Total, Direct, and Indirect Effects in Logit and Probit Models
The DOI matches its Crossref record; 47 of the 48 references it cites were found in a registry or an index.
Abstract
This article presents a method for estimating and interpreting total, direct, and indirect effects in logit or probit models. The method extends the decomposition properties of linear models to these models; it closes the much-discussed gap between results based on the “difference in coefficients” method and the “product of coefficients” method in mediation analysis involving nonlinear probability models models; it reports effects measured on both the logit or probit scale and the probability scale; and it identifies causal mediation effects under the sequential ignorability assumption. We also show that while our method is computationally simpler than other methods, it always performs as well as, or better than, these methods. Further derivations suggest a hitherto unrecognized issue in identifying heterogeneous mediation effects in nonlinear probability models. We conclude the article with an application of our method to data from the National Educational Longitudinal Study of 1988.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The KHB test was developed for nonlinear dependent variables(Breen et al., 2013), but in STATA it can be applied to linear ones as well, in which case it is the same as the Sobel test.”
From Rape or Homicide: Which Is Worse? (2024) · cites this paper as Breen et al., 2013
In the citing paper
“To avoid the identification anomalies and non-linear scale distortions of logistic mediation, the second stage utilizes a linear probability specification, which permits an exact additive decomposition of conditional indirect effects (Breen et al., 2013) and formal evaluation of the Index of Moderated Mediation (a 3 × b 1 ; H3).”
From Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer (2026) · cites this paper as Breen et al., 2013
Citations
Cites
(1990) · Choice Reviews Online · doi:10.5860/choice.27-3338 · Cited by 35,305
(2001) · RePEc: Research Papers in Economics · Cited by 27,577
Estimating 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×
“While most treatments of causal mediation analysis use the potential outcomes framework of Rubin (1974, 1978), we refrain from doing this here and rather use the equivalent expression in terms of conditional independence between covariates and unobservables.”
MethodKupper, L. L., Hosmer, D. W., & Lemeshow, S. (1990) · Journal of the American Statistical Association · doi:10.2307/2290035 · Cited by 7,599
Regression Models for Categorical and Limited Dependent Variables.
MTW, & Long, J. S. (1997) · Journal of the American Statistical Association · doi:10.2307/2965458 · Cited by 6,898
A general approach to causal mediation analysis.
Imai, K., Keele, L., & Tingley, D. (2010) · Psychological Methods · doi:10.1037/a0020761 · Cited by 4,143 · cited 1×
“Using Monte Carlo simulations, Karlson et al. (2012) compared the method we propose with other methods for comparing coefficients across samesample nested logit or probit models.”
MethodA statistical model for the analysis of ordinal level dependent variables
McKelvey, R. D., & Zavoina, W. (1975) · The Journal of Mathematical Sociology · doi:10.1080/0022250x.1975.9989847 · Cited by 2,599
Bayesian inference for causal effects: The role of randomization
Rubin, D. B. (1978) · The Annals of Statistics · doi:10.1214/aos/1176344064 · Cited by 2,503
Statistical Methods for Comparing Regression Coefficients Between Models
Clogg, C. C., Petkova, E., & Haritou, A. (1995) · American Journal of Sociology · doi:10.1086/230638 · Cited by 2,072
The Analysis of Cross-Classified Categorical Data
Drane, J. W. (1979) · Technometrics · doi:10.1080/00401706.1979.10489789 · Cited by 1,941
Research works printed but not linked: 3
- Amemiya Takeshi, 1975, Annals of Economic and Social Measurement, 4, 363
- Blalock Hubert M., 1979, Social Statistics
- Pearl Judea, 2001, Proceedings of the Seventeenth Conference on Uncertainty and Artificial Intelligence, 411
Cited by
Interpreting and Understanding Logits, Probits, and Other Nonlinear Probability Models
Breen, R., Karlson, K. B., & Holm, A. (2018) · Annual Review of Sociology · doi:10.1146/annurev-soc-073117-041429 · Cited by 468
