A potential outcomes approach to defining and estimating gestational age-specific exposure effects during pregnancy

Many studies seek to evaluate the effects of potentially harmful pregnancy exposures during specific gestational periods. We consider an observational pregnancy cohort where pregnant individuals can initiate medication usage or become exposed to a drug at various times during their pregnancy. An important statistical challenge involves how to define and estimate exposure effects when pregnancy loss or delivery can occur over time. Without proper consideration, the results of standard analysis may be vulnerable to selection bias, immortal time-bias, and time-dependent confounding. In this study, we apply the “target trials” framework of Hernán and Robins in order to define effects based on the counterfactual approach often used in causal inference. This effect is defined relative to a hypothetical randomized trial of timed pregnancy exposures where delivery may precede and thus potentially interrupt exposure initiation. We describe specific implementations of inverse probability weighting, G-computation, and Targeted Maximum Likelihood Estimation to estimate the effects of interest. We demonstrate the performance of all estimators using simulated data and show that a standard implementation of inverse probability weighting is biased. We then apply our proposed methods to a pharmacoepidemiology study to evaluate the potentially time-dependent effect of exposure to inhaled corticosteroids on birthweight in pregnant people with mild asthma.

Comparative effectiveness of the BNT162b2 vs ChAdOx1 vaccine against Covid-19

Although pivotal trials with varying populations and study methods suggest higher efficacy for mRNA than adenoviral Covid-19 vaccines, no direct evidence is available. Here, we conducted a head-to-head comparison of BNT162b2 versus ChAdOx1 against Covid-19. We analysed 235,181 UK Biobank participants aged 50 years or older and vaccinated with one or two doses of BNT162b2 or ChAdOx1. People were followed from the vaccination date until 18/10/2021. Inverse probability weighting was used to minimise confounding and the Cox models to derive hazard ratio. We found that, compared with two doses of ChAdOx1, vaccination with BNT162b2 was associated with 30% lower risks of both SARS-CoV-2 infection and related hospitalisation during the period dominated by the delta variant. Also, this comparative effectiveness was consistent across several subgroups and persisted for at least six months, suggesting no differential waning between the two vaccines. Our findings can inform evidence-based Covid-19 vaccination campaigns and booster strategies.

The impact of COVID-19 on tourists’ length of stay and daily expenditures

This study evaluates the effect of the COVID-19 pandemic on tourists’ length of stay and daily expenditures at a destination. The paper compares detailed microdata for visitors to a Northern Spanish region in the summer periods of 2019 (pre-pandemic) and 2020 (after the pandemic outbreak). We estimate the pandemic-induced impacts on the length of stay and expenditures per person for several categories using regression adjustment, inverse probability weighting regression and propensity score matching. We find clear evidence of a drop in the length of stay of around 1.26 nights, representing a 23.8% decline. We also show that, although total expenditures per person and day have remained constant, there has been a change in the allocations for categories in the tourism budget.

G-computation and doubly robust standardisation for continuous-time data: A comparison with inverse probability weighting

In time-to-event settings, g-computation and doubly robust estimators are based on discrete-time data. However, many biological processes are evolving continuously over time. In this paper, we extend the g-computation and the doubly robust standardisation procedures to a continuous-time context. We compare their performance to the well-known inverse-probability-weighting estimator for the estimation of the hazard ratio and restricted mean survival times difference, using a simulation study. Under a correct model specification, all methods are unbiased, but g-computation and the doubly robust standardisation are more efficient than inverse-probability-weighting. We also analyse two real-world datasets to illustrate the practical implementation of these approaches. We have updated the R package RISCA to facilitate the use of these methods and their dissemination.

Using Inverse Probability Weighting to Address Post-Outcome Collider Bias

We consider the problem of bias arising from conditioning on a post-outcome collider. We illustrate this with reference to Elwert and Winship (2014) but we go beyond their study to investigate the extent to which inverse probability weighting might offer solutions. We use linear models to derive expressions for the bias arising in different kinds of post-outcome confounding, and we show the specific situations in which inverse probability weighting will allow us to obtain estimates that are consistent or, if not consistent, less biased than those obtained via ordinary least squares regression.

