User profiles for Ashley I. Naimi
Ashley NaimiAssociate Professor, Department Epidemiology, Emory University Verified email at emory.edu Cited by 3290 |
Stacked generalization: an introduction to super learning
Stacked generalization is an ensemble method that allows researchers to combine several
different prediction algorithms into one. Since its introduction in the early 1990s, the method …
different prediction algorithms into one. Since its introduction in the early 1990s, the method …
Mediation misgivings: ambiguous clinical and public health interpretations of natural direct and indirect effects
AI Naimi, JS Kaufman… - International journal of …, 2014 - academic.oup.com
Recent methodological innovation is giving rise to an increasing number of applied papers
in medical and epidemiological journals in which natural direct and indirect effects are …
in medical and epidemiological journals in which natural direct and indirect effects are …
An introduction to g methods
Robins’ generalized methods (g methods) provide consistent estimates of contrasts (eg
differences, ratios) of potential outcomes under a less restrictive set of identification conditions …
differences, ratios) of potential outcomes under a less restrictive set of identification conditions …
Reflection on modern methods: demystifying robust standard errors for epidemiologists
All statistical estimates from data have uncertainty due to sampling variability. A standard
error is one measure of uncertainty of a sample estimate (such as the mean of a set of …
error is one measure of uncertainty of a sample estimate (such as the mean of a set of …
The parametric g-formula for time-to-event data: intuition and a worked example
Background: The parametric g-formula can be used to estimate the effect of a policy, intervention,
or treatment. Unlike standard regression approaches, the parametric g-formula can be …
or treatment. Unlike standard regression approaches, the parametric g-formula can be …
Estimating risk ratios and risk differences using regression
AI Naimi, BW Whitcomb - American journal of epidemiology, 2020 - academic.oup.com
Generalized linear models (GLMs) are often used with binary outcomes to estimate odds
ratios. Though not as widely appreciated, GLMs can also be used to quantify risk differences, …
ratios. Though not as widely appreciated, GLMs can also be used to quantify risk differences, …
Constructing inverse probability weights for continuous exposures: a comparison of methods
Inverse probability–weighted marginal structural models with binary exposures are common
in epidemiology. Constructing inverse probability weights for a continuous exposure can be …
in epidemiology. Constructing inverse probability weights for a continuous exposure can be …
Mediation analysis for health disparities research
Social epidemiologists often seek to determine the mechanisms that underlie health
disparities. This work is typically based on mediation procedures that may not be justified with …
disparities. This work is typically based on mediation procedures that may not be justified with …
Extreme heat and risk of early delivery among preterm and term pregnancies
Background: The relationship between ambient temperature and risk of delivery is poorly
understood. We examined the association between heat and risk of delivery among preterm …
understood. We examined the association between heat and risk of delivery among preterm …
Challenges in obtaining valid causal effect estimates with machine learning algorithms
Unlike parametric regression, machine learning (ML) methods do not generally require
precise knowledge of the true data-generating mechanisms. As such, numerous authors have …
precise knowledge of the true data-generating mechanisms. As such, numerous authors have …