Self-citationPergelova, A., Manolova, T., Simeonova-Ganeva, R., & Yordanova, D. (2019) · Journal of Small Business Management · doi:10.1111/jsbm.12494 · Cited by 288
“We also decomposed the effect of the three digital capability measures on internationalization into total, direct, and indirect effects (Breen, Karlson, and Holm 2013). this additional analysis (table 3) shows that information management systems have the biggest direct and total effects of all…”
MethodJansen, T., Rademakers, J., Waverijn, G., Verheij, R., Osborne, R., & Heijmans, M. (2018) · BMC Health Services Research · doi:10.1186/s12913-018-3197-4 · Cited by 284
Atheists and Other Cultural Outsiders: Moral Boundaries and the Non-Religious in the United States
Edgell, P., Hartmann, D., Stewart, E., & Gerteis, J. (2016) · Social Forces · doi:10.1093/sf/sow063 · Cited by 251
Friis, K., Lasgaard, M., Rowlands, G., Osborne, R. H., & Maindal, H. T. (2016) · Journal of Health Communication · doi:10.1080/10810730.2016.1201175 · Cited by 228
“This command decomposes the total effect into direct effect (the effect of the independent variable (educational level) on the dependent variable (health behavior) when controlling for mediating variables (health literacy scales) and indirect effect (the effect of the independent variable on the dependent variable thr…”
BackgroundAssociation of Air Pollution Exposure With Psychotic Experiences During Adolescence
Newbury, J. B., Arseneault, L., Beevers, S., Kitwiroon, N., Roberts, S., Pariante, C. M., Kelly, F. J., & Fisher, H. L. (2019) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2019.0056 · Cited by 203
Santini, Z. I., Fiori, K. L., Feeney, J., Tyrovolas, S., Haro, J. M., & Koyanagi, A. (2016) · Journal of Affective Disorders · doi:10.1016/j.jad.2016.06.032 · Cited by 192
“We analyzed data with Stata version 13.1 (StataCorp, 2013).”
MethodInfluentialVancampfort, D., Koyanagi, A., Ward, P. B., Rosenbaum, S., Schuch, F. B., Mugisha, J., Richards, J., Firth, J., & Stubbs, B. (2017) · International Journal of Behavioral Nutrition and Physical Activity · doi:10.1186/s12966-017-0463-5 · Cited by 182
“Given that depression, mobility difficulties, pain/ discomfort and sleep problems may be linked with chronic conditions as part of the symptomatology per se or the consequences of the symptoms [42], we investigated the mediating effect of these factors with the use of Karlson-Holm-Breen command in Stata [43].”
MethodInfluentialChristiansen, J., Larsen, F. B., & Lasgaard, M. (2016) · Social Science & Medicine · doi:10.1016/j.socscimed.2016.01.020 · Cited by 171
Katikireddi, S. V., Skivington, K., Leyland, A. H., Hunt, K., & Mercer, S. W. (2017) · BMC Medicine · doi:10.1186/s12916-017-0913-6 · Cited by 171
“We also implemented an alternative mediation modelling approach using Stata’s khb command, which overcomes some methodological concerns about traditional approaches to mediation analysis [22]—in particular, the limitation that regression coefficients from different logistic regression models should not be compared.”
MethodHoffmann, R., Šedová, B., & Vinke, K. (2021) · Global Environmental Change · doi:10.1016/j.gloenvcha.2021.102367 · Cited by 159
Achterberg, P., de Koster, W., & van der Waal, J. (2015) · Public Understanding of Science · doi:10.1177/0963662515617367 · Cited by 202
Stubbs, B., Vancampfort, D., Firth, J., Schuch, F. B., Hallgren, M., Smith, L., Gardner, B., Kahl, K. G., Veronese, N., Solmi, M., et al. (2018) · Journal of Affective Disorders · doi:10.1016/j.jad.2017.12.104 · Cited by 138
“We used the khb (Karlson Holm Breen) command in Stata (Breen et al., 2013) for this purpose.”
MethodInfluentialDecreasing the SES math achievement gap: Initial math proficiency and home learning environments
Galindo, C., & Sonnenschein, S. (2015) · Contemporary Educational Psychology · doi:10.1016/j.cedpsych.2015.08.003 · Cited by 188
Physical multimorbidity and loneliness: A population-based study
Stickley, A., & Koyanagi, A. (2018) · PLOS ONE · doi:10.1371/journal.pone.0191651 · Cited by 135
Vancampfort, D., Stubbs, B., & Koyanagi, A. (2017) · International Journal of Behavioral Nutrition and Physical Activity · doi:10.1186/s12966-017-0602-z · Cited by 144
“The statistical analysis was performed with Stata 14.1 (Stata Corp LP, College station, Texas).”
