The DOI matches its Crossref record; 46 of the 47 references it cites were found in a registry or an index.
Thinking Clearly About Correlations and Causation: Graphical Causal Models for Observational Data
Open accessAbstract
Correlation does not imply causation; but often, observational data are the only option, even though the research question at hand involves causality. This article discusses causal inference based on observational data, introducing readers to graphical causal models that can provide a powerful tool for thinking more clearly about the interrelations between variables. Topics covered include the rationale behind the statistical control of third variables, common procedures for statistical control, and what can go wrong during their implementation. Certain types of third variables—colliders and mediators—should not be controlled for because that can actually move the estimate of an association away from the value of the causal effect of interest. More subtle variations of such harmful control include using unrepresentative samples, which can undermine the validity of causal conclusions, and statistically controlling for mediators. Drawing valid causal inferences on the basis of observational data is not a mechanistic procedure but rather always depends on assumptions that require domain knowledge and that can be more or less plausible. However, this caveat holds not only for research based on observational data, but for all empirical research endeavors.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Baron, R. M., & Kenny, D. A. (1986) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.51.6.1173 · Cited by 91,532 · cited 1×
“Both old and newer common approaches to estimating the remaining (direct) effect after accounting for a mediator (e.g., Baron & Kenny, 1986; Hayes, 2009) rely on statistical control of the mediating variable, but such approaches can introduce endogenous selection bias (Elwert & Winship, 2014).”
BackgroundMissing data: our view of the state of the art
Schafer, J. L., & Graham, J. W. (2002) · Psychological Methods · doi:10.1037/1082-989x.7.2.147 · Cited by 11,638 · cited 1×
“Schafer and Graham (2002) have provided an introduction to the management of missing data for psychologists.”
Background(1979) · Medical Entomology and Zoology · Cited by 11,252
Beyond Baron and Kenny: Statistical Mediation Analysis in the New Millennium
Hayes, A. F. (2009) · Communication Monographs · doi:10.1080/03637750903310360 · Cited by 9,757 · cited 1×
“Both old and newer common approaches to estimating the remaining (direct) effect after accounting for a mediator (e.g., Baron & Kenny, 1986; Hayes, 2009) rely on statistical control of the mediating variable, but such approaches can introduce endogenous selection bias (Elwert & Winship, 2014).”
BackgroundEstimating causal effects of treatments in randomized and nonrandomized studies
Rubin, D. B. (1974) · Journal of Educational Psychology · doi:10.1037/h0037350 · Cited by 9,436 · cited 1×
“A solid rule of thumb is that researchers should not control for such posttreatment variables (Rosenbaum, 1984; Rubin, 1974).”
BackgroundCausation, Prediction, and Search
Spirtes, P., Glymour, C., & Scheines, R. (2001) · doi:10.7551/mitpress/1754.001.0001 · Cited by 4,521
Causal diagrams for empirical research
PEARL, J. (1995) · Biometrika · doi:10.1093/biomet/82.4.669 · Cited by 2,355 · cited 1×
“They were developed primarily by the computer scientist Judea Pearl (e.g., Pearl, 1995; see Pearl, Glymour, & Jewell, 2016, for an introduction) and share many features with structural equation models (SEMs).1 DAGs offer an intuitive approach for thinking about causal structures.”
MethodWhy Propensity Scores Should Not Be Used for Matching
King, G., & Nielsen, R. (2019) · Political Analysis · doi:10.1017/pan.2019.11 · Cited by 1,706 · cited 1×
“The use of propensity scores for matching is controversial, and critics have indicated that other procedures might be preferable (King & Nielsen, 2016).”
BackgroundThe theoretical status of latent variables.
Borsboom, D., Mellenbergh, G. J., & van Heerden, J. (2003) · Psychological Review · doi:10.1037/0033-295x.110.2.203 · Cited by 1,566
Angrist, J. D., & Pischke, J.-S. (2010) · Journal of Economic Perspectives · doi:10.1257/jep.24.2.3 · Cited by 1,566
Research works printed but not linked: 2
- Mohan K., 2013, Advances in Neural Information Processing Systems 26 (NIPS 2013), 1277
- Robins J. M., 1999, Computation, Causation, & Discovery, 305
Cited by
Sorted by citations
Items 301–400 of 1,001
Holsbø, E., & Olsen, K. S. (2020) · Frontiers in Oncology · doi:10.3389/fonc.2020.575461 · Cited by 13
“One solution might be to map out the molecular two-way interactions and feedback loops as linear sequences of events in time (29), but this is beyond the scope of our work.”
