Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Modeling Variables With a Spike at Zero: Examples and Practical Recommendations.

Eva Lorenz¹, Carolin Jenkner², Willi Sauerbrei³

¹Medical University of Innsbruck, Department of Internal Medicine V, Anichstraße 35, 6020, Innsbruck, Austria.

American Journal of Epidemiology

|April 4, 2017

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Intersectional inequalities in self-rated health in Germany across sex/gender, migration, education and income: a cross-sectional study.

Journal of epidemiology and community health·2026

Same author

Ascertainment of Cancer Cases in the German National Cohort (NAKO): Methods and Initial Results.

Deutsches Arzteblatt international·2026

Same author

Inequalities and determinants of unmet need for SARS-CoV-2 testing in Ghana, Burkina Faso and Madagascar (2020 - 2021).

Communications medicine·2026

Same author

Individual and combined associations of physical activity and cognitive function with all-cause mortality in older men and women: a prospective analysis of the German National Cohort (NAKO).

BMC geriatrics·2026

Same author

Baseline Procalcitonin and C-Reactive Protein Levels in Asymptomatic Individuals From West Africa With and Without <i>P. falciparum</i> Parasitemia.

Open forum infectious diseases·2026

Same author

Sex-specific individual and joint associations of multiple environmental exposures with diabetes and obesity in the population-based German National Cohort (NAKO).

Environmental research·2026

Same journal

Correction to: Home dampness and molds and occurrence of respiratory tract infections in the first 27 years of life: the Espoo Cohort Study.

American journal of epidemiology·2026

Same journal

A SIMPLE AND POWERFUL TEST OF VACCINE WANING.

American journal of epidemiology·2026

Same journal

Association Between maternal body mass index, offspring growth and pubertal timing: results from a longitudinal birth cohort study.

American journal of epidemiology·2026

Same journal

Correction to: Developing a novel algorithm to identify incident and prevalent dementia in Medicare claims-the ARIC Study.

American journal of epidemiology·2026

Same journal

RE: advancing observational research on arts and health: theory-informed approaches using the RADIANCE framework.

American journal of epidemiology·2026

Same journal

Maternal Cesarean Section and Offspring ASD or ADHD Risk: A Nurses' Health Study II Analysis.

American journal of epidemiology·2026

See all related articles

This summary is machine-generated.

This study compares methods for analyzing variables with a zero spike in epidemiological research, offering practical recommendations for modeling exposure data. It evaluates different statistical approaches for continuous exposure variables with a proportion of zero values.

Area of Science:

Epidemiologic research
Biostatistics
Health research methodology

Background:

Many epidemiologic and clinical studies encounter variables with a 'spike at zero,' where a proportion of individuals have zero exposure (e.g., never smokers) and others have continuous exposure levels.
Standard statistical approaches like categorization or ignoring the zero spike can lead to information loss or biased results.
Existing methods for handling spike-at-zero variables include adding a binary indicator or using fractional polynomials to model the continuous portion.

Purpose of the Study:

To compare various statistical approaches for modeling variables with a spike at zero in epidemiologic studies.
To evaluate the strengths and limitations of different analytical procedures.
To provide practical recommendations for the optimal use of these methods in research.

Keywords:

case-control studies dose-response model fraction unexposed fractional polynomials regression modeling

Related Experiment Videos

Main Methods:

Comparative analysis of statistical modeling techniques for spike-at-zero variables.
Application of methods to data from three German case-control studies: MARIE (breast cancer), Rhein-Neckar Larynx Study, and a lung cancer study.
Evaluation of approaches including categorization, transformations, regression with binary indicators, and fractional polynomials.

Main Results:

Demonstration of the strengths and limitations of different modeling procedures when applied to real-world epidemiologic data.
Identification of specific scenarios where certain methods perform better than others.
Empirical evidence supporting the utility of advanced modeling techniques for complex exposure data.

Conclusions:

The choice of statistical method significantly impacts the analysis of variables with a spike at zero.
Fractional polynomials and regression with binary indicators offer robust alternatives to traditional methods.
Recommendations are provided to guide researchers in selecting the most appropriate analytical strategy for their specific data and research questions.