MethodInfluentialStubbs, B., Koyanagi, A., Schuch, F. B., Firth, J., Rosenbaum, S., Veronese, N., Solmi, M., Mugisha, J., & Vancampfort, D. (2016) · Acta Psychiatrica Scandinavica · doi:10.1111/acps.12654 · Cited by 128
“The sample weighting and the complex study design were taken into account with the use of the svy command in STATA which uses the Taylor linearization method for robust variance estimation.”
MethodInfluentialObesity and adiposity indicators, asthma, and atopy in Puerto Rican children
Forno, E., Acosta‐Pérez, E., Brehm, J. M., Han, Y., Alvarez, M., Colón‐Semidey, A., CANINO, G. J., & Celedon, J. C. (2013) · Journal of Allergy and Clinical Immunology · doi:10.1016/j.jaci.2013.09.041 · Cited by 145
Williams, J., Bucci, S., Berry, K., & Varese, F. (2018) · Clinical Psychology Review · doi:10.1016/j.cpr.2018.05.009 · Cited by 126
Gender segregation in higher education: an empirical test of seven explanations
Barone, C., & Assirelli, G. (2019) · Higher Education · doi:10.1007/s10734-019-00396-2 · Cited by 174
“We first look at the corresponding parameters and at the variations of gender effects across models, then we use the KHB method for a formal decomposition exercise for categorical outcomes based on a mediation analysis (Breen et al. 2013).”
Political Socialization and Voting: The Parent–Child Link in Turnout
Gidengil, E., Wass, H., & Valaste, M. (2016) · Political Research Quarterly · doi:10.1177/1065912916640900 · Cited by 178
“Using the method developed by Karlson, Holm, and Breen (2012; see also Breen, Karlson, and Holm 2013), we compare the extent to which parental voting and the adult child’s own educational attainment mediate the relationship between parental education and the propensity to vote.”
BackgroundMethodHarnois, C. E., & Bastos, J. L. (2018) · Journal of Health and Social Behavior · doi:10.1177/0022146518767407 · Cited by 122
Police Body-Worn Cameras: Effects on Officers’ Burnout and Perceived Organizational Support
Adams, I., & Mastracci, S. (2019) · Police Quarterly · doi:10.1177/1098611118783987 · Cited by 120
Domènech-Abella, J., Mundó, J., Leonardi, M., Chatterji, S., Tobiasz-Adamczyk, B., Koskinen, S., Ayuso-Mateos, J. L., & Haro, J. M. (2018) · Journal of Affective Disorders · doi:10.1016/j.jad.2018.08.077 · Cited by 119
Steinmann, J.-P. (2018) · Journal of Ethnic and Migration Studies · doi:10.1080/1369183x.2018.1480359 · Cited by 150
“…for decomposing effects in models with a binary dependent variable, it allows for a simultaneous analysis of multiple mediators, it corrects for rescaling effects when additional variables are included in a model, and it works better when control variables are added (Breen, Karlson, and Holm 2013).”
BackgroundBell, C. N., Sacks, T. K., Tobin, C. S. T., & Thorpe, R. J. (2020) · SSM - Population Health · doi:10.1016/j.ssmph.2020.100561 · Cited by 127
Brännström, L., Vinnerljung, B., Forsman, H., & Almquist, Y. B. (2017) · Child Maltreatment · doi:10.1177/1077559517701855 · Cited by 141
Jacks-(and Jills)-of-all-trades: On whether, how and why gender influences firm innovativeness
Strohmeyer, R., Tonoyan, V., & Jennings, P. D. (2017) · Journal of Business Venturing · doi:10.1016/j.jbusvent.2017.07.001 · Cited by 132
van der Waal, J., & de Koster, W. (2017) · Political Studies · doi:10.1177/0032321717723505 · Cited by 134
“Consequently, we applied the KHB method (Breen et al., 2013), which was specifically designed to correct for this characteristic of logistic regression analyses, and also tests to what extent the effects of independent variables of interest on a dependent variable are mediated by another variable.”