BackgroundCollinearity isn't a disease that needs curingPreprint
Vanhove, J. (2020) · doi:10.31234/osf.io/mv2wx · Cited by 13
“Statistical models describe associations; imbuing them with a causal or even interventionist interpretation requires strong additional assumptions (for guidance, see Elwert, 2013; Rohrer, 2018; Shmueli, 2010).”
BackgroundDesigning digital health interventions with causal inference and multi-armed bandits: a review
Švihrová, R., Rossi, A. D., Marzorati, D., Tzovara, A., & Faraci, F. D. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1435917 · Cited by 17
“However, incorrect direction of edge in the output can introduce incorrect assumptions for the subsequent identi fi cation and inference (183).”
Multiple Marginalized Identities, Minority Stress, and Mental Health
Rubin‐McGregor, J., Heitt, J., & Hunger, J. M. (2025) · Social and Personality Psychology Compass · doi:10.1111/spc3.70077 · Cited by 16
Trust is good, control is better: The role of trust and personal control in response to threat
Pauer, S., Rutjens, B. T., & van Harreveld, F. (2024) · Journal of Applied Social Psychology · doi:10.1111/jasp.13058 · Cited by 15
Through the lens of causal inference: Decisions and pitfalls of covariate selection
Chen, G., Cai, Z., & Taylor, P. A. (2024) · Aperture Neuro · doi:10.52294/001c.124817 · Cited by 12
The evolution of online news headlines
Nickl, P. L., Moussaïd, M., & Lorenz-Spreen, P. (2025) · Humanities and Social Sciences Communications · doi:10.1057/s41599-025-04514-7 · Cited by 12
“With these assumptions about the underlying process, we concluded that length would be a bad control, resulting in an uninterpretable and misleading regression (Achen 2005; Rohrer 2018); see Cinelli et al. (2022) for an introduction to Directed Acyclic Graphs.”
Towards a personalized happiness approach to capturing change in satisfaction
Beck, E. D., Cheung, F., Thapa, S., & Jackson, J. J. (2025) · Nature Human Behaviour · doi:10.1038/s41562-025-02171-z · Cited by 25
Pro-environmental behavior and life satisfaction: How strong is our evidence?
Binder, M., Blankenberg, A., & Nickel, J. (2025) · Ecological Economics · doi:10.1016/j.ecolecon.2025.108684 · Cited by 13
Twenge, J. M., Joiner, T. E., Rogers, M. L., & Martin, G. N. (2020) · Clinical Psychological Science · doi:10.1177/2167702619898179 · Cited by 13
“However, Orben and Przybylski included TV use in this calculation, which is not the same as technology use and has a weaker association with well-being than digital media use; in addition, they included control variables that may be mediators—an approach that explains away mechanisms of interest and is thus strongly d…”
BackgroundKavish, N., Helton, J. J., Vaughn, M. G., & Boutwell, B. B. (2020) · Intelligence · doi:10.1016/j.intell.2020.101448 · Cited by 15
Econometrics and the Growth of Firms: Perspectives from Evolutionary Economics
Coad, A. (2021) · Strategy Science · doi:10.1287/stsc.2021.0132 · Cited by 12
O’Leary, K. C., Gleasure, R., O’Reilly, P., & Feller, J. (2021) · Technovation · doi:10.1016/j.technovation.2021.102369 · Cited by 12
Autonomy Is An Acquired Taste: Exploring Developer Preferences for GitHub Bots
Ghorbani, A., Cassee, N., Robinson, D. J. S., Alami, A., Ernst, N., Serebrenik, A., & Wąsowski, A. (2023) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse48619.2023.00123 · Cited by 14
“Causal Model and Associated Statistical Models: We created a causal graph [36] to model the relationships between themes from our interviews (Section III-B).”
MethodCurrie, C. L., Motz, T., & Copeland, J. L. (2020) · Journal of Urban Health · doi:10.1007/s11524-020-00446-6 · Cited by 12
“Controlling for such intermediate variables introduces bias by decomposing the total effect of x on y into its parts [32].”
