A Step-Up Multiple Test Procedure

Dunnett, Charles W.; Tamhane, Ajit C.

doi:10.2307/2290465

Cited by 97 publications

(89 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, paired combinations typically resulted in more TUBB3 expression in comparison to individual compounds. A one-way ANOVA of average TUBB3 expression and post-hoc analysis (using Dunnett’s correction to account for multiple comparisons) identified 13 neuronal differentiation conditions that were statistically different (p < 0.05) from spontaneous differentiation (Figure 1E) (Dunnett & Tamhane, 1992). Moreover, only paired combinations were significantly different from spontaneous differentiation, and 11 of the 13 significant combinations contained RA.…”

Section: Resultsmentioning

confidence: 99%

High‐throughput identification of factors promoting neuronal differentiation of human neural progenitor cells in microscale 3D cell culture

Nierode

Gopal

Kwon

et al. 2018

Biotech & Bioengineering

View full text Add to dashboard Cite

Identification of conditions for guided and specific differentiation of human stem cell and progenitor cells is important for continued development and engineering of in vitro cell culture systems for use in regenerative medicine, drug discovery, and human toxicology. Three-dimensional (3D) and organotypic cell culture models have been used increasingly for in vitro cell culture because they may better model endogenous tissue environments. However, detailed studies of stem cell differentiation within 3D cultures remain limited, particularly with respect to high-throughput screening. Herein, we demonstrate the use of a microarray chip-based platform to screen, in high-throughput, individual and paired effects of 12 soluble factors on the neuronal differentiation of a human neural progenitor cell line (ReNcell VM) encapsulated in microscale 3D Matrigel cultures. Dose-response analysis of selected combinations from the initial combinatorial screen revealed that the combined treatment of all-trans retinoic acid (RA) with the glycogen synthase kinase 3 inhibitor CHIR-99021 (CHIR) enhances neurogenesis while simultaneously decreases astrocyte differentiation, whereas the combined treatment of brain-derived neurotrophic factor and the small azide neuropathiazol enhances the differentiation into neurons and astrocytes. Subtype specification analysis of RA- and CHIR-differentiated cultures revealed that enhanced neurogenesis was not biased toward a specific neuronal subtype. Together, these results demonstrate a high-throughput screening platform for rapid evaluation of differentiation conditions in a 3D environment, which will aid the development and application of 3D stem cell culture models.

show abstract

Section: Resultsmentioning

confidence: 99%

High‐throughput identification of factors promoting neuronal differentiation of human neural progenitor cells in microscale 3D cell culture

Nierode

Gopal

Kwon

et al. 2018

Biotech & Bioengineering

View full text Add to dashboard Cite

show abstract

“…Dunnett and Tamhane, however, found that the modifications offered by Hommel and Rom resulted in, at best, marginal increases in power. Similarly, Dunnett and Tamhane's (1992) …”

Section: Discussionmentioning

confidence: 98%

“…Therefore, in another context (e.g., a one-way completely randomized design) where other test statistics could be used (e.g., Welch's, 1951, omnibus test for mean equality), the rank ordering found in this study may not apply. 1 Hommel (1988), Rom (1990), and Dunnett and Tamhane (1992) have improved Hochberg's (1988) procedure. Dunnett and Tamhane, however, found that the modifications offered by Hommel and Rom resulted in, at best, marginal increases in power.…”

Section: Discussionmentioning

confidence: 99%

Stepwise and Simultaneous Multiple Comparison Procedures of Repeated Measures’ Means