MethodNewbury, J., Arseneault, L., Caspi, A., Moffitt, T. E., Odgers, C. L., & Fisher, H. L. (2016) · Schizophrenia Bulletin · doi:10.1093/schbul/sbw052 · Cited by 112
A Note on a Reformulation of the KHB Method
Breen, R., Bernt Karlson, K., & Holm, A. (2021) · Sociological Methods & Research · doi:10.1177/0049124118789717 · Cited by 110
“Further explanation and proofs of this can be found in the study by Karlson, Holm, and Breen (2012) and Breen, Karlson, and Holm (2013).”
BackgroundSelf-citationFraile, M., & Gómez, R. (2017) · European Journal of Political Research · doi:10.1111/1475-6765.12200 · Cited by 120
The News You Choose: news media preferences amplify views on climate change
Bolin, J. L., & Hamilton, L. C. (2018) · Environmental Politics · doi:10.1080/09644016.2018.1423909 · Cited by 138
“We applied the product-of-coefficients method described by Breen et al. (2013), which is computationally simple yet performs competitively in Monte Carlo evaluations.”
MethodApel, R. J., & Horney, J. (2017) · Criminology · doi:10.1111/1745-9125.12134 · Cited by 117
The Influence of Investigative Resources on Homicide Clearances
Braga, A. A., Turchan, B. S., & Barao, L. M. (2018) · Journal of Quantitative Criminology · doi:10.1007/s10940-018-9386-9 · Cited by 113
Jackson, J. W. (2020) · Epidemiology · doi:10.1097/ede.0000000000001319 · Cited by 134
Disease burden of adverse childhood experiences across 14 states
Waehrer, G. M., Miller, T. R., Marques, S. S., Oh, D. L., & Harris, N. B. (2020) · PLoS ONE · doi:10.1371/journal.pone.0226134 · Cited by 109
Jacob, L., Haro, J. M., & Koyanagi, A. (2019) · PLOS ONE · doi:10.1371/journal.pone.0215182 · Cited by 96
Shahriar, A. Z. M. (2018) · Journal of Business Venturing · doi:10.1016/j.jbusvent.2018.04.005 · Cited by 124
Racial/Ethnic Disparities in Time to a Breast Cancer Diagnosis
Molina, Y., Silva, A., & Rauscher, G. H. (2015) · Medical Care · doi:10.1097/mlr.0000000000000417 · Cited by 92
Femlogit—Implementation of the Multinomial Logit Model with Fixed Effects
Pforr, K. (2014) · The Stata Journal Promoting communications on statistics and Stata · doi:10.1177/1536867x1401400409 · Cited by 117
Koyanagi, A., DeVylder, J., Stubbs, B., Carvalho, A. F., Veronese, N., Haro, J. M., & Santini, Z. I. (2017) · Journal of Psychiatric Research · doi:10.1016/j.jpsychires.2017.10.001 · Cited by 108
“We used the khb (Karlson Holm Breen) command in Stata for this purpose (Breen et al., 2013).”
MethodPetts, R. J., Knoester, C., & Waldfogel, J. (2019) · Sex Roles · doi:10.1007/s11199-019-01050-y · Cited by 122
Revisiting the Causal Links between Economic Sanctions and Human Rights Violations
Liou, R. Y.-L., Murdie, A. M., & Peksen, D. (2020) · Political Research Quarterly · doi:10.1177/1065912920941596 · Cited by 91
Sexual Orientation and Risk of Pregnancy Among New York City High-School Students
Lindley, L. L., & Walsemann, K. M. (2015) · American Journal of Public Health · doi:10.2105/ajph.2015.302553 · Cited by 92
From Existential to Social Understandings of Risk: Examining Gender Differences in Nonreligion
Edgell, P., Frost, J., & Stewart, E. M. (2017) · Social Currents · doi:10.1177/2329496516686619 · Cited by 89
Is the Tea Party a “Religious” Movement? Religiosity in the Tea Party versus the Religious Right
Braunstein, R., & Taylor, M. (2017) · Sociology of Religion · doi:10.1093/socrel/srw056 · Cited by 83
Newbury, J., Arseneault, L., Caspi, A., Moffitt, T. E., Odgers, C. L., & Fisher, H. L. (2018) · Schizophrenia Bulletin · doi:10.1093/schbul/sbx060 · Cited by 82
“That is, almost half of the effect of urbanicity on adolescent psychotic experiences (media-tory estimates are supported by pathway analyses 55 ) was explained by the levels of social cohesion and neighborhood disorder in urban vs rural neighborhoods.”
