東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Strengthening Negative Control Analy...

Park, Jeong-eun,

Linked to FindBook

Google Book

Amazon

博客來

Strengthening Negative Control Analyses in Observational Studies: Evaluating Shared Confounding Structures With Measured Covariates /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Strengthening Negative Control Analyses in Observational Studies: Evaluating Shared Confounding Structures With Measured Covariates // Jeong-eun Park.
Author:	Park, Jeong-eun,
Description:	1 electronic resource (275 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
Contained By:	Dissertations Abstracts International86-11B.
Subject:	Epidemiology. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31932027
ISBN:	9798315741107

Strengthening Negative Control Analyses in Observational Studies: Evaluating Shared Confounding Structures With Measured Covariates /
Park, Jeong-eun,

Strengthening Negative Control Analyses in Observational Studies: Evaluating Shared Confounding Structures With Measured Covariates /Jeong-eun Park. - 1 electronic resource (275 pages)

Source: Dissertations Abstracts International, Volume: 86-11, Section: B.

Negative controls are increasingly used to detect and correct for bias in observational studies, but their effectiveness relies on sharing the same confounding structures as the primary exposure-outcome relationship (U-comparability). Despite their growing use, limited research exists evaluating whether the assumption is met in applied studies. This dissertation addresses this gap through three interconnected aims.Aim 1 systematically reviewed sixteen pharmacoepidemiologic studies employing negative control analyses. The review found that while researchers often reported covariate distributions within negative control analyses, they rarely compared confounding structures directly across primary and negative control analyses. When comparisons were made, methods varied considerably, with no standardized approach for assessing U-comparability.Aim 2 developed and evaluated covariate ranking similarity as a diagnostic tool for assessing U-comparability of negative control exposures (NCEs). This approach compares the rankings of measured covariate effects on the primary exposure and candidate NCEs using rank correlation. Through Monte Carlo simulation, the method was tested under varying conditions of unmeasured confounding strength, direct effects of measured covariates on primary exposure/candidate NCEs not mediated through unmeasured confounders, and measured covariate-unmeasured confounder correlations. Results demonstrated that U-comparable NCEs showed strongly positive rank correlations (Spearman coefficient up to 0.811) that increased with confounding strength. The method performed best when direct covariate effects on exposures were minimized and measured covariate-unmeasured confounder correlations had high variance.Aim 3 applied the covariate ranking similarity approach in a real-world pharmacoepidemiologic study examining associations between oral bisphosphonate (BP) adherence and cardiovascular (CV) events. Using NCEs as proxies for unmeasured confounders, we empirically evaluated multiple candidate negative control outcomes (NCOs) for their U-comparability. Pneumonia and certain preventive services demonstrated strong confounding similarity with the primary outcome as NCOs, while accidents, transfusions, as well as influenza vaccination failed to show comparable associations with NCEs. Limiting bias detection to the empirically validated U-comparable NCOs produced more consistent conclusions on confounding due to overall health/functional status and health-seeking tendency in the CV protective effect of oral BP adherence.This dissertation provides a systematic framework for empirically validating U-comparability in negative control analyses, potentially improving confidence in detecting unmeasured confounding in observational studies.

English

ISBN: 9798315741107Subjects--Topical Terms:

568544
Epidemiology.
Subjects--Index Terms:

Covariate ranking similarity

Strengthening Negative Control Analyses in Observational Studies: Evaluating Shared Confounding Structures With Measured Covariates /
LDR:04375nmm a22004453i 4500 001 2438290
005 20251210114002.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798315741107
035 $a (MiAaPQD)AAI31932027
035 $a AAI31932027
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Park, Jeong-eun, $e author. $3 3829543
245 1 0 $a Strengthening Negative Control Analyses in Observational Studies: Evaluating Shared Confounding Structures With Measured Covariates / $c Jeong-eun Park.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (275 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
500 $a Advisors: Zafari, Zafar Committee members: DosReis, Susan; Camelo Castillo, Wendy; Schuemie, Martijn; Shi, Xu.
502 $b Ph.D. $c University of Maryland, Baltimore $d 2025.
520 $a Negative controls are increasingly used to detect and correct for bias in observational studies, but their effectiveness relies on sharing the same confounding structures as the primary exposure-outcome relationship (U-comparability). Despite their growing use, limited research exists evaluating whether the assumption is met in applied studies. This dissertation addresses this gap through three interconnected aims.Aim 1 systematically reviewed sixteen pharmacoepidemiologic studies employing negative control analyses. The review found that while researchers often reported covariate distributions within negative control analyses, they rarely compared confounding structures directly across primary and negative control analyses. When comparisons were made, methods varied considerably, with no standardized approach for assessing U-comparability.Aim 2 developed and evaluated covariate ranking similarity as a diagnostic tool for assessing U-comparability of negative control exposures (NCEs). This approach compares the rankings of measured covariate effects on the primary exposure and candidate NCEs using rank correlation. Through Monte Carlo simulation, the method was tested under varying conditions of unmeasured confounding strength, direct effects of measured covariates on primary exposure/candidate NCEs not mediated through unmeasured confounders, and measured covariate-unmeasured confounder correlations. Results demonstrated that U-comparable NCEs showed strongly positive rank correlations (Spearman coefficient up to 0.811) that increased with confounding strength. The method performed best when direct covariate effects on exposures were minimized and measured covariate-unmeasured confounder correlations had high variance.Aim 3 applied the covariate ranking similarity approach in a real-world pharmacoepidemiologic study examining associations between oral bisphosphonate (BP) adherence and cardiovascular (CV) events. Using NCEs as proxies for unmeasured confounders, we empirically evaluated multiple candidate negative control outcomes (NCOs) for their U-comparability. Pneumonia and certain preventive services demonstrated strong confounding similarity with the primary outcome as NCOs, while accidents, transfusions, as well as influenza vaccination failed to show comparable associations with NCEs. Limiting bias detection to the empirically validated U-comparable NCOs produced more consistent conclusions on confounding due to overall health/functional status and health-seeking tendency in the CV protective effect of oral BP adherence.This dissertation provides a systematic framework for empirically validating U-comparability in negative control analyses, potentially improving confidence in detecting unmeasured confounding in observational studies.
546 $a English
590 $a School code: 0373
650 4 $a Epidemiology. $3 568544
650 4 $a Health sciences. $3 3168359
650 4 $a Biostatistics. $3 1002712
653 $a Covariate ranking similarity
653 $a Negative control
653 $a Observational studies
653 $a Pharmacoepidemiology
653 $a U-comparability
653 $a Unmeasured confounding
690 $a 0766
690 $a 0566
690 $a 0308
710 2 $a University of Maryland, Baltimore. $b Pharmaceutical Health Services Research. $e degree granting institution. $3 3829419
720 1 $a Zafari, Zafar $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-11B.
790 $a 0373
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31932027