Flexible semiparametric analysis of longitudinal genetic studies by reduced rank smoothing

Yuanjia Wang, Chiahui Huang, Yixin Fang, Qiong Yang, Runze Li

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In longitudinal genetic studies, investigators collect repeated measurements on a trait that changes with time along with genetic markers. For family-based longitudinal studies, since repeated measurements are nested within subjects and subjects are nested within families, both the subject level and the measurement level correlations must be taken into account in the statistical analysis to achieve more accurate estimation. In such studies, the primary interests include testing for a quantitative trait locus effect, and estimating the age-specific quantitative trait locus effect and residual polygenic heritability function. We propose flexible semiparametric models and their statistical estimation and hypothesis testing procedures for longitudinal genetic data. We employ penalized splines to estimate non-parametric functions in the model. We find that misspecifying the baseline function or the genetic effect function in a parametric analysis may lead to a substantially inflated or highly conservative type I error rate on testing and large mean-squared error on estimation. We apply the proposed approaches to examine age-specific effects of genetic variants reported in a recent genomewide association study of blood pressure collected in the Framingham Heart Study.

Original languageEnglish (US)
Pages (from-to)1-24
Number of pages24
JournalJournal of the Royal Statistical Society. Series C: Applied Statistics
Volume61
Issue number1
DOIs
StatePublished - Jan 1 2012

Fingerprint

Reduced Rank
Smoothing
Quantitative Trait Loci
Repeated Measurements
Heritability
Penalized Splines
Statistical Estimation
Testing
Parametric Analysis
Type I Error Rate
Longitudinal Study
Semiparametric Model
Blood Pressure
Hypothesis Testing
Mean Squared Error
Statistical Analysis
Baseline
Estimate

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{c663b47adc2b44c3a802f8aa829000f7,
title = "Flexible semiparametric analysis of longitudinal genetic studies by reduced rank smoothing",
abstract = "In longitudinal genetic studies, investigators collect repeated measurements on a trait that changes with time along with genetic markers. For family-based longitudinal studies, since repeated measurements are nested within subjects and subjects are nested within families, both the subject level and the measurement level correlations must be taken into account in the statistical analysis to achieve more accurate estimation. In such studies, the primary interests include testing for a quantitative trait locus effect, and estimating the age-specific quantitative trait locus effect and residual polygenic heritability function. We propose flexible semiparametric models and their statistical estimation and hypothesis testing procedures for longitudinal genetic data. We employ penalized splines to estimate non-parametric functions in the model. We find that misspecifying the baseline function or the genetic effect function in a parametric analysis may lead to a substantially inflated or highly conservative type I error rate on testing and large mean-squared error on estimation. We apply the proposed approaches to examine age-specific effects of genetic variants reported in a recent genomewide association study of blood pressure collected in the Framingham Heart Study.",
author = "Yuanjia Wang and Chiahui Huang and Yixin Fang and Qiong Yang and Runze Li",
year = "2012",
month = "1",
day = "1",
doi = "10.1111/j.1467-9876.2011.01016.x",
language = "English (US)",
volume = "61",
pages = "1--24",
journal = "Journal of the Royal Statistical Society. Series C: Applied Statistics",
issn = "0035-9254",
publisher = "Wiley-Blackwell",
number = "1",

}

Flexible semiparametric analysis of longitudinal genetic studies by reduced rank smoothing. / Wang, Yuanjia; Huang, Chiahui; Fang, Yixin; Yang, Qiong; Li, Runze.

In: Journal of the Royal Statistical Society. Series C: Applied Statistics, Vol. 61, No. 1, 01.01.2012, p. 1-24.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Flexible semiparametric analysis of longitudinal genetic studies by reduced rank smoothing

AU - Wang, Yuanjia

AU - Huang, Chiahui

AU - Fang, Yixin

AU - Yang, Qiong

AU - Li, Runze

PY - 2012/1/1

Y1 - 2012/1/1

N2 - In longitudinal genetic studies, investigators collect repeated measurements on a trait that changes with time along with genetic markers. For family-based longitudinal studies, since repeated measurements are nested within subjects and subjects are nested within families, both the subject level and the measurement level correlations must be taken into account in the statistical analysis to achieve more accurate estimation. In such studies, the primary interests include testing for a quantitative trait locus effect, and estimating the age-specific quantitative trait locus effect and residual polygenic heritability function. We propose flexible semiparametric models and their statistical estimation and hypothesis testing procedures for longitudinal genetic data. We employ penalized splines to estimate non-parametric functions in the model. We find that misspecifying the baseline function or the genetic effect function in a parametric analysis may lead to a substantially inflated or highly conservative type I error rate on testing and large mean-squared error on estimation. We apply the proposed approaches to examine age-specific effects of genetic variants reported in a recent genomewide association study of blood pressure collected in the Framingham Heart Study.

AB - In longitudinal genetic studies, investigators collect repeated measurements on a trait that changes with time along with genetic markers. For family-based longitudinal studies, since repeated measurements are nested within subjects and subjects are nested within families, both the subject level and the measurement level correlations must be taken into account in the statistical analysis to achieve more accurate estimation. In such studies, the primary interests include testing for a quantitative trait locus effect, and estimating the age-specific quantitative trait locus effect and residual polygenic heritability function. We propose flexible semiparametric models and their statistical estimation and hypothesis testing procedures for longitudinal genetic data. We employ penalized splines to estimate non-parametric functions in the model. We find that misspecifying the baseline function or the genetic effect function in a parametric analysis may lead to a substantially inflated or highly conservative type I error rate on testing and large mean-squared error on estimation. We apply the proposed approaches to examine age-specific effects of genetic variants reported in a recent genomewide association study of blood pressure collected in the Framingham Heart Study.

UR - http://www.scopus.com/inward/record.url?scp=84856039615&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856039615&partnerID=8YFLogxK

U2 - 10.1111/j.1467-9876.2011.01016.x

DO - 10.1111/j.1467-9876.2011.01016.x

M3 - Article

AN - SCOPUS:84856039615

VL - 61

SP - 1

EP - 24

JO - Journal of the Royal Statistical Society. Series C: Applied Statistics

JF - Journal of the Royal Statistical Society. Series C: Applied Statistics

SN - 0035-9254

IS - 1

ER -