Spatial Randomness Applied to the Assessment of the Association Between a Disease and a Phenotype

• 발행기관: 한국자료분석학회
• 저자명: 이재용(Jaeyong Yee) 박미라(Mira Park)
• 간행물 정보: 『Journal of The Korean Data Analysis Society (JKDAS)』Vol.21 No.6, 2713~2720쪽, 전체 8쪽
• 주제분류: 자연과학 > 통계학
• 파일형태: PDF
• 발행일자: 2019.12.31

영문 초록

In the era of genome-wide association studies, the association of a single or interacting genotypes has been sought with a phenotype. Meanwhile, as the extent of the phenotype that may be measured simultaneously for each subject grows, phenome-wide association studies are gaining importance. Consequently, the classification of individual phenotype with a more complex disease with statistical significance has become a vital necessity. We show that the concept of spatial randomness can be utilized to estimate the degree of association of a phenotype with a disease. Distribution of phenotypic values would form an underlying set. Each of those values are turned on or off according to the subject’s diagnosis for a disease. Idea is such that if the disease was not associated with the phenotype, the subset of the distribution by the turned-on samples would be formed by randomly selected subjects. Original and the subset would coincide in the probability distribution. On the other hand, if there was an association, the whole set and subset of the phenotype would differ in the probability distribution. Method of quantification of the difference leading to the estimation of the statistical significance is proposed.

목차

1. Introduction

2. Methods

3. Analysis

4. Conclusion

References

키워드

spatial randomness disease-phenotype association Kolmogorov-Smirnov test Kuiper’s statistic