<b>GFD</b>: An <i>R</i>  Package for the Analysis of General Factorial Designs

Friedrich, Sarah; Konietschke, Frank; Pauly, Markus

doi:10.18637/jss.v079.c01

Cited by 36 publications

(22 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Repeated measures designs and multivariate data will be part of future research. Implementations of the new methods in freely available software packages (eg, within the R‐package GFD 6 ) are envisioned.…”

Section: Discussionmentioning

confidence: 99%

“…The repeated statement allows modeling of the structure of the variance‐covariance matrix of the error term. When no covariates are available (ie, mean comparisons only), the ANOVA‐type statistic is also implemented in the R‐package GFD 6 …”

Section: The Ancova‐type Statisticmentioning

confidence: 99%

“…Pauly et al 4 provide a detailed overview of the different solutions and highlight the so‐called Wald‐type statistic (along with a permutation version) as well as the ANOVA‐type statistic developed by Brunner et al 5 In comparison, the Wald‐type statistic is applicable for large samples only (

n_{i} \approx 50

), while the ANOVA‐type statistic controls the type‐1 error rate accurately even when sample sizes are rather small (

n_{i} \approx 10

). However, both of the statistics found their way into statistical practice and are implemented in prominent software packages like SAS PROC MIXED and in the R‐package GFD 6 . For the analysis of general ANCOVA designs, Zimmermann et al 7 propose a Wald‐type test along with a resampling version (wild‐bootstrap approach) using Heteroscedasticity Consistent Standard Error (HCSE) estimators 8‐11 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis of covariance under variance heteroscedasticity in general factorial designs

Konietschke

Cao

Gunawardana

et al. 2021

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

Adjusting for baseline values and covariates is a recurrent statistical problem in medical science. In particular, variance heteroscedasticity is non‐negligible in experimental designs and ignoring it might result in false conclusions. Approximate inference methods are developed to test null hypotheses formulated in terms of adjusted treatment effects and regression parameters in general analysis of covariance designs with arbitrary numbers of factors. Variance homoscedasticity is not assumed. The distributions of the test statistics are approximated using Box‐type approximation methods. Extensive simulation studies show that the procedures are particularly suitable when sample sizes are rather small. A real data set illustrates the application of the methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: The Ancova‐type Statisticmentioning

confidence: 99%

n_{i} \approx 50

), while the ANOVA‐type statistic controls the type‐1 error rate accurately even when sample sizes are rather small (

n_{i} \approx 10

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of covariance under variance heteroscedasticity in general factorial designs

Konietschke

Cao

Gunawardana

et al. 2021

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…Statistical analysis was performed using RStudio (RStudio Inc., Boston, MA, United States). Data sets were analyzed according to the general factorial design included in the GFD-package in R (Friedrich et al, 2017) using the ANOVA-type approximation for the calculation of p -values. P -values of <0.05 were considered significant.…”

Section: Methodsmentioning

confidence: 99%

Dimethylsulfoxide Inhibits Oligodendrocyte Fate Choice of Adult Neural Stem and Progenitor Cells

et al. 2019

View full text Add to dashboard Cite

Several clinical trials address demyelinating diseases via transplantation of mesenchymal stromal cells (MSCs). Published reports detail that administration of MSCs in patients may provide a beneficial immunomodulation, and that factors secreted by MSCs are potent inducers of oligodendrogenesis. Dimethylsulfoxide (DMSO) is widely used in life science and medicine as solvent, vehicle or cryoprotectant for cells used in transplantation. Importantly, most transplantation protocols do not include the removal of DMSO before injecting the cell suspension into patients. This indifferent application of DMSO is coming under increasing scrutiny following reports investigating its potential toxic side-effects. While the impact of DMSO on the central nervous system (CNS) has been partially studied, its effect on oligodendrocytes and oligodendrogenesis has not been addressed yet. Consequently, we evaluated the influence of DMSO on oligodendrogenesis, and on the pro-oligodendrogenic effect of MSCs’ secreted factors, using adult rat neural stem and progenitor cells (NSPCs). Here, we demonstrate that a concentration of 1% DMSO robustly suppressed oligodendrogenesis and drove the fate of differentiating NSPCs toward astrogenesis. Furthermore, the pro-oligodendrogenic effect of MSC-conditioned medium (MSCCM) was also nearly completely abolished by the presence of 1% DMSO. In this condition, inhibition of the Erk1/2 signal transduction pathway and high levels of Id2 expression, a specific inhibitor of oligodendrogenic differentiation, were detected. Furthermore, inflammatory demyelinating diseases may even potentiate the impact of DMSO on oligodendrogenesis. Our results demonstrate the imperative of considering the strong anti-oligodendrogenic activity of DMSO when designing future clinical trial protocols.

show abstract

“…This procedure has been implemented in the GFD R package. 12 An interesting discussion in Thangavelu and Brunner (2007) 13 highlights that methods based on within-stratum ranks may lead to paradoxical results due to the nontransitivity issue and Efron's parodox dice. 14 In order to circumvent this nontransitivity issue, the authors provided a modification of the AT statistic proposed by Brunner et al (1997) 10 based on an unweighted average of all the distributions.…”

Section: Introductionmentioning

confidence: 99%

Stratified two‐sample design: A review on nonparametric methods

Arboretti

Ceccato

Salmaso

2020

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

In this article, a comparison between the most promising nonparametric tests in a two-sample stratified design for practical uses is performed. We compared methods that exhibit good small-sample properties in order to be used with the most common stratum sizes. From the literature we identified as promising the following solutions: the aligned rank test, a small-sample approximation for the ANOVA-type statistic based on an unweighted average of all the distributions, and an asymptotic permutation distribution for the Wald-type statistic. We also developed a permutation version of the aligned rank test and another permutation testing procedure based on the Mann-Whitney statistic using the nonparametric combination procedure. All selected methods were compared by means of a simulation study. The results show that the aligned rank test and its permutation version perform better in most of the considered situations. Data from a genuine industrial problem were used for illustration purposes and to confirm the simulation results.

show abstract

GFD: An R Package for the Analysis of General Factorial Designs

Cited by 36 publications

References 15 publications

Analysis of covariance under variance heteroscedasticity in general factorial designs

Analysis of covariance under variance heteroscedasticity in general factorial designs

Dimethylsulfoxide Inhibits Oligodendrocyte Fate Choice of Adult Neural Stem and Progenitor Cells

Stratified two‐sample design: A review on nonparametric methods

Contact Info

Product

Resources

About