Group sequential design: Selecting appropriate bounds.

Anderson, Keaven M.; Clark, Jo

doi:10.1200/jco.2010.28.15_suppl.e13159

Cited by 4 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Correspondingly, we used the gsDesign function from the gsDesign package (Anderson, 2014) with the default settings to compute the expected sample sizes for a GS design with 4 looks (3 interim tests + final test) and the matching FPE and FNE rates. Figure 4 systematically applies this comparison between the (expected) sample sizes of all three designs to all conditions of the simulation and shows the relative efficiency gain of the SBF sample size compared with the NHST-PA fixed- n benchmark and the typical GS design.…”

Section: Resultsmentioning

confidence: 99%

“…We employed a GS design with four looks (three interim looks plus the final look), with a total Type I error rate of 5% and a statistical power of 95%. Necessary sample sizes and critical boundaries were computed using the default settings of the gsDesign package (Anderson, 2014). The planned sample sizes were n = 16, 31, 46, and 61 in each group for the first to the fourth look, with corresponding critical two-sided p values of .0016, .0048, .0147, and .0440.…”

Section: Three Research Designsmentioning

confidence: 99%

See 1 more Smart Citation

Sequential hypothesis testing with Bayes factors: Efficiently testing mean differences.

Schönbrodt

Wagenmakers

Zehetleitner

et al. 2017

Psychological Methods

439

466

View full text Add to dashboard Cite

Unplanned optional stopping rules have been criticized for inflating Type I error rates under the null hypothesis significance testing (NHST) paradigm. Despite these criticisms this research practice is not uncommon, probably as it appeals to researcher's intuition to collect more data in order to push an indecisive result into a decisive region. In this contribution we investigate the properties of a procedure for Bayesian hypothesis testing that allows optional stopping with unlimited multiple testing, even after each participant. In this procedure, which we call Sequential Bayes Factors (SBF), Bayes factors are computed until an a priori defined level of evidence is reached. This allows flexible sampling plans and is not dependent upon correct e↵ect size guesses in an a priori power analysis. We investigated the long-term rate of misleading evidence, the average expected sample sizes, and the biasedness of e↵ect size estimates when an SBF design is applied to a test of mean di↵erences between two groups. Compared to optimal NHST, the SBF design typically needs 50% to 70% smaller samples to reach a conclusion about the presence of an e↵ect, while having the same or lower long-term rate of wrong inference.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Three Research Designsmentioning

confidence: 99%

Sequential hypothesis testing with Bayes factors: Efficiently testing mean differences.

Schönbrodt

Wagenmakers

Zehetleitner

et al. 2017

Psychological Methods

439

466

View full text Add to dashboard Cite

show abstract

“…In a second step, we simulated a GS with four looks (three interim analyses and one final test) for the same population scenarios and nominal error rates. Sample sizes for each step and the respective critical values were calculated with the gsDesign package in R (K. Anderson, 2014).…”

Section: Statistical Error Rates Of Sprt Gs and Sbfsmentioning

confidence: 99%

Controlling decision errors with minimal costs: The sequential probability ratio t test.

Schnuerch

Erdfelder

2020

Psychological Methods

View full text Add to dashboard Cite

show abstract

“…We had preregistered a sequential analysis (Lakens, 2014). That is, we used the R package gsDesign (Anderson, 2016; Version 3.0–1) to determine three equally spaced time points at which we would peak at the data. At the first and second peak, the preregistered criteria for finishing the study earlier were not fulfilled.…”

Section: Methodsmentioning

confidence: 99%

“You’re just envious”: Inferring benign and malicious envy from facial expressions and contextual information.

Lange¹,

Fischer²,

Kleef³

2022

Emotion

View full text Add to dashboard Cite

We have no known conflicts of interest. We report all studies we ever conducted in this line of research. We report how we determined our sample size, all data exclusions (if any), all manipulations, and all measures in the study. The anonymized data, analysis scripts, and materials are available on the Open Science Framework (https://osf.io/n9uvj/). All studies were preregistered (see https://aspredicted.org/3tq2y.pdf, https://aspredicted.org/i9vw6.pdf, https://aspredicted.org/ej26f.pdf). The research reported in this article was supported by grants from the German Research foundation (DFG) awarded to Jens Lange (LA 4029/1-1, LA 4029/2-1). We thank the members of the Department of Social Psychology at the University of Amsterdam for valuable feedback. We also thank Sami Paul Chakkour, Niklas Koch, Franziska Thomiczny, and Johanna Woitzel for serving as actors in Study 3.

show abstract

Group sequential design: Selecting appropriate bounds.

Cited by 4 publications

References 0 publications

Sequential hypothesis testing with Bayes factors: Efficiently testing mean differences.

Sequential hypothesis testing with Bayes factors: Efficiently testing mean differences.

Controlling decision errors with minimal costs: The sequential probability ratio t test.

“You’re just envious”: Inferring benign and malicious envy from facial expressions and contextual information.

Contact Info

Product

Resources

About