BackgroundHow cultural evolution can inform the science of science communication—and vice versa
Bendixen, T. (2020) · Humanities and Social Sciences Communications · doi:10.1057/s41599-020-00634-4 · Cited by 14
“However, this constitutes a classical case of the “Table 2 Fallacy” (Westreich & Greenland, 2013), and may render the results unreliable by introducing various biases, especially if the goal is to establish causal relationships (e.g., Achen, 2005; Lübke et al., 2020; Rohrer, 2018).”
BackgroundUrbatsch, R., & Wang, Y. (2021) · Energy Research & Social Science · doi:10.1016/j.erss.2021.102283 · Cited by 10
Pitfalls of self‐reported measures of self‐control: Surprising insights from extreme debtors
Jia, L., Yuen, W. L., Ong, Q., & Theseira, W. E. (2022) · Journal of Personality · doi:10.1111/jopy.12733 · Cited by 14
Giudice, M. D. (2021) · doi:10.31234/osf.io/4vq8f · Cited by 12
“…approximates the data-generating process will in general be the most successful at predicting real-world outcomes […] a biased, psychologically implausible model can often systemat ically outperform a mechanistically more accurate, but also more complex, model” (Yarkoni & Westfall, 2017, p. 1100).”
BackgroundResultInfluentialBest Practices in Supervised Machine Learning: A Tutorial for PsychologistsPreprint
Pargent, F., Schoedel, R., & Stachl, C. (2022) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/89snd · Cited by 13
Overcoming the Black Box Challenge: Building Trust in Artificial Intelligence Algorithms in Oncology
Alum, E. U., Egwu, C. K., Manjula, V. S., Ekpang, P. O., Ekpang, J. E., Echegu, D. A., Alum, B. N., & Uti, D. E. (2026) · Technology in Cancer Research & Treatment · doi:10.1177/15330338261434649 · Cited by 12
“51 There are various elements that cause the black-box phenomenon in oncology AI.”
Kezios, K. (2021) · Epidemiologic Reviews · doi:10.1093/epirev/mxab008 · Cited by 12
Reciprocal effects between reading comprehension and emotional cognitive ability
Wenren, S., Ding, W., Wang, Z., Xia, Y. Y., Xie, R., & Li, W. (2023) · Learning and Individual Differences · doi:10.1016/j.lindif.2023.102398 · Cited by 20
Giudice, M. D. (2024) · Methodology · doi:10.5964/meth.11235 · Cited by 31
Lyddy, C. J., Good, D. J., Yuan, S., Michel, E. J., Ahlvik, C. A., & Reb, J. M. (2025) · Journal of Business Research · doi:10.1016/j.jbusres.2025.115307 · Cited by 16
Hormonal Contraception and Sexuality: Causal Effects, Unobserved Selection, or Reverse Causality?
Botzet, L. J., Gerlach, T. M., Driebe, J. C., Penke, L., & Arslan, R. C. (2021) · Collabra Psychology · doi:10.1525/collabra.29039 · Cited by 11
Beach, B., Willis, P. B., Powell, J., Vickery, A., Smith, R., & Cameron, A. (2022) · Innovation in Aging · doi:10.1093/geroni/igac061 · Cited by 13
“The use of PSM for causal inference in observational studies is not without controversy (cf., King & Nielsen, 2019), though it remains popular in the social sciences (Rohrer, 2018).”
BackgroundCui, Y., Yang, T., Li, H., Wang, H., Jin, S., Liu, N., Liu, X., Liu, H., & Zhang, Y. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2022.1073409 · Cited by 12
“In future studies, longitudinal design can be carried out for research, or a direct acyclic graph (DAG) can be adopted to explore the potential causal relationship between family function and self-management, as long as the collected data are consistent with the hypothesis put forward by the DAG (57, 58).”
ResultMartin, M., Steele, B., Spreckelsen, T. F., Lachman, J. M., Gardner, F. E. M., & Shenderovich, Y. (2023) · Prevention Science · doi:10.1007/s11121-023-01515-3 · Cited by 14
“…of controls, such as through directed acyclic graphs (DAGs) (Pearl et al., 2016), research in the field may be at risk of including unnecessary controls and overcontrol bias (incorporating inappropriate variables leading to spurious results or underpowered models) (Achen, 2005; Rohrer, 2018).”