BackgroundArpino, B., Gumà, J., & Julià, A. (2018) · PLoS ONE · doi:10.1371/journal.pone.0195320 · Cited by 93
Rijnhart, J. J. M., Valente, M. J., Smyth, H. L., & MacKinnon, D. P. (2021) · Prevention Science · doi:10.1007/s11121-021-01308-6 · Cited by 83
“However, it might be more meaningful to estimate the a coefficient with linear regression analysis rather than with logistic regression analysis (Breen et al., 2013; Li et al., 2007; Winship & Mare, 1983).”
Contribution of Four Comorbid Conditions to Racial/Ethnic Disparities in Mortality Risk
Daw, J. (2016) · American Journal of Preventive Medicine · doi:10.1016/j.amepre.2016.07.036 · Cited by 84
Hadjar, A., & Scharf, J. (2018) · Journal of Ethnic and Migration Studies · doi:10.1080/1369183x.2018.1433025 · Cited by 113
“(Breen et al. 2013) decomposing direct and indirect effects indicate the genuine effects of the value of education on educational aspirations.”
BackgroundMethodInfluentialWang, G., Zhou, Y., Duan, J., Kan, Q., Cheng, Z., & Tang, S. (2023) · BMC Public Health · doi:10.1186/s12889-023-16169-7 · Cited by 92
“Then we used a logistic regression model based on the KHB method [74, 75] for robustness testing.”
MethodBaumer, E. P., Cundiff, K., & Luo, L. (2020) · Criminology · doi:10.1111/1745-9125.12264 · Cited by 87
Redistribution attitudes and vote choice across the educational divide
Attewell, D. (2022) · European Journal of Political Research · doi:10.1111/1475-6765.12486 · Cited by 89
Frischmuth, T., Hindberg, K., Aukrust, P., Ueland, T., Brækkan, S. K., Hansen, J., & Morelli, V. M. (2022) · Journal of Thrombosis and Haemostasis · doi:10.1111/jth.15701 · Cited by 72
Stubbs, B., Koyanagi, A., Schuch, F., Firth, J., Rosenbaum, S., Gaughran, F., Mugisha, J., & Vancampfort, D. (2016) · Schizophrenia Bulletin · doi:10.1093/schbul/sbw111 · Cited by 71
Family enrichment and women entrepreneurial success: the mediating effect of family interference
Welsh, D. H. B., & Kaciak, E. (2019) · International Entrepreneurship and Management Journal · doi:10.1007/s11365-019-00587-4 · Cited by 85
“Thus, the two human capital dimensions do confound the KHB decomposition (Breen et al. 2013) and, as such, are worthy of being assigned a role of control variables (Hsu et al.”
BackgroundInfluentialMore than self‐interest: Why different classes have different attitudes to income inequality
Langsæther, P. E., & Evans, G. (2020) · British Journal of Sociology · doi:10.1111/1468-4446.12747 · Cited by 79
Populist Psychology: Economics, Culture, and Emotions
Rhodes-Purdy, M., Navarre, R., & Utych, S. (2021) · The Journal of Politics · doi:10.1086/715168 · Cited by 87
“We conduct mediation analysis per Breen, Karlson, and Holm (2013), using the khb Stata package.”
MethodShahriar, A. Z. M., & Shepherd, D. A. (2019) · Journal of Business Venturing · doi:10.1016/j.jbusvent.2019.06.006 · Cited by 91
Hoffmann, R., & Muttarak, R. (2019) · Environmental Research Letters · doi:10.1088/1748-9326/ab5ea0 · Cited by 104
“A mediation analysis based on the KHB method (Breen et al 2013) is employed to identify the underlying mechanisms of the effect of education on proenvironmental behavior.”
MethodAnsari, S., Anand, A., & Hossain, B. (2022) · PLoS ONE · doi:10.1371/journal.pone.0269646 · Cited by 78
“X is the partial effect of Z on Y given X; θZX is a term from an auxiliary regression of Z on X and σe is a scale parameter which allows the variance of the error to differ from that of the standard logistic distribution [60].”
BackgroundWedow, R., Zacher, M., Huibregtse, B. M., Mullan Harris, K., Domingue, B. W., & Boardman, J. D. (2018) · American Sociological Review · doi:10.1177/0003122418785368 · Cited by 67
“The use of probit or logit models when examining mediation (as we do in this analysis) is preferred over linear probability or Y standardized models, which may introduce bias (see Breen, Karlson, and Holm 2013).”
