English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Observational studies often use linear regression to assess the effect ofambient air pollution on outcomes of interest, such as human health outcomes orcrop yields. Yet pollution datasets are typically noisy and include only asubset of potentially relevant pollutants, giving rise to both measurementerror bias (MEB) and omitted variable bias (OVB). While it is well understoodthat these biases exist, less is understood about whether these biases tend tobe positive or negative, even though it is sometimes falsely claimed thatmeasurement error simply biases regression coefficient estimates towards zero.In this paper, we show that more can be said about the direction of thesebiases under the realistic assumptions that the concentrations of differenttypes of air pollutants are positively correlated with each other and that eachtype of pollutant has a nonpositive association with the outcome variable. Inparticular, we demonstrate both theoretically and using simulations that underthese two assumptions, the OVB will typically be negative and that more oftenthan not the MEB for null pollutants or for pollutants that are perfectlymeasured will be negative. We also provide precise conditions, which areconsistent with the assumptions, under which we prove that the biases areguaranteed to be negative. While the discussion in this paper is motivated bystudies assessing the effect of air pollutants on crop yields, the findings arealso relevant to regression-based studies assessing the effect of airpollutants on human health outcomes.

Biases in estimates of air pollution impacts: the role of omitted variables and measurement errors