在大规模关联研究中,通过获得10个或更多的对照来增加功率,当类型-1错误在大规模关联研究中很小时,每次得到10个或更多的对照
Hormuzd A Katki1, Sonja I Berndt2, Mitchell J Machiela2
1Division of Cancer Epidemiology and Genetics, Department of Health and Human Services, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA. katkih@mail.nih.gov.
BMC medical research methodology
|June 29, 2023
概括
对于小alpha (α) 的全基因组关联研究,每例使用超过4个对照显著增加了统计能力,并降低了最小可检测的几率比率 (OR). 增加对每个病例的控制,特别是大量的控制,提高了对遗传发现的研究能力和精度.
科学领域:
- 遗传学 是一个遗传学.
- 统计遗传学 统计遗传学
- 生物信息学是一种生物信息学.
背景情况:
- 传统的统计功率计算通常假设1型错误率 (α) 为0.05,这表明每例4个控制项之外的收益有限.
- 大规模的关联研究,特别是全基因组关联研究 (GWAS),使用更小的α值 (例如10-6到10-9),并且经常可以获得丰富的对照数据.
- 在严格的显著性值下的关联研究中,每个病例的最佳控制数仍然是最大限度地提高统计能力和最大限度地减少错误发现的重要考虑因素.
研究的目的:
- 调查通过增加每个案例的控制数量超出 4:1 的传统比率来实现的统计功率增长和p值降低.
- 为了评估这些收益,特别是在与大规模遗传关联研究相关的小显著性值 (α) 下进行评估.
- 为了确定对最小可检测的几率比率 (OR) 的影响,随着对照对病例比率的增加.
主要方法:
- 计算统计功率,预期p值的中位数和最小可检测的几率比率 (OR) 作为对照对病例比率的函数.
- 在一系列下降显著性水平 (α) 中进行了分析,从传统的0.05到GWAS典型的非常小的值.
- 评估了增加对这些关键统计指标的个案控制的影响.
主要成果:
- 每个案例的控制数量增加到4个以上,显著提高了统计能力,并降低了p值,特别是在小α值 (10−6到10−9) 中.
- 例如,在α = 5 × 10−8的情况下,每次从4个控制器增加到10个控制器将功率从0.65提高到0.78,而50个控制器将功率提高到0.84.
- 将对照数从1增加到4将可检测的最小OR降低20.9%,而从4增加到50的对照数提供了额外的9.7%的降低,不管α.
结论:
- 在小α时每例招募10个或更多的对照,可以显著增加功率,将预期的p值降低1-2个数量级,并减少最小可检测的OR.
- 较高的对照对病例比率的好处在较大的病例数量中更为明显,并且取决于暴露频率和真实OR.
- 这些发现提倡在大规模关联研究中更广泛地共享可比对照数据,以提高遗传发现的效率和力量.
相关概念视频
01:13Accuracy and Errors in Hypothesis Testing
224
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%...
224
01:14Errors In Hypothesis Tests
4.3K
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.
4.3K
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
148
Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
148
01:10Bonferroni Test
2.8K
The Bonferroni test is a statistical test named after Carlo Emilio Bonferroni, an Italian mathematician best known for Bonferroni inequalities. This statistical test is a type of multiple comparison test to determine which means are different than the rest. Bonferroni test can minimize the Type 1 error by reducing the significance level alpha, which otherwise increases with sample pairs.
The means of different samples are first paired in all possible combinations.
The null hypothesis of the...
The means of different samples are first paired in all possible combinations.
The null hypothesis of the...
2.8K
01:27Confounding in Epidemiological Studies
191
Confounding in statistical epidemiology represents a pivotal challenge, referring to the distortion in the perceived relationship between an exposure and an outcome due to the presence of a third variable, known as a confounder. This variable is associated with both the exposure and the outcome but is not a direct link in their causal chain. Its presence can lead to erroneous interpretations of the exposure's effect, either exaggerating or underestimating the true association. This...
191
01:24Testing a Claim about Population Proportion
3.4K
A complete procedure for testing a claim about a population proportion is provided here.
There are two methods of testing a claim about a population proportion: (1) Using the sample proportion from the data where a binomial distribution is approximated to the normal distribution and (2) Using the binomial probabilities calculated from the data.
The first method uses normal distribution as an approximation to the binomial distribution. The requirements are as follows: sample size is large...
There are two methods of testing a claim about a population proportion: (1) Using the sample proportion from the data where a binomial distribution is approximated to the normal distribution and (2) Using the binomial probabilities calculated from the data.
The first method uses normal distribution as an approximation to the binomial distribution. The requirements are as follows: sample size is large...
3.4K