MethodSantini, Z., Pisinger, V., Nielsen, L., Madsen, K. R., Nelausen, M., Koyanagi, A., Koushede, V., Roffey, S., Thygesen, L., & Meilstrup, C. (2021) · Frontiers in Behavioral Neuroscience · doi:10.3389/fnbeh.2021.632906 · Cited by 60
“First, to assess the role of loneliness in the association between each type of social disconnectedness and all outcomes, a mediation analysis was performed using the khb (Karlson Holm Breen) command in Stata (Kohler et al., 2011; Breen et al., 2013).”
MethodInfluentialWho Controls Criminal Law? Racial Threat and the Adoption of State Sentencing Law, 1975 to 2012
Duxbury, S. (2020) · American Sociological Review · doi:10.1177/0003122420967647 · Cited by 78
“Note: Indirect effects are corrected for rescaling (Breen et al. 2013; Karlson et al. 2012).”
BackgroundMethodHesselman, S., Högberg, U., Råssjö, E.-B., Schytt, E., Löfgren, M., & Jonsson, M. (2017) · BJOG An International Journal of Obstetrics & Gynaecology · doi:10.1111/1471-0528.14708 · Cited by 71
“This formulation of the model allows for the fraction of the total effect that is mediated through indirect paths to be determined, despite the coefficients being on different scales.(22) The GSEM was fit using STATA version 14.”
MethodForster, A. G., & van de Werfhorst, H. G. (2019) · European Sociological Review · doi:10.1093/esr/jcz049 · Cited by 110
“As we are among other things interested in mediation effects, we employ KHB-modelling to adjust the coefficients for scaling effects and to correctly estimate the size of the mediation (Karlson, Holm and Breen, 2012; Breen, Karlson and Holm, 2013).”
MethodHsieh, N., Liu, H., & Lai, W.-H. (2021) · The Gerontologist · doi:10.1093/geront/gnaa136 · Cited by 64
“The KHB method decomposes the total effect of a predictor variable on an outcome variable into direct and indirect (mediation) effects in nonlinear probability models such as ordinal logit models (Breen et al., 2013; Karlson et al., 2012).”
MethodLei, L., & Desai, S. (2021) · Social Science & Medicine · doi:10.1016/j.socscimed.2021.113982 · Cited by 86
“A comparison of coefficients across logistic regression models is not straightforward because of the rescaling of the model when including new covariates (Breen et al., 2013).”
MethodIndustry 4.0 and production recovery in the covid era
Cugno, M., Castagnoli, R., Büchi, G., & Pini, M. (2021) · Technovation · doi:10.1016/j.technovation.2021.102443 · Cited by 76
Education and Social Mobility: New Analytical Approaches
Breen, R., & Karlson, K. B. (2013) · European Sociological Review · doi:10.1093/esr/jct025 · Cited by 92
Self-citationScience career aspiration and science capital in China and UK: a comparative study using PISA data
Du, X., & Wong, B. (2019) · International Journal of Science Education · doi:10.1080/09500693.2019.1662135 · Cited by 73
Boertien, D., & Härkönen, J. (2018) · Demographic Research · doi:10.4054/demres.2018.38.41 · Cited by 85
“We used the Karlson-Holm-Breen (KHB) method for mediation analysis with nonlinear probability models (Breen, Karlson, and Holm 2013) to estimate how much of the educational difference is explained by each individual variable.”
MethodQuantifying relative importance: computing standardized effects in models with binary outcomes
Grace, J. B., Johnson, D. J., Lefcheck, J. S., & Byrnes, J. E. K. (2018) · Ecosphere · doi:10.1002/ecs2.2283 · Cited by 75
“…now recognize that because of the causal non-identi fi cation, the coef fi cients recovered by the software are not the true parameter values; instead, the whole model has been rescaled by a scaling factor ( r u ) that converts the true error standard deviation to the fi xed value (Breen et al. 2013).”
