Related Experiment Video
Updated: May 16, 2025
12:22
The Use of Reverse Phase Protein Arrays RPPA to Explore Protein Expression Variation within Individual Renal Cell Cancers
Published on: January 22, 2013
33.5K
A computationally efficient approach to false discovery rate control and power maximisation via randomisation and
Marco Molinari1, Magne Thoresen1
1Department of Biostatistics, University of Oslo, Oslo, Norway.
Statistical Methods in Medical Research
|April 1, 2025
Summary
This study introduces a novel strategy for high-dimensional regression by combining the Mirror Statistic for false discovery rate (FDR) control with outcome randomization. This approach enhances statistical power in variable selection, particularly with complex datasets.
Area of Science:
- Statistics
- Machine Learning
- Computational Biology
Background:
- Variable selection and inference in high-dimensional regression models present significant statistical challenges.
- High-dimensional data necessitates specialized procedures for accurate predictor selection and false discovery rate (FDR) control.
Purpose of the Study:
- To propose a novel strategy for variable selection and FDR control in high-dimensional regression.
- To enhance the statistical power of variable selection procedures using outcome randomization.
- To combine the Mirror Statistic approach with outcome randomization for improved performance.
Main Methods:
- The study jointly adopts the Mirror Statistic approach for FDR control.
- Outcome randomization is employed as an alternative to data splitting to generate independent outcomes.
- Regression coefficients are estimated using these independent outcomes for Mirror Statistic construction.
Main Results:
- The proposed strategy effectively combines the benefits of the Mirror Statistic and outcome randomization.
- Increased statistical power (true positive rate) was observed in simulations, especially with highly correlated covariates and a high percentage of active variables.
- The method demonstrates scalability to very high-dimensional problems with a low memory footprint.
Conclusions:
- The joint adoption of the Mirror Statistic and outcome randomization offers a powerful and scalable solution for variable selection in high-dimensional regression.
- This approach overcomes limitations of traditional data splitting methods, providing enhanced power and efficiency.
- The proposed method is suitable for complex datasets common in modern statistical and machine learning applications.
Keywords:
False discovery rategene expressionhigh-dimensional regressionpost-selection inferencevariable selectionMore Related Videos
Related Concept Videos
01:13Randomized Experiments
6.6K
The randomization process involves assigning study participants randomly to experimental or control groups based on their probability of being equally assigned. Randomization is meant to eliminate selection bias and balance known and unknown confounding factors so that the control group is similar to the treatment group as much as possible. A computer program and a random number generator can be used to assign participants to groups in a way that minimizes bias.
Simple randomization
Simple...
Simple randomization
Simple...
6.6K
01:17Wald-Wolfowitz Runs Test II
165
The Wald-Wolfowitz runs test, commonly referred to as the runs test, is a nonparametric test used to assess the randomness of ordered data. The test evaluates the number of runs, which are consecutive sequences of similar elements within the data. If the number of runs is significantly higher or lower than expected, the data is considered non-random, indicating a detectable pattern or structure.
For binary data, runs are identified using symbols such as + and −, or equivalently, 1s and...
For binary data, runs are identified using symbols such as + and −, or equivalently, 1s and...
165
01:14Errors In Hypothesis Tests
4.1K
When performing a hypothesis test, there are four possible outcomes depending on the actual truth (or falseness) of the null hypothesis and the decision to reject or not.
4.1K
01:09Censoring Survival Data
50
Survival analysis is a statistical method used to analyze time-to-event data, often employed in fields such as medicine, engineering, and social sciences. One of the key challenges in survival analysis is dealing with incomplete data, a phenomenon known as "censoring." Censoring occurs when the event of interest (such as death, relapse, or system failure) has not occurred for some individuals by the end of the study period or is otherwise unobservable, and it might have many different...
50
01:13Accuracy and Errors in Hypothesis Testing
163
Hypothesis testing is a fundamental statistical tool that begins with the assumption that the null hypothesis H0 is true. During this process, two types of errors can occur: Type I and Type II. A Type I error refers to the incorrect rejection of a true null hypothesis, while a Type II error involves the failure to reject a false null hypothesis.
In hypothesis testing, the probability of making a Type I error, denoted as α, is commonly set at 0.05. This significance level indicates a 5%...
In hypothesis testing, the probability of making a Type I error, denoted as α, is commonly set at 0.05. This significance level indicates a 5%...
163
01:11Blinding
2.3K
Blinding is a commonly used method of not telling participants which treatment a subject is receiving. Blinding is a critical part of a randomized control trial or RCT. It reduces the bias that affects the results. In an RCT, blinding is used in the form of a placebo. A placebo effect occurs when untreated subjects falsely believe they have received the treatment and report improved symptoms. A placebo or a dummy treatment is administered to subjects to negate the bias caused by such an effect.
2.3K