomes