Limits...
Influence analysis in quantitative trait loci detection.

Dou X, Kuriki S, Maeno A, Takada T, Shiroishi T - Biom J (2014)

Bottom Line: Besides influence analysis on specific LOD scores, we also develop influence analysis methods on the shape of the LOD score curves.These methods are shown useful in the influence analysis of a real dataset of an experimental population from an F2 mouse cross.By receiver operating characteristic analysis, we confirm that the proposed methods show better performance than existing diagnostics.

View Article: PubMed Central - PubMed

Affiliation: The Institute of Statistical Mathematics, Research Organization of Information and Systems, 10-3 Midori-cho, Tachikawa, Tokyo, 190-8562, Japan.

Show MeSH
Simulation results for Section 6.1. Distributions of the maximum /SEIF/ and their approximations based on 1000 replicates. (A), (B), (C), and (D) are the simulation results under the models M0, M1, M2, and M3, respectively. Solid lines are the empirical distribution functions of simulated T0 and their approximations  when there are no outliers. Dashed lines are empirical distribution functions of simulated T1 and  when one outlier exists. (T0, , T1,  are referred to as “T no outlier,” “ no outlier,” “T outlier,” “ 1 outlier” in the legends, respectively.)
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4282084&req=5

fig04: Simulation results for Section 6.1. Distributions of the maximum /SEIF/ and their approximations based on 1000 replicates. (A), (B), (C), and (D) are the simulation results under the models M0, M1, M2, and M3, respectively. Solid lines are the empirical distribution functions of simulated T0 and their approximations when there are no outliers. Dashed lines are empirical distribution functions of simulated T1 and when one outlier exists. (T0, , T1, are referred to as “T no outlier,” “ no outlier,” “T outlier,” “ 1 outlier” in the legends, respectively.)

Mentions: Figure 4 shows the simulation results for the four models. The empirical distribution functions of Tk and (k=0,1) are depicted as black and gray lines, respectively. We find that the distribution of and are close to each other, which means that the distribution of ( or ) is stable for the existence of outliers. We also find that and are close to T0 and distinct from T1. This indicates that when no outlier exists the false positive rate is appropriately controlled (i.e., unbiased) and when outliers exist it has statistical power in detecting influential individuals. We also tried simulations with two outliers. The results are similar and omitted.


Influence analysis in quantitative trait loci detection.

Dou X, Kuriki S, Maeno A, Takada T, Shiroishi T - Biom J (2014)

Simulation results for Section 6.1. Distributions of the maximum /SEIF/ and their approximations based on 1000 replicates. (A), (B), (C), and (D) are the simulation results under the models M0, M1, M2, and M3, respectively. Solid lines are the empirical distribution functions of simulated T0 and their approximations  when there are no outliers. Dashed lines are empirical distribution functions of simulated T1 and  when one outlier exists. (T0, , T1,  are referred to as “T no outlier,” “ no outlier,” “T outlier,” “ 1 outlier” in the legends, respectively.)
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4282084&req=5

fig04: Simulation results for Section 6.1. Distributions of the maximum /SEIF/ and their approximations based on 1000 replicates. (A), (B), (C), and (D) are the simulation results under the models M0, M1, M2, and M3, respectively. Solid lines are the empirical distribution functions of simulated T0 and their approximations when there are no outliers. Dashed lines are empirical distribution functions of simulated T1 and when one outlier exists. (T0, , T1, are referred to as “T no outlier,” “ no outlier,” “T outlier,” “ 1 outlier” in the legends, respectively.)
Mentions: Figure 4 shows the simulation results for the four models. The empirical distribution functions of Tk and (k=0,1) are depicted as black and gray lines, respectively. We find that the distribution of and are close to each other, which means that the distribution of ( or ) is stable for the existence of outliers. We also find that and are close to T0 and distinct from T1. This indicates that when no outlier exists the false positive rate is appropriately controlled (i.e., unbiased) and when outliers exist it has statistical power in detecting influential individuals. We also tried simulations with two outliers. The results are similar and omitted.

Bottom Line: Besides influence analysis on specific LOD scores, we also develop influence analysis methods on the shape of the LOD score curves.These methods are shown useful in the influence analysis of a real dataset of an experimental population from an F2 mouse cross.By receiver operating characteristic analysis, we confirm that the proposed methods show better performance than existing diagnostics.

View Article: PubMed Central - PubMed

Affiliation: The Institute of Statistical Mathematics, Research Organization of Information and Systems, 10-3 Midori-cho, Tachikawa, Tokyo, 190-8562, Japan.

Show MeSH