Revisiting the Table 2 fallacy: A motivating example examining preeclampsia and preterm birth

被引:32
作者
Bandoli, Gretchen [1 ]
Palmsten, Kristin [2 ]
Chambers, Christina D. [1 ,3 ]
Jelliffe-Pawlowski, Laura L. [4 ,5 ]
Baer, Rebecca J. [1 ,4 ]
Thompson, Caroline A. [6 ,7 ]
机构
[1] Univ Calif San Diego, Dept Pediat, La Jolla, CA 92093 USA
[2] HealthPartners Inst, Minneapolis, MN USA
[3] Univ Calif San Diego, Dept Family Med & Publ Hlth, La Jolla, CA 92093 USA
[4] Univ Calif San Francisco, Dept Epidemiol & Biostat, San Francisco, CA 94143 USA
[5] Univ Calif San Francisco, Sch Med, Calif Preterm Birth Initiat, San Francisco, CA USA
[6] San Diego State Univ, Grad Sch Publ Hlth, San Diego, CA 92182 USA
[7] Sutter Hlth, Palo Alto Med Fdn Res Inst, Palo Alto, CA USA
基金
美国国家卫生研究院;
关键词
measures of effect; perinatal epidemiology; preterm birth; Table; 2; Fallacy; RISK-FACTORS; ALCOHOL-CONSUMPTION; GESTATIONAL-AGE; MORTALITY; DELIVERY;
D O I
10.1111/ppe.12474
中图分类号
R1 [预防医学、卫生学];
学科分类号
1004 ; 120402 ;
摘要
BackgroundA Table Fallacy, as coined by Westreich and Greenland, reports multiple adjusted effect estimates from a single model. This practice, which remains common in published literature, can be problematic when different types of effect estimates are presented together in a single table. The purpose of this paper is to quantitatively illustrate this potential for misinterpretation with an example estimating the effects of preeclampsia on preterm birth. MethodsWe analysed a retrospective population-based cohort of 2963888 singleton births in California between 2007 and 2012. We performed a modified Poisson regression to calculate the total effect of preeclampsia on the risk of PTB, adjusting for previous preterm birth. pregnancy alcohol abuse, maternal education, and maternal socio-demographic factors (Model 1). In subsequent models, we report the total effects of previous preterm birth, alcohol abuse, and education on the risk of PTB, comparing and contrasting the controlled direct effects, total effects, and confounded effect estimates, resulting from Model 1. ResultsThe effect estimate for previous preterm birth (a controlled direct effect in Model 1) increased 10% when estimated as a total effect. The risk ratio for alcohol abuse, biased due to an uncontrolled confounder in Model 1, was reduced by 23% when adjusted for drug abuse. The risk ratio for maternal education, solely a predictor of the outcome, was essentially unchanged. ConclusionsReporting multiple effect estimates from a single model may lead to misinterpretation and lack of reproducibility. This example highlights the need for careful consideration of the types of effects estimated in statistical models.
引用
收藏
页码:390 / 397
页数:8
相关论文
共 30 条
[1]   Alcohol consumption during pregnancy and the risk of early stillbirth among singletons [J].
Aliyu, Muktar H. ;
Wilson, Ronee E. ;
Zoorob, Roger ;
Chakrabartya, Sangita ;
Alio, Amina P. ;
Kirby, Russell S. ;
Salihu, Hamisu M. .
ALCOHOL, 2008, 42 (05) :369-374
[2]   Confounding, causality, and confusion: the role of intermediate variables in interpreting observational studies in obstetrics [J].
Ananth, Cande V. ;
Schisterman, Enrique F. .
AMERICAN JOURNAL OF OBSTETRICS AND GYNECOLOGY, 2017, 217 (02) :167-175
[3]   Placental Abruption and Perinatal Mortality With Preterm Delivery as a Mediator: Disentangling Direct and Indirect Effects [J].
Ananth, Cande V. ;
VanderWeele, Tyler J. .
AMERICAN JOURNAL OF EPIDEMIOLOGY, 2011, 174 (01) :99-108
[4]   Preeclampsia, and preterm birth subtypes in Nova Scotia, 1986 to 1992 [J].
Ananth, CV ;
Savitz, DA ;
Luther, ER ;
Bowes, WA .
AMERICAN JOURNAL OF PERINATOLOGY, 1997, 14 (01) :17-23
[5]  
[Anonymous], 2013, HYPERTENSION PREGNAN
[6]  
[Anonymous], REPROD HEALTH S1
[7]  
[Anonymous], J MATERN FETAL NEONA
[8]   Disparities and relative risk ratio of preterm birth in six Central and Eastern European centers [J].
Arora, Chander P. ;
Kacerovsky, Marian ;
Zinner, Balazs ;
Ertl, Tibor ;
Ceausu, Iuliana ;
Rusnak, Igor ;
Shurpyak, Serhiy ;
Sandhu, Meenu ;
Hobel, Calvin J. ;
Dumesic, Daniel A. ;
Vari, Sandor G. .
CROATIAN MEDICAL JOURNAL, 2015, 56 (02) :119-127
[9]   Maternal Preeclampsia and Neonatal Outcomes [J].
Backes, Carl H. ;
Markham, Kara ;
Moorehead, Pamela ;
Cordero, Leandro ;
Nankervis, Craig A. ;
Giannone, Peter J. .
JOURNAL OF PREGNANCY, 2011, 2011 :214365
[10]   Population-based risks of mortality and preterm morbidity by gestational age and birth weight [J].
Baer, R. J. ;
Rogers, E. E. ;
Partridge, J. C. ;
Anderson, J. G. ;
Morris, M. ;
Kuppermann, M. ;
Franck, L. S. ;
Rand, L. ;
Jelliffe-Pawlowski, L. L. .
JOURNAL OF PERINATOLOGY, 2016, 36 (11) :1008-1013