BackgroundTaking the problem of colliders seriously in the study of crime: A research note
Novak, A. S., Boutwell, B. B., & Smith, T. B. (2023) · Journal of Experimental Criminology · doi:10.1007/s11292-023-09565-x · Cited by 14
“Recent attention notwithstanding, discussion of collider bias is somewhat of a rarity in the social and behavioral sciences (Gratz, 2019; Rohrer, 2018), particularly among criminologists.”
InfluentialResearch on the Application of Fuzzy Bayesian Network in Risk Assessment of Catenary Construction
Chen, Y., Li, X., Wang, J., Liu, M., Cai, C., & Shi, Y. (2023) · Mathematics · doi:10.3390/math11071719 · Cited by 12
Adamkovic, M. (2020) · Frontiers in Psychology · doi:10.3389/fpsyg.2020.00171 · Cited by 10
“(5) Another potential pitfall of the model is the issue of modeling causality from cross-sectional data in behavioral sciences (see, for example, Pearl, 2009; Rohrer, 2018).”
BackgroundDonohue, B. C., Gavrilova, E., Danlag, A., Perry, J. E., Kuhn, C., Allen, D. N., & Benning, S. D. (2020) · Psychology in the Schools · doi:10.1002/pits.22458 · Cited by 16
“To avoid distorting relationships among variables through selection bias (or conditioning on a collider; Rohrer, 2018), the entire sample was used in each analysis (subjects were pooled across experimental phases).”
MethodPrediction and Explanation in a Postmodern World
Krueger, J. I. (2020) · Frontiers in Psychology · doi:10.3389/fpsyg.2020.597706 · Cited by 9
Causal Perception in Question-Answering Systems
Law, P.-M., Lo, L. Y., Endert, A., Stasko, J., & Qu, H. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445444 · Cited by 11
“graph [55, 66], a technique often employed in statistics literature for visualizing complex causal relationships.”
BackgroundMethodDo Behavioral Observations Make People Catch the Goal? A Meta-Analysis on Goal Contagion
Brohmer, H., Corcoran, K., van Aert, R. C. M., & Eckerstorfer, L. V. (2021) · International Review of Social Psychology · doi:10.5334/irsp.428 · Cited by 15
Evolutionary Personality Psychology
Lewis, D. M. G., Al-Shawaf, L., & Buss, D. M. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.022 · Cited by 11
Bertoldo, G., Callegher, C. Z., & Altoè, G. (2022) · Meta-Psychology · doi:10.15626/mp.2020.2573 · Cited by 14
Steele, J., Fisher, J. P., & Crawford, D. A. (2020) · Journal of Trainology · doi:10.17338/trainology.9.1_20 · Cited by 11
Richardson, T. G., Smith, G. D., & Munafo, M. R. (2019) · Psychological Science · doi:10.1177/0956797618774532 · Cited by 11
Tobi, E. W., van Zwet, E. W., Lumey, L. H., & Heijmans, B. T. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/362392 · Cited by 11
The use, misuse and opportunities for structural equation modelling ( SEM ) in wildlife ecology
Mendes, C. P., & Luskin, M. S. (2025) · Journal of Applied Ecology · doi:10.1111/1365-2664.70189 · Cited by 10
Sheely, A. (2022) · Social Policy and Society · doi:10.1017/s1474746421000877 · Cited by 9
“By including health in the model, it would be possible to misleadingly control away the association between low quality work and food insecurity (Rohrer, 2018).”
BackgroundAlmansoof, H. S., Nuhmani, S., & Muaidi, Q. I. (2023) · PeerJ · doi:10.7717/peerj.14877 · Cited by 10
“Therefore, no causal inferences can be concluded (Rohrer, 2018).”
BackgroundRegistered reports in software engineering
Ernst, N., & Baldassarre, M. T. (2023) · Empirical Software Engineering · doi:10.1007/s10664-022-10277-5 · Cited by 10
“…on the lack of statistical maturity in the literature (de Oliveira Neto et al, 2019), for example, not tracking effect sizes (Kitchenham et al, 2019) or not referencing existing theories (Han-nay et al, 2007), for example, by creating causal models that outline constructs and context (Rohrer, 2018).”
BackgroundHeart rate variability and psychological health: The key role of trait emotional awareness
Quirin, M., Malekzad, F., Jais, M., Kehr, H. M., & Ennis, M. (2024) · Acta Psychologica · doi:10.1016/j.actpsy.2024.104252 · Cited by 10
Goh, A. Y. H., Hartanto, A., Kasturiratna, K. T. A. S., & Majeed, N. M. (2025) · Social Media + Society · doi:10.1177/20563051251313855 · Cited by 14
“Although the current study employs a daily diary method, which increases the ecological validity of our study, the correlational nature of the study may limit causal inferences (Rohrer, 2018).”
