Scalar-on-function regression for predicting distal outcomes from intensively gathered longitudinal data: Interpretability for applied scientists

John J. Dziak, Donna L. Coffman, Matthew Reimherr, Justin Petrovich, Runze Li, Saul Shiffman, Mariya P. Shiyko

Research output: Contribution to journalArticle

Abstract

Researchers are sometimes interested in predicting a distal or external outcome (such as smoking cessation at follow-up) from the trajectory of an intensively recorded longitudinal variable (such as urge to smoke). This can be done in a semiparametric way via scalar-on-function regression. However, the resulting fitted coefficient regression function requires special care for correct interpretation, as it represents the joint relationship of time points to the outcome, rather than a marginal or cross-sectional relationship. We provide practical guidelines, based on experience with scientific applications, for helping practitioners interpret their results and illustrate these ideas using data from a smoking cessation study.

Original languageEnglish (US)
Pages (from-to)150-180
Number of pages31
JournalStatistics Surveys
Volume13
DOIs
StatePublished - Jan 1 2019

Fingerprint

Smoking
Interpretability
Regression Function
Longitudinal Data
Scalar
Trajectory
Coefficient
Relationships
Longitudinal data
Smoking cessation
Interpretation
Experience
Coefficients

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{ff02dcb58164479cad5325c70fb6d715,
title = "Scalar-on-function regression for predicting distal outcomes from intensively gathered longitudinal data: Interpretability for applied scientists",
abstract = "Researchers are sometimes interested in predicting a distal or external outcome (such as smoking cessation at follow-up) from the trajectory of an intensively recorded longitudinal variable (such as urge to smoke). This can be done in a semiparametric way via scalar-on-function regression. However, the resulting fitted coefficient regression function requires special care for correct interpretation, as it represents the joint relationship of time points to the outcome, rather than a marginal or cross-sectional relationship. We provide practical guidelines, based on experience with scientific applications, for helping practitioners interpret their results and illustrate these ideas using data from a smoking cessation study.",
author = "Dziak, {John J.} and Coffman, {Donna L.} and Matthew Reimherr and Justin Petrovich and Runze Li and Saul Shiffman and Shiyko, {Mariya P.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1214/19-SS126",
language = "English (US)",
volume = "13",
pages = "150--180",
journal = "Statistics Surveys",
issn = "1935-7516",
publisher = "Institute of Mathematical Statistics",

}

Scalar-on-function regression for predicting distal outcomes from intensively gathered longitudinal data : Interpretability for applied scientists. / Dziak, John J.; Coffman, Donna L.; Reimherr, Matthew; Petrovich, Justin; Li, Runze; Shiffman, Saul; Shiyko, Mariya P.

In: Statistics Surveys, Vol. 13, 01.01.2019, p. 150-180.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Scalar-on-function regression for predicting distal outcomes from intensively gathered longitudinal data

T2 - Interpretability for applied scientists

AU - Dziak, John J.

AU - Coffman, Donna L.

AU - Reimherr, Matthew

AU - Petrovich, Justin

AU - Li, Runze

AU - Shiffman, Saul

AU - Shiyko, Mariya P.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Researchers are sometimes interested in predicting a distal or external outcome (such as smoking cessation at follow-up) from the trajectory of an intensively recorded longitudinal variable (such as urge to smoke). This can be done in a semiparametric way via scalar-on-function regression. However, the resulting fitted coefficient regression function requires special care for correct interpretation, as it represents the joint relationship of time points to the outcome, rather than a marginal or cross-sectional relationship. We provide practical guidelines, based on experience with scientific applications, for helping practitioners interpret their results and illustrate these ideas using data from a smoking cessation study.

AB - Researchers are sometimes interested in predicting a distal or external outcome (such as smoking cessation at follow-up) from the trajectory of an intensively recorded longitudinal variable (such as urge to smoke). This can be done in a semiparametric way via scalar-on-function regression. However, the resulting fitted coefficient regression function requires special care for correct interpretation, as it represents the joint relationship of time points to the outcome, rather than a marginal or cross-sectional relationship. We provide practical guidelines, based on experience with scientific applications, for helping practitioners interpret their results and illustrate these ideas using data from a smoking cessation study.

UR - http://www.scopus.com/inward/record.url?scp=85074748920&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074748920&partnerID=8YFLogxK

U2 - 10.1214/19-SS126

DO - 10.1214/19-SS126

M3 - Article

C2 - 31745402

AN - SCOPUS:85074748920

VL - 13

SP - 150

EP - 180

JO - Statistics Surveys

JF - Statistics Surveys

SN - 1935-7516

ER -