Establishing causal relationships in observational studies is an important step in research and policy decision making. The association between an exposure and an outcome can be confounded by multiple factors, often making it hard to draw causal conclusions. The co-twin control design (CTCD) is a powerful approach that allows for the investigation of causal effects while controlling for genetic and shared environmental confounding factors. This article introduces the CTCD and offers an overview of analysis methods for binary and continuous outcome and exposure variables. Tools for data simulation are provided, along with practical guidance and accompanying scripts for implementing the CTCD in R, SPSS, and Stata. While the CTCD offers valuable insights into causal inference, it depends on several assumptions that are important when interpreting CTCD results. By presenting a broad overview of the CTCD, this article aims to equip researchers with actionable recommendations and a comprehensive understanding of the design’s strengths and limitations.

Bullying research has shown repeatedly that victims of bullying have an increased risk for later internalizing problems and bullies have an increased risk for later externalizing problems. Bullying involvement is often, either explicitly or implicitly, presented as part of a causal mechanism for maladjustment. However, genetic vulnerability may confound the reported associations. This study examined to what extent genetic vulnerability can account for the reported associations between bullying involvement (age 11-14) and later internalizing and externalizing problems (age 16), using data from the TRacking Adolescents' Individual Lives Survey (n = 1604). Because polygenic scores capture only a fraction of the total genetic effect, they were extrapolated to the size of single-nucleotide polymorphism and twin heritability estimates to examine genetic confounding while controlling for (hypothetical) polygenic scores that fully capture the genetic effect. Genetic vulnerability for internalizing and externalizing problems confounded, respectively, the association between bullying victimization and later internalizing problems, and the association between bullying perpetration and later externalizing problems. As such, this study showcases a method that can be broadly used to assess the magnitude of genetic confounding. Caution is, however, warranted in interpreting particularly the less straightforward extrapolations of polygenic scores to the size of twin heritability estimates.

A core part of political research is to identify how political preferences are shaped. The nature of these questions is such that robust causal identification is often difficult to achieve, and we are not seldom stuck with observational methods that we know have limited causal validity. The purpose of this paper is to measure the magnitude of bias stemming from both measurable and unmeasurable confounders across three broad domains of individual determinants of political preferences: socio-economic factors, moral values, and psychological constructs. We leverage a unique combination of rich Swedish registry data for a large sample of identical twins, with a comprehensive battery of 34 political preference measures, and build a meta-analytical model comparing our most conservative observational (naive) estimates with discordant twin estimates. This allows us to infer the amount of bias from unobserved genetic and shared environmental factors that remains in the naive models for our predictors, while avoiding precision issues common in family-based designs. The results are sobering: in most cases, substantial bias remains in naive models. A rough heuristic is that about half of the effect size even in conservative observational estimates is composed of confounding.

An impressive literature has revealed that variation in virtually every measurable phenotype is the result of a combination of genetic and environmental influences. Based on these findings, studies that fail to use genetically informed modeling strategies risk model misspecification and biased parameter estimates. Twin- and adoption-based research designs have frequently been used to overcome this limitation. Despite the many advantages of such approaches, many available datasets do not contain samples of twins, siblings or adoptees, making it impossible to utilize these modeling strategies. The current study proposes a measurement strategy for estimating the intergenerational transmission of antisocial behavior (ASB) within a nationally representative sample of singletons using an extended pedigree risk approach that relies on information from first- and second-degree relatives. An evaluation of this approach revealed a pattern of findings that directly aligned with studies examining ASB using more traditional twin- and adoption-based research designs. While the proposed pedigree risk approach is not capable of effectively isolating genetic and environmental influences, this overall alignment in results provides tentative evidence suggesting that the proposed pedigree risk measure effectively captures genetic influences. Future replication studies are necessary as this observation remains preliminary. Whenever possible, more traditional quantitative genetic methodologies should be favored, but the presented strategy remains a viable alternative for more limited samples.