The Development of Turn‐Taking Skills in Typical Development and Autism
Fusaroli, R., Cox, C. M. M., Weed, E., Szabó, B. I., FEIN, D. A., & Naigles, L. (2025) · Cognitive Science · doi:10.1111/cogs.70082 · Cited by 10
A causal framework for the drivers of animal social network structure
Kawam, B., Ostner, J., McElreath, R. L., Schülke, O., & Redhead, D. (2025) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013370 · Cited by 12
“Arguing otherwise can be perceived as endorsing the statement that “correlation implies causation” (Pearl & Mackenzie, 2018; Rohrer, 2018, 2023).”
DAG With Omitted Objects Displayed (DAGWOOD): a framework for revealing causal assumptions in DAGs
Haber, N., Wood, M. E., Wieten, S. E., & Breskin, A. (2022) · Annals of Epidemiology · doi:10.1016/j.annepidem.2022.01.001 · Cited by 10
“Violations of these key hidden decision assumptions can lead to substantial issues in effect estimates, particularly where observational settings are the only practical option (8).”
BackgroundRüger, H., Stawarz, N., Skora, T., & Wiernik, B. M. (2021) · Journal of Environmental Psychology · doi:10.1016/j.jenvp.2021.101667 · Cited by 11
Krämer, M. D., van Scheppingen, M. A., Chopik, W. J., & Richter, D. (2022) · European Journal of Personality · doi:10.1177/08902070221118443 · Cited by 10
“Second, recommendations from a structural causal modeling perspective (Elwert & Winship, 2014; Rohrer, 2018) are more cautious, aiming to avoid pitfalls such as conditioning on a pre-treatment collider (collider bias) or a mediator (overcontrol bias).”
Addictions treatment mechanisms of change science and implementation science: A critical review
Magill, M., Maisto, S. A., Borsari, B. E., Glass, J. E., Hallgren, K. A., Houck, J. M., Kiluk, B. D., & Kuerbis, A. (2023) · Alcoholism Clinical and Experimental Research · doi:10.1111/acer.15053 · Cited by 11
“Probably the most common way is via subjective evaluation, and Kazdin and Nock’s (2003) seven recommendations assume this approach (also see, e.g., Hammerton & Munafò, 2021; Rohrer, 2018).”
BackgroundPlanning to revisit: Neural activity in refixation precursors
Nikolaev, A. R., Ehinger, B., Meghanathan, R. N., & van Leeuwen, C. (2023) · Journal of Vision · doi:10.1167/jov.23.7.2 · Cited by 10
Fernández-García, O., Gil-Llario, M., & Ballester-Arnal, R. (2023) · Children and youth services review · doi:10.1016/j.childyouth.2023.107091 · Cited by 10
Exploring the Use of the Picture Exchange Communication System (PECS) in Special Education Settings
May, R. J., Salman, H., O’Neill, S. J., Denne, L. D., Grindle, C. F., Cross, R., Tyler, E., Meek, I., & Games, C. (2024) · Journal of Autism and Developmental Disorders · doi:10.1007/s10803-023-06194-1 · Cited by 11
“Importantly, the structure of the DAG implies different statistical analyses depending on the causal estimate (the “estimand”) of interest (Rohrer, 2018).”
Ballou, N., Sewall, C. J. R., Ratcliffe, J., Zendle, D. I., Tokarchuk, L. N., & Deterding, S. (2024) · Technology Mind and Behavior · doi:10.1037/tmb0000124 · Cited by 18
“We include age and gender as covariates, given evidence that they are exogenously related to both playtime (Padilla-Walker et al., 2010; Ream et al., 2013) and well-being (Girgus & Yang, 2015) and are therefore potential confounds (Rohrer, 2018).”
Jin, M., Onie, S., Curby, K. M., & Most, S. B. (2018) · Visual Cognition · doi:10.1080/13506285.2018.1553223 · Cited by 10
“Note that we also conducted these 2 × 2 × 2 analyses without including covariates, following recommendations elsewhere in the literature (Rohrer, 2018; Simmons, Nelson, & Simonsohn, 2011), and effect sizes uniformly increased.”
