Two‐Stage Group Sequential Robust Tests in Family‐Based Association Studies: Controlling Type I Error

Yan, Lihan; Zheng, Gang; Li, Zhaohai

doi:10.1111/j.1469-1809.2008.00435.x

Cited by 9 publications

(10 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Twostage procedures with simultaneous analysis of a recessive, an additive and a dominant test statistic for case-parent trio designs have recently been proposed by Yan and colleagues (Yan et al, 2008). These authors use Bonferroni-type upper bounds for the type I error risk and consider nominal significance levels around 0.05, which is appropriate for candidate gene association studies.…”

Section: Introductionmentioning

confidence: 99%

Optimal Robust Two‐Stage Designs for Genome‐Wide Association Studies

Nguyen¹,

Pahl²,

Schäfer³

2009

Annals of Human Genetics

View full text Add to dashboard Cite

SummaryOptimal robust two-stage designs for genome-wide association studies are proposed using the maximum of the recessive, additive and dominant linear trend test statistics. These designs combine cost-saving two-stage genotyping with robustness against misspecification of the genetic model and are much more efficient than designs based on a single model specific test statistic in detecting multiple loci with different modes of inheritance. For given power of 90%, typical cost savings of 34% can be realised by increasing the total sample size by about 13% but genotyping only about half of the sample for the full marker set in the first stage and carrying forward about 0.06% of the markers to the second stage analysis. We also present robust two-stage designs providing optimal allocation of a limited budget for pre-existing samples. If a sample is available which would yield a power of 90% when fully genotyped, genotyping only half of the sample due to a limited budget will typically cause a loss of power of more than 55%. Using an optimal two-stage approach in the same sample under the same budget restrictions will limit the loss of power to less than 10%. In general, the optimal proportion of markers to be followed up in the second stage strongly depends on the cost ratio for chips and individual genotyping, while the design parameters of the optimal designs (total sample size, first stage proportion, first and second stage significance limit) do not much depend on the genetic model assumptions.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimal Robust Two‐Stage Designs for Genome‐Wide Association Studies

Nguyen¹,

Pahl²,

Schäfer³

2009

Annals of Human Genetics

View full text Add to dashboard Cite

show abstract

“…Among several approximations studied by Efron (1997), Yan et al (2008) found the two-point formula is simple to use and controls the Type I error reasonably well. We consider MAX3 = max(|Z 0 |, |Z 1/2 |, |Z 1 |) with a target α/2 level.…”

Section: Applying Max3 In Sequential Designmentioning

confidence: 99%

“…Using an approximation of the tail probability for maximal-type statistics studied by Efron (1997), Yan et al (2008) proposed tools for obtaining the critical values when MAX3 was used as the test statistic in a two-stage group sequential design for a family-based genetic study. In the family-based association study, MAX3 has the same form as that for the case-control study.…”

Section: Applying Max3 In Sequential Designmentioning

confidence: 99%

“…However, the test statistics Z θ are different, so are their correlations. The goals of Yan et al (2008) were to study how to find critical values using Efron's approaches and a specific alpha spending function so that the overall Type I error is controlled due to using MAX3 sequentially. It should be noted that in Yan et al (2008), the design parameters were fixed so that the thresholds for the two stages can be determined to control Type I errors.…”

Section: Applying Max3 In Sequential Designmentioning

confidence: 99%

“…The goals of Yan et al (2008) were to study how to find critical values using Efron's approaches and a specific alpha spending function so that the overall Type I error is controlled due to using MAX3 sequentially. It should be noted that in Yan et al (2008), the design parameters were fixed so that the thresholds for the two stages can be determined to control Type I errors. In the next section, we will examine the performance (in terms of minimum ASN or maximum statistical power) of two-stage designs with changes of these design parameters.…”

Section: Applying Max3 In Sequential Designmentioning

confidence: 99%

See 2 more Smart Citations

Optimal two-stage sequential robust design for gene-intervention studies

Liu

Yan

et al. 2011

Statistics and Its Interface

Self Cite

View full text Add to dashboard Cite

Gene-intervention studies investigate the responsiveness to therapies according to individuals' genetic profiles. We propose a two-stage sequential design for these studies and investigate the cost of the sample size versus the statistical power. In a typical sequential design, a single normally distributed test statistic is used. For a genetic study, the robust test is used because of the uncertainty of the underlying genetic model (e.g. the recessive, additive or dominant models). The robust test statistic that we consider in the twostage sequential design is the maximum of three correlated normally distributed statistics, each which is optimal under the corresponding genetic model. We study various factors that affect minimizing the average sample number (ASN) or maximizing the power of a gene-intervention study under the two-stage sequential design and make recommendations for the optimal solutions under different scenarios.AMS 2000 subject classifications: 92D10.

show abstract

Efficiency robust statistics for genetic linkage and association studies under genetic model uncertainty

Joo

Kwak

Chen

et al. 2009

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

When testing genetic linkage and association, test statistics that follow a normal or Chi-square distributions are often used. These statistics are usually derived under a specific mode of inheritance (genetic model). Common genetic models include, but not limited to, the recessive, additive, multiplicative, and dominant models. For many diseases, their underlying genetic models are often unknown. Instead, a family of scientifically plausible genetic models may be available, which includes the four commonly used models. Hence, the optimal test is not available. Employing a single test statistic which is optimal for one model may suffer from substantial loss of power when the model is misspecified. In this situation efficient robust tests are useful. In this tutorial, we first review several commonly used robust statistics, including maximum efficiency robust tests, maximal tests, and constrained likelihood ratio tests for three common designs in genetic studies: (i) linkage analysis using affected sib-pairs, (ii) association studies using parents-offspring trios, and (iii) case-control association studies (unmatched and matched). Codes in the R statistical language for applying these robust statistics to test for linkage and association are presented with examples. We also provide some comparisons of the performance of the various robust tests via simulation studies. Guidelines for applications are also given for each study design. Finally, applications of robust tests to genome-wide association studies and meta-analysis are discussed.

show abstract

Two‐Stage Group Sequential Robust Tests in Family‐Based Association Studies: Controlling Type I Error

Cited by 9 publications

References 32 publications

Optimal Robust Two‐Stage Designs for Genome‐Wide Association Studies

Optimal Robust Two‐Stage Designs for Genome‐Wide Association Studies

Optimal two-stage sequential robust design for gene-intervention studies

Efficiency robust statistics for genetic linkage and association studies under genetic model uncertainty

Contact Info

Product

Resources

About