Keselman

1994

Journal of Educational Statistics

View full text Add to dashboard Cite

Key words: Stepwise and simultaneous multiple comparison procedures, repeated measures designs, balanced and unbalanced nonspherical modelsStepwise multiple comparison procedures (MCPs) for repeated measures' means based on the methods of Hayter were compared for their overall family wise rates of Type I error when multisample sphericity and multivariate normality were not satisfied. Robust stepwise procedures were identified by Keselman, Keselman, and Shaffer (1991) with respect to three definitions of power. On average, Welsch's (1977a) step-up procedure was found to be the most powerful MCP. Keselman, Keselman, and Shaffer (1991) presented robust pairwise simultaneous multiple comparison procedures (MCPs) for repeated measures' means. These MCPs used a nonpooled statistic (i.e., nonpooled across both the between-and within-subjects factors of a two-way mixedmodel repeated measures design) and simultaneous critical values from the Studentized range, Studentized maximum modulus, or Bonferroni t distributions, based on Satterthwaite's (1941Satterthwaite's ( , 1946 solution for degrees of freedom (df). These three simultaneous MCPs were found to be robust with respect to the overall familywise Type I error rate for violations of multisample sphericity and multivariate normality in unbalanced 3x4 and 3x8 mixed-model repeated measures designs. More recently, Keselman (1993) identified 11 stepwise MCPs (which involved adaptations of the procedures of Hayter

show abstract

“…Dunnett and Tamhane (1992) and Rom (1990) both developed stepwise procedures with the motivation of lowering Type II error. Both methods make strong distributional assumptions and require complicated, iterative calculation.…”

Section: Discussionmentioning

confidence: 99%

Comparisons of methods for multiple hypothesis testing in neuropsychological research.

et al. 2009

View full text Add to dashboard Cite

Hypothesis testing with multiple outcomes requires adjustments to control Type I error inflation, which reduces power to detect significant differences. Maintaining the prechosen Type I error level is challenging when outcomes are correlated. This problem concerns many research areas, including neuropsychological research in which multiple, interrelated assessment measures are common. Standard p value adjustment methods include Bonferroni-, Sidak-, and resampling-class methods. In this report, the authors aimed to develop a multiple hypothesis testing strategy to maximize power while controlling Type I error. The authors conducted a sensitivity analysis, using a neuropsychological dataset, to offer a relative comparison of the methods and a simulation study to compare the robustness of the methods with respect to varying patterns and magnitudes of correlation between outcomes. The results lead them to recommend the Hochberg and Hommel methods (step-up modifications of the Bonferroni method) for mildly correlated outcomes and the step-down minP method (a resampling-based method) for highly correlated outcomes. The authors note caveats regarding the implementation of these methods using available software. Neuropsychological datasets typically consist of multiple, partially overlapping measures, henceforth termed outcomes. A given neuropsychological domain-for example, executive function-is composed of multiple interrelated subfunctions, and frequently all subfunction outcomes of interest are subject to hypothesis testing. At a given α (critical threshold), the risk of incorrectly rejecting a null hypothesis, a Type I error, increases as more hypotheses are tested. This applies to all types of hypotheses, including a set of two-group comparisons across multiple outcomes (e.g., differences between two groups across several cognitive measures) or multiple-group comparisons within an analysis of variance framework (e.g., cognitive performance differences between several treatment groups and a control group). Collectively, we define these issues as the multiplicity problem (Pocock, 1997).Controlling Type I error at a desired level is a statistical challenge, further complicated by the correlated outcomes prevalent in neuropsychological data. By making adjustments to control Type I error, we increase the risk of incorrectly accepting a null hypothesis, a Type II error. In other words, we reduce power. Failure to control Type I error when examining multiple outcomes may yield false inferences, which may slow or sidetrack research progress. Researchers need strategies that maximize power while ensuring an acceptable Type I error rate.Many methods exist to manage the multiplicity problem. Several methods are based on the Bonferroni and Sidak inequalities (Sidak, 1967;Simes, 1986). These methods adjust α values or p values using simple functions of the number of tested hypotheses (Sankoh, Huque, & Dubey, 1997;Westfall & Young, 1993). Holm (1979), Hochberg (1988), and Hommel (1988 developed Bonferroni derivatives in...

show abstract

A Step-Up Multiple Test Procedure

Cited by 97 publications

References 0 publications

High‐throughput identification of factors promoting neuronal differentiation of human neural progenitor cells in microscale 3D cell culture

High‐throughput identification of factors promoting neuronal differentiation of human neural progenitor cells in microscale 3D cell culture

Stepwise and Simultaneous Multiple Comparison Procedures of Repeated Measures’ Means

Comparisons of methods for multiple hypothesis testing in neuropsychological research.

Contact Info

Product

Resources

About