MethodMoè, A., & Putwain, D. W. (2020) · Educational Psychology · doi:10.1080/01443410.2020.1730767 · Cited by 10
“Sixth, since threat and challenge appraisal measures were taken after message delivery, having included them as covariates could have underestimated the effects as pointed out by Rohrer (2018).”
BackgroundWhy is personality tied to sleep quality? A biometric analysis of twins
Križan, Z., Hisler, G. C., Krueger, R. F., & McGue, M. K. (2020) · Journal of Research in Personality · doi:10.1016/j.jrp.2020.104048 · Cited by 10
Development of Personality across the Life Span
Atherton, O. E., Donnellan, M. B., & Robins, R. W. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.017 · Cited by 15
Null-hacking, a lurking problemPreprint
Protzko, J. (2018) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/9y3mp · Cited by 13
Snodgrass, J. G., Dengah, H. J. F., Sagstetter, S. I., & Zhao, K. X. (2024) · PLoS ONE · doi:10.1371/journal.pone.0302857 · Cited by 12
A Credibility Revolution for Relationship Science: Where Can We Step Up Our Game?
Joel, S., Eastwick, P. W., & Khera, D. S. (2025) · Social and Personality Psychology Compass · doi:10.1111/spc3.70042 · Cited by 10
Theorising in HCI using Causal Models
Velloso, E., & Hornbæk, K. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713789 · Cited by 11
“Our goal is to present an approach that has been gaining traction outside the field (e.g. epidemiology [68], nutrition [72], psychology [58]) but is still under-utilised in HCI, even though it fits its ethos.”
Parenthood in Europe: Not More Life Satisfaction, but More Meaning in Life
Hudde, A., & Jacob, M. (2025) · Journal of Marriage and the Family · doi:10.1111/jomf.13116 · Cited by 10
Huang, D., Li, J., He, F., Song, Z., & Jiao, C. (2025) · Habitat International · doi:10.1016/j.habitatint.2025.103624 · Cited by 9
Currie, C. L., Higa, E. K., & Swanepoel, L.-M. (2021) · Adversity and Resilience Science · doi:10.1007/s42844-021-00035-9 · Cited by 8
“Controlling for such intermediate variables introduces bias by decomposing the total effect of x on y into its parts (Rohrer, 2018; Achen, 2005).”
BackgroundSundgot‐Borgen, J., Trangsrud, L. K. J., Otterbring, T., & Bratland‐Sanda, S. (2022) · Journal of Eating Disorders · doi:10.1186/s40337-022-00705-8 · Cited by 11
“Moreover, we cannot rule out the potential presence of colliders in our analyses, and our cross-sectional design does not allow us to draw causality conclusions with certainty; but see [62].”
BackgroundLui, F., Finik, J. M., Wu, M., Leng, J. C. F., & Gany, F. M. (2023) · Journal of Community Health · doi:10.1007/s10900-023-01246-0 · Cited by 9
“Mediators are not included as covariates, since controlling for a variable in the causal pathway removes part of the causal effect [ 36, 37].”
Lee, B. E. C., Ling, M., Boyd, L., Olsson, C. A., & Sheen, J. A. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1200839 · Cited by 9
“Once the theoretical framework was developed, Daggity applied the Pearl’s single and back door criterion (Pearl, 2009; Rohrer, 2018) to find the MSAS for each predictor’s model.”
BackgroundMethodInfluentialEmbedding Research on Emotion Duration in a Network Model
Lange, J. (2023) · Affective Science · doi:10.1007/s42761-023-00203-3 · Cited by 9
Hakimi, S., Martin, L. J., & Rosenberg, M. W. (2024) · Journal of Activity Sedentary and Sleep Behaviors · doi:10.1186/s44167-024-00047-7 · Cited by 12
“Issues with repre-sentativeness are important to note because they can lead to collider bias whereby two variables (e.g., exposure and outcome) cause a third variable (e.g., participation in the study), with the effect of the third variable distorting the causal association being measured [74].”
BackgroundMisstatements, misperceptions, and mistakes in controlling for covariates in observational research
Yu, X. D., Zoh, R. S., Fluharty, D. A., Mestre, L. M., Valdez, D., Tekwe, C. D., Vorland, C. J., Jamshidi‐Naeini, Y., Chiou, S. H., Lartey, S. T., et al. (2024) · eLife · doi:10.7554/elife.82268 · Cited by 10
““A collider for a certain pair of variables is any variable that is causally influenced by both of them” ( Rohrer, 2018 ).”