BackgroundBias Amplification and Bias Unmasking
Middleton, J. A., Scott, M. A., Diakow, R., & Hill, J. L. (2016) · Political Analysis · doi:10.1093/pan/mpw015 · Cited by 59
Noncollapsibility and its role in quantifying confounding bias in logistic regression
Schuster, N. A., Twisk, J. W. R., ter Riet, G., Heymans, M. W., & Rijnhart, J. J. M. (2021) · BMC Medical Research Methodology · doi:10.1186/s12874-021-01316-8 · Cited by 61
Transmission of Faith in Families: The Influence of Religious Ideology
Smith, J. (2020) · Sociology of Religion · doi:10.1093/socrel/sraa045 · Cited by 87
“To more closely examine the explanatory effects of intervening variables, I apply multiple mediator, or KHB, analyses (Breen et al. 2013) to Models 4 and 9 of table 3 (results not shown).”
MethodChildhood lead exposure is associated with lower cognitive functioning at older ages
Lee, H., Lee, M. W., Warren, J. R., & Ferrie, J. P. (2022) · Science Advances · doi:10.1126/sciadv.abn5164 · Cited by 70
“To formally test for mediation, we used the KHB method (40, 59).”
MethodRaitasalo, K., Kraus, L., Bye, E. K., Karlsson, P., Tigerstedt, C., Törrönen, J., & Raninen, J. (2020) · Addiction · doi:10.1111/add.15089 · Cited by 81
Silver, E., Goff, K., & Iceland, J. (2022) · Criminology · doi:10.1111/1745-9125.12303 · Cited by 59
Congregado, E., Iglesias, J., Millán, J. M., & Román, C. (2015) · Applied Economics · doi:10.1080/00036846.2015.1083080 · Cited by 75
“Using the KHB method (Karlson, Holm, and Breen 2012; Breen, Karlson, and Holm 2013), we tested for a possible mediating effect and observed that, although significant, this indirect effect is small.”
MethodWerneck, A. O., da Silva, D. R. P., Malta, D. C., Lima, M. G., Júnior, P. R. B. D. S., Azevedo, L. O., Barros, M. B. D. A., & Szwarcwald, C. L. (2020) · Sleep Medicine · doi:10.1016/j.sleep.2020.09.021 · Cited by 60
“The Karlson Holm Breen method was used for the mediation [23].”
MethodNot All Homes Are Safe: Family Violence Following the Onset of the Covid-19 Pandemic
Drotning, K. J., Doan, L., Sayer, L. C., Fish, J. N., & Rinderknecht, R. G. (2022) · Journal of Family Violence · doi:10.1007/s10896-022-00372-y · Cited by 73
“Second, to assess whether household income loss mediates the relationship between gender, sexual identity, and experiences with family violence, we employ the KHB decomposition method (Breen et al., 2013).”
MethodDoes Collaborative Learning Influence Persistence to the Second Year of College?
Loes, C. N., An, B. P., Saichaie, K., & Pascarella, E. T. (2016) · The Journal of Higher Education · doi:10.1080/00221546.2016.1243942 · Cited by 79
“…do not observe Y*, they are able to observe a dichotomized version of Y*, which is Y. Researchers observe Y = 1 (2nd-year reenrollment) when Y* crosses a certain threshold, and they observe Y = 0 (failure to reenroll) when Y* does not meet that threshold (Breen et al., 2013; Mood, 2010).”
BackgroundMethodInfluentialThe Economic Consequences of Divorce in Germany: What Has Changed since the Turn of the Millennium?
Bröckel, M., & Andreß, H. (2015) · Comparative Population Studies · doi:10.12765/cpos-2015-04 · Cited by 76
Stolz, J., Pollack, D., & de Graaf, N. D. (2020) · European Sociological Review · doi:10.1093/esr/jcaa014 · Cited by 60
Wang, B., Wang, X., Yu, L., Liu, W., Song, J., Fan, L., Zhou, M., Yang, M., Ma, J., Cheng, M., et al. (2022) · Environment International · doi:10.1016/j.envint.2022.107261 · Cited by 65
Disability pension among adult former child welfare clients: A Swedish national cohort study
Vinnerljung, B., Brännström, L., & Hjern, A. (2015) · Children and Youth Services Review · doi:10.1016/j.childyouth.2015.07.001 · Cited by 68
“Bymeans of decomposition analyses (Breen et al., 2013),we also assess which confounding factors were most influential for the differences between crude and adjusted ORs for DP for the child welfare groups when compared to majority population peers.”