Probability weighting explains Independence Axiom violations of Expected Utility Theory in monkeys

Expected Utility Theory (EUT) provides axioms for maximizing utility in risky choice. The independence axiom (IA) is its most demanding axiom: preferences between two options should not change when altering both options equally by mixing them with a common gamble. We tested common consequence (CC) and common ratio (CR) violations of the IA in thousands of stochastic choice over several months using a large variety of binary option sets. Three monkeys showed few outright Preference Reversals (8%) but substantial graded Preference Changes (46%) between the initial preferred gamble and the corresponding altered gamble. Linear Discriminant Analysis (LDA) indicated that gamble probabilities predicted most Preference Changes in CC (72%) and CR (87%) tests. The Akaike Information Criterion indicated that probability weighting within Cumulative Prospect Theory (CPT) explained choices better than models using Expected Value (EV) or EUT. Fitting by utility and probability weighting functions of CPT resulted in nonlinear and non-parallel indifference curves (IC) in the Marschak-Machina triangle and suggested IA non-compliance of models using EV or EUT. Indeed, CPT models predicted Preference Changes better than EV and EUT models. Indifference points in out-of-sample tests were closer to CPT-estimated ICs than EV and EUT ICs. Finally, while the few outright Preference Reversals may reflect the long experience of our monkeys, their more graded Preference Changes corresponded to those reported for humans. In benefitting from the wide testing possibilities in monkeys, our stringent axiomatic tests contribute critical information about risky decision-making and serves as basis for investigating neuronal decision mechanisms.

Reliable population utility signal from diverse economic value coding in orbitofrontal neurons

Economic value encapsulates the subjective combination of reward magnitude and probability. We investigated the mechanism for subjective value computation in single neurons using an economic axiomatic approach. We found that single neurons in the macaque orbitofrontal cortex, known to be sensitive to reward magnitude and probability, encode the economic value functions (utility and probability weighting) in a heterogeneous manner, such that the activity of individual neurons did not match the animal's choices. However, the utility and probability weighting code from a population of these varied neurons reliably matched the animals' choices and risk attitudes. Thus, the neuronal population code for economic value amounted to a distributional representation of the formal economic functions. With a diverse single-unit economic value code converging into a reliable population-level utility code, this scheme suggests a brain mechanism for the flexible accommodation of multiple choice patterns and risk attitudes.

Sex Differences in Cardiovascular Outcomes of Older Adults After Myocardial Infarction

Background Evidence on the impact of sex on prognoses after myocardial infarction (MI) among older adults is limited. We evaluated sex differences in long‐term cardiovascular outcomes after MI in older adults. Methods and Results All patients with MI ≥70 years admitted to 20 Finnish hospitals during a 10‐year period and discharged alive were studied retrospectively using a combination of national registries (n=31 578, 51% men, mean age 79). The primary outcome was combined major adverse cardiovascular event within 10‐year follow‐up. Sex differences in baseline features were equalized using inverse probability weighting adjustment. Women were older, with different comorbidity profiles and rarer ST‐segment–elevation MI and revascularization, compared with men. Adenosine diphosphate inhibitors, anticoagulation, statins, and high‐dose statins were more frequently used by men, and renin‐angiotensin‐aldosterone inhibitors and beta blockers by women. After balancing these differences by inverse probability weighting, the cumulative 10‐year incidence of major adverse cardiovascular events was 67.7% in men, 62.0% in women (hazard ratio [HR], 1.17; CI, 1.13–1.21; P <0.0001). New MI (37.0% in men, 33.1% in women; HR, 1.16; P <0.0001), ischemic stroke (21.1% versus 19.5%; HR, 1.10; P =0.004), and cardiovascular death (56.0% versus 51.1%; HR, 1.18; P <0.0001) were more frequent in men during long‐term follow‐up after MI. Sex differences in major adverse cardiovascular events were similar in subgroups of revascularized and non‐revascularized patients, and in patients 70 to 79 and ≥80 years. Conclusions Older men had higher long‐term risk of major adverse cardiovascular events after MI, compared with older women with similar baseline features and evidence‐based medications. Our results highlight the importance of accounting for confounding factors when studying sex differences in cardiovascular outcomes.

Prospect Theory with Bounded Temporal Horizon for Modeling Prosumer Behavior in the Smart Grid

We study prosumer decision-making in the smart grid in which a prosumer must decide whether to make a sale of solar energy units generated at her home every day or hold (store) the energy units in anticipation of a future sale at a better price. Specifically, we enhance a Prospect Theory (PT)-based behavioral model by taking into account bounded temporal horizons (a time window specified in terms of the number of days) that prosumers implicitly impose on their decision-making in arriving at “hold” or “sell” decisions of energy units. The new behavioral model for prosumers assumes that in addition to the framing and probability weighting effects imposed by classical PT, humans make decisions that will affect their lives within a bounded temporal horizon regardless of how far into the future their units may be sold. Modeling the utility of the prosumer with parameters such as the offered price on a day, the available energy units on a day, and the probabilities of the forecast prices, we fit the PT-based proposed behavioral model with bounded temporal horizons to prosumer data collected over 10 weeks from 57 homeowners who generated surplus units of solar power and had the opportunity to sell those units to the local utility at the price set that day by the utility or hold the units for sale in the future. For most participants, a model with a bounded temporal horizon in the range of 1–6 days provided a much better fit to their responses than was found for the traditional EUT-based model, thus validating the need to model PT effects (framing and probability weighting) and bounded temporal horizons imposed in prosumer decision-making.