BackgroundThe effect of physical activities and self-esteem on school performance: A probabilistic analysis
Cerda, A. A., García, L. Y., & Cerda, A. J. (2021) · Cogent Education · doi:10.1080/2331186x.2021.1936370 · Cited by 14
Tumour genotypes account for survival differences in right‐ and left‐sided colon cancers
Ward, T. M., Cauley, C. E., Stafford, C. E., Goldstone, R. N., Bordeianou, L., Kunitake, H., Berger, D. L., & Ricciardi, R. (2022) · Colorectal Disease · doi:10.1111/codi.16060 · Cited by 9
“Following the structure of the DAG, a researcher can minimize spurious associations in a statistical model by including the variables in the model necessary to prevent confounding associations, while not including extra variables, which could lead to introduction of colliders [23].”
MethodThe only thing that can stop bad causal inference is good causal inference
Rohrer, J. M., Schmukle, S. C., & McElreath, R. L. (2022) · Behavioral and Brain Sciences · doi:10.1017/s0140525x21000789 · Cited by 9
Self-citationKokou‐Kpolou, C. K., Park, S., Bet, Q., Iorfa, S. K., Chinweuba, D. C., & Chukwuorji, J. C. (2022) · Current Psychology · doi:10.1007/s12144-022-04192-7 · Cited by 11
“The DAG is a Bayesian network method that models a network in which edges are directed and noncircular (Rohrer, 2018).”
MethodCohen, N. P., Chodorow, M. S., & Byosiere, S. (2020) · PLoS ONE · doi:10.1371/journal.pone.0238176 · Cited by 11
Lawson, M. A., & Kakkar, H. (2020) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/ves5m · Cited by 11
A universe of uncertainty hiding in plain sight
Engzell, P. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2218530120 · Cited by 9
Smartphones undermine social connectedness more in men than women: A mini mega-analysis.
Leitao, M., Proulx, J. D. E., & Kushlev, K. (2024) · Technology Mind and Behavior · doi:10.1037/tmb0000125 · Cited by 8
Antecedents and consequences of smartphone self-extension.
Ross, M. Q., & Kushlev, K. (2024) · Psychology of Popular Media · doi:10.1037/ppm0000540 · Cited by 8
Wiehn, J., Kurth, T., Ravens‐Sieberer, U., Prugger, C., Piccininni, M., & Reiß, F. (2024) · Frontiers in Pediatrics · doi:10.3389/fped.2024.1252964 · Cited by 8
The Basic Needs in Games Model of Video Game Play and Mental Health
Ballou, N., & Deterding, S. (2024) · Interacting with Computers · doi:10.1093/iwc/iwae042 · Cited by 16
Women’s Humility and Men’s Lack of Hubris: Gender Biases in Self-Estimated Spatial Intelligence
Hofer, G., Hünninghaus, M., Platzer, J., Grinschgl, S., & Neubauer, A. C. (2025) · Sex Roles · doi:10.1007/s11199-025-01572-8 · Cited by 14
“Such a study will likely benefit from considering third variables like age, education, study or career field based on careful consideration of potential causal pathways (see e.g., Rohrer, 2018) to improve its inferences.”
Li, J., Kaltiainen, J., & Hakanen, J. (2025) · Journal of Business and Psychology · doi:10.1007/s10869-025-10037-4 · Cited by 9
“Failing to control for such variables may increase the risk of spurious associations between the hypothesized variables (Rohrer, 2018).”
Yang, L., Gao, C., Qin, R., Wu, Q., Sun, H., & Zhang, T. (2025) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2025.138831 · Cited by 8
Mechanisms of cultural diversity in urban populations
Lee, H., Jacoby, N., Hennequin, R., & Moussallam, M. (2025) · Nature Communications · doi:10.1038/s41467-025-60538-2 · Cited by 13
“DAG provides a clear and ef fi cient method to identify, present, and hypothesise the causal relationships between variables 58,59 .”