BackgroundLee, H., & Schafer, M. H. (2020) · Journal of Aging and Health · doi:10.1177/0898264320972547 · Cited by 63
“Next, we conducted formal mediation tests using the Karlson–Holm–Breen (KHB) method (Breen et al., 2013; Kohler et al., 2011).”
MethodEthnic choice effects at the transition into upper-secondary education in Switzerland
Tjaden, J., & Scharenberg, K. (2016) · Acta Sociologica · doi:10.1177/0001699316679491 · Cited by 75
“The KHB method performs better especially when additional control variables are included in the model (Breen et al., 2013), which was the case here.”
MethodTinkler, J., & Zhao, J. (2019) · Journal of Public Administration Research and Theory · doi:10.1093/jopart/muz037 · Cited by 69
Depression, Risk Preferences, and Risk-Taking Behavior
Cobb‐Clark, D. A., Dahmann, S. C., & Kettlewell, N. (2020) · The Journal of Human Resources · doi:10.3368/jhr.58.1.0419-10183r1 · Cited by 68
Su, R., & Shen, W. (2020) · Journal of Chinese Political Science · doi:10.1007/s11366-020-09696-2 · Cited by 66
Playford, C., Dibben, C. J. L., & Williamson, L. (2017) · International Journal for Equity in Health · doi:10.1186/s12939-017-0698-4 · Cited by 60
“This approach is advantageous because it permits the inclusion of multiple mediators while holding other covariates constant [24].”
BackgroundMethodMetabolic syndrome and trajectory of knee pain in older adults
Pan, F., Tian, J., Cicuttini, F., & Jones, G. (2019) · Osteoarthritis and Cartilage · doi:10.1016/j.joca.2019.05.030 · Cited by 57
Jacob, M., Iannelli, C., Duta, A., & Smyth, E. (2020) · International Journal of Comparative Sociology · doi:10.1177/0020715220913043 · Cited by 65
“The role of school subjects as mediators for field of study choice Finally, we run decomposition analysis using the KHB decomposition for the different field of study specifications (Breen et al., 2013).”
MethodInfluentialCategorical Distinctions and Claims-Making: Opportunity, Agency, and Returns from Wage Negotiations
Sauer, C., Valet, P., Shams, S., & Tomaskovic‐Devey, D. (2021) · American Sociological Review · doi:10.1177/00031224211038507 · Cited by 66
“Alternative mediation analysis strategies after logistic regressions using the khb method (Breen, Karlson, and Holm 2013) led to similar results.”
MethodExplaining the increasing disability prevalence among mid-life US adults, 2002 to 2016
Zajacova, A., & Montez, J. K. (2018) · Social Science & Medicine · doi:10.1016/j.socscimed.2018.05.041 · Cited by 56
Uncertain Time: Precarious Schedules and Job Turnover in the US Service Sector
Choper, J., Schneider, D., & Harknett, K. (2021) · Industrial and Labor Relations Review · doi:10.1177/00197939211048484 · Cited by 67
“…we use the Karlson, Holm, and Breen (KHB) method, which allows for the decomposition of total effects into direct and indirect effects in nonlinear models, net of control variables (Karlson and Holm 2011; Kohler, Karlson, and Holm 2011; Karlson, Holm, and Breen 2012; Breen, Karlson, and Holm 2013).”
Method
Metadata
- Authors
- Breen, R., Karlson, K. B., & Holm, A.
- Affiliations
- Yale University (US)
- Aarhus University (DK)
- University of Copenhagen (DK)
- Corresponding author
- Breen, Richard
- Venue
- Sociological Methods & Research
- Publisher
- SAGE Publications
- Published
- 2013-05
- Volume
- 42
- Issue
- 2
- Pages
- 164-191
- ISSN
- 0049-1241 (ISSN-L)
- 1552-8294
- OpenAlex
- W2110453893
- Cited by
- 818
- References
- 48
- Citations by year
- 2026: 64 · 2025: 75 · 2024: 78 · 2023: 81 · 2022: 99 · 2021: 87 · 2020: 73 · 2019: 63 · 2018: 66 · 2017: 48 · 2016: 37 · 2015: 27 · 2014: 14 · 2013: 6
- FWCI
- 24.64
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
- Locations
- Sociological Methods & Research (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Social Sciences › Sociology and Political Science › Intergenerational and Educational Inequality Studies
- Keywords
- mediation analysis, logit model, probit model, causal mediation analysis, sequential ignorability
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.