MultiDST
Multiple Testing Made Easy
A tool designed for multiple hypothesis testing in statistical analysis. It provides implementations of various methods to control the family-wise error rate (FWER) and false discovery rate (FDR) in scenarios involving multiple hypothesis tests. Significant Index Plot (SIP) can be used to visualize the significant hypotheses under each of the method with ease.
Get Started
Implemented Methods
Bonferroni Correction
Baseline method; simple and conservative.
Bonferroni, C. (1935). Il calcolo delle assicurazioni su gruppi di teste. https://api.semanticscholar.org/CorpusID:89994272
Holm-Bonferroni Correction
Sequential approach; adjusts thresholds progressively.
Holm, S. (1979). A Simple Sequentially Rejective Multiple Test Procedure. Source: Scandinavian Journal of Statistics Scand J Statist, 6(6), 65–70. http://www.jstor.org/stable/4615733%0A http://www.jstor.org/page/info/about/policies/terms.jsp%0A http://www.jstor.org
Benjamini-Hochberg Procedure
Balances power and control; widely used in genomics.
Benjamini, Y., & Hochberg, Y. (1995). "Controlling the false discovery rate: A practical and powerful approach to multiple testing." Journal of the Royal Statistical Society. Series B (Methodological), 57(1), 289-300.
Benjamini-Yekutieli Method
FDR control under dependence; accounts for correlated tests.
Benjamini, Y., & Yekutieli, D. (2001a). The control of the false discovery rate in multiple testing under dependency. Annals of Statistics, 29(4), 1165–1188. https://doi.org/10.1214/aos/1013699998
Storey’s Q Value
Adaptive FDR control; estimates proportion of true null hypotheses.
Storey, J. D., & Tibshirani, R. (2003). Statistical Significance for Genome-Wide Studies.
SGoF Test (Sequential Goodness-of-Fit)
Increased power for large-scale testing; combines p-values from multiple tests.
Carvajal-Rodríguez, A., de Uña-Alvarez, J., & Rolán-Alvarez, E. (2009). A new multitest correction (SGoF) that increases its statistical power when increasing the number of tests. BMC Bioinformatics, 10, 209. https://doi.org/10.1186/1471-2105-10-209
Testimonials
"A very beneficial new method for scientists dealing with gene expression data to narrow down true significant results based on the dataset."
Dr. Isaac Adeyemi Babarinde
Senior Research Associate, SUSTech University - Shenzhen China
"The platform MultiDST has greatly simplified the process of identifying significant product types and cohorts, enabling an efficient approack to decision making with large-scale policy data."
Ms. Fathima Ahmeer
AGM - Life Operations, Janashakthi Insurance PLC
"MultiDST is a very intuitive useful new method with applications in material physics & nano science as well. It is beneficial in material discovery through high-throughput experiments."
Associate Prof. Gayan Hettiarachchi
Associate Professor, Tokyo International University
"MultiDST has significantly streamlined the analysis process of multiple testing with robust features and intuitive visualizations, accelerating complex evaluations for accurate and efficient results."
Dr. Champa Magalle
Senior Lecturer (Statistics), University of Colombo
"MultiDST is a sure method of getting statistically significant results and has proven to be very useful for multiple testing specially in large scale biomedical data."
Dr. Tharindumala Abeywardana
PhD (Senior Scientist) University of California San Diego, Los Angeles, USA
"MultiDST is an extremely useful tool for those working on identifying deferentially expressed genes. This tool brings all the different techniques under one platform to make the analysis process simple."
Dr. Rasika Jayatillake
Senior Lecturer (Statistics), University of Colombo
"MultiDST offers a user-friendly platform for multiple corrections featuring enhanced visualizations, making it useful for genetic researchers working with complex datasets."
Ms. Hashini Coorey
PhD Candidate & Graduate Lab Assistant - Clemson University, SC USA
"MultiDST has significantly reduced the time spent on multiple testing analysis. A great tool for researchers working with high-throughput medical data."
Ms. Rukshala Gunaratne
PhD Candidate - University of Melbourne