Statistical modelling in archaeology: some recent trends and future perspectives
Crema, E. R. (2025) · Journal of Archaeological Science · doi:10.1016/j.jas.2025.106295 · Cited by 11
Approach–Avoidance Theories of Personality
Corr, P. J., & Krupıć, D. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.025 · Cited by 12
Bulling, L. J., Hilpert, P., Bertschi, I. C., Ivic, A., & Bodenmann, G. (2023) · International Journal of Applied Positive Psychology · doi:10.1007/s41042-023-00087-5 · Cited by 8
“…on observational data (i.e., correlation is not causation), yet new publications (Rohrer, 2018; Rohrer et al., 2021 ) suggest that this hinders progress in psychology and it would be much better to make implicit causal assumptions explicit (Grosz et al., 2020; Rohrer, 2018; Rohrer et al., 2021).”
BackgroundInfluentialInzlicht, M., Sparrow-Mungal, T. B., & Depow, G. J. (2024) · Social Psychological and Personality Science · doi:10.1177/19485506241245744 · Cited by 12
“We caution, however, that selection effects could introduce a collider bias (Rohrer, 2018) that prevent these and other results from generalizing to broader populations.”
ResultJoint Effects in Cross-Lagged Panel Research Using Structural Nested Mean Models
Mulder, J. D., Usami, S., & Hamaker, E. L. (2024) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2024.2355579 · Cited by 11
“…equation modeling software packages can handle various missing data patterns through the use of full information maximum 3 We do not provide an introduction to these graphical rules here, but the interested reader is referred to Rohrer (2018) and Pearl (2009). likelihood (FIML; Arbuckle, 1996).”
Bertin, P., Ionescu, O., Green, R., Abts, K., Rogenhofer, J. M., Delouvée, S., Yzerbyt, V. Y., & Klein, O. (2024) · European Journal of Social Psychology · doi:10.1002/ejsp.3093 · Cited by 8
Rieg, R., & Ulrich, P. (2024) · Business Performance Review · doi:10.22495/bprv2i2p3 · Cited by 9
“This so-called identification strategy is supported by graphical means, the directed acyclic graph (DAG), and a process to select the relations in the DAG that allow an identification of causal effects which is the Backdoor criterion (Pearl et al., 2016, p. 61; Rohrer, 2018).”
Breakthrough Knowledge Synthesis in the Age of Google
Brown, R. B. (2020) · Philosophies · doi:10.3390/philosophies5010004 · Cited by 10
“A directed acyclic graph (DAG) may be used to visually represent direct causal pathways between variables [73].”
MethodWu, T. L., Ting, T.-T., Chen, C., Su, L., & Chen, W. J. (2020) · BMC Public Health · doi:10.1186/s12889-020-09777-0 · Cited by 7
Automatability of Work and Preferences for Redistribution*
van Hoorn, A. (2021) · Oxford Bulletin of Economics and Statistics · doi:10.1111/obes.12460 · Cited by 10
“In general, there is a downside to including realized outcomes as controls because such variables can be and endogenous and thus potentially ‘ bad controls ’ (Angrist and Pischke, 2008:64 – 68; Rohrer, 2018).”
BackgroundPrecursor types predict the stability of neuronal branches
Fuchs, J., & Eickholt, B. J. (2021) · Journal of Cell Science · doi:10.1242/jcs.258983 · Cited by 8
Metadata
- Authors
- Rohrer, J. M.
- Affiliations
- German Institute for Economic Research (DE)
- Corresponding author
- Rohrer, Julia M.
- ORCID
- Rohrer, Julia M.
- Venue
- Advances in Methods and Practices in Psychological Science
- Publisher
- SAGE Publications
- Published
- 2018-01-29
- Volume
- 1
- Issue
- 1
- Pages
- 27-42
- ISSN
- 2515-2459 (ISSN-L)
- 2515-2467
- OpenAlex
- W2776946813
- Cited by
- 1,002
- References
- 47
- Citations by year
- 2026: 124 · 2025: 145 · 2024: 150 · 2023: 147 · 2022: 122 · 2021: 132 · 2020: 137 · 2019: 31 · 2018: 14
- FWCI
- 65.35
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Advances in Methods and Practices in Psychological Science (publishedVersion)
- MPG.PuRe (Max Planck Society) (submittedVersion)
- OSF Preprints (OSF Preprints) (submittedVersion, cc-by)
- OSF Preprints (OSF Preprints) (submittedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Philosophy of Biology and Scientific Explanation
- Keywords
- causal inference, observational data, causal graphical models, confounding, third variable, particle colliders, mediation, statistical control, causal assumptions, correlation versus causation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
