The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Monotonicity of effect sizes: questioning kappa-squared as mediation effect size measure
Abstract
Mediation analysis is important for research in psychology and other social and behavioral sciences. Great progress has been made in testing mediation effects and in constructing their confidence intervals. Mediation effect sizes have also been considered. Preacher and Kelley (2011) proposed and recommended κ² as an effect size measure for a mediation effect. In this article, we argue that κ² is not an appropriate effect size measure for mediation models, because of its lack of the property of rank preservation (e.g., the magnitude of κ² may decrease when the mediation effect that κ² represents increases). Furthermore, κ² can lead to paradoxical results in multiple mediation models. We show that the problem of κ² is due to (a) the improper calculation of the maximum possible value of the indirect effect, and (b) mathematically, the maximum possible indirect effect is infinity, implying that the definition of κ² is mathematically incorrect. At this time, it appears that the traditional mediation effect size measure PM (the ratio of the indirect effect to the total effect), together with some other statistical information, should be preferred for basic mediation models. But for inconsistent mediation models where the indirect effect and the direct effect have opposite signs, the situation is less clear. Other considerations and suggestions for future research are also discussed.
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
“Three single-arm trials showed that increased global trait mindfulness mediated the impact of MBIs on reduction in GAD severity [8] and perceived stress [9-11]”
In the citing paper
“evidence that MBIs better equipped people with GAD and depression with the skills to perceive emotions and thoughts as transient occurrences rather than personally associating with them – a process called “decentering” – than controls [8, 95]”
Citations
Cites
Statistical power analysis for the behavioral sciences
Cohen, J. (1990) · Computers Environment and Urban Systems · doi:10.1016/0198-9715(90)90050-4 · Cited by 65,417
Statistical Power Analysis for the Behavioral Sciences (2nd ed.).
Lachenbruch, P. A., & Cohen, J. (1989) · Journal of the American Statistical Association · doi:10.2307/2290095 · Cited by 37,421
Preacher, K. J., & Hayes, A. F. (2008) · Behavior Research Methods · doi:10.3758/brm.40.3.879 · Cited by 34,117
Asymptotic Confidence Intervals for Indirect Effects in Structural Equation Models
Sobel, M. E. (1982) · Sociological Methodology · doi:10.2307/270723 · Cited by 12,810
Reconsidering Baron and Kenny: myths and truths about mediation analysis
Zhao, X., Lynch, J. G., & Chen, Q. (2010) · Journal of Consumer Research · doi:10.1086/651257 · Cited by 12,583
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
A comparison of methods to test mediation and other intervening variable effects
MacKinnon, D. P., Lockwood, C. M., Hoffman, J. M., West, S. G., & Sheets, V. (2002) · Psychological Methods · doi:10.1037/1082-989x.7.1.83 · Cited by 9,406
Distribution Theory for Glass's Estimator of Effect Size and Related Estimators
Hedges, L. V. (1981) · Journal of Educational Statistics · doi:10.2307/1164588 · Cited by 5,695
Introduction to Statistical Mediation Analysis
MacKinnon, D. P. (2012) · doi:10.4324/9780203809556 · Cited by 5,618
Equivalence of the Mediation, Confounding and Suppression Effect
MacKinnon, D. P., Krull, J. L., & Lockwood, C. M. (2000) · Prevention Science · doi:10.1023/a:1026595011371 · Cited by 4,188
Cited by
Sorted by citations
Items 101–200 of 350
de Vries, E. E., Verlinden, M., Rijlaarsdam, J., Jaddoe, V. W. V., Verhulst, F. C., Arseneault, L., & Tiemeier, H. W. (2017) · Research on Child and Adolescent Psychopathology · doi:10.1007/s10802-017-0380-8 · Cited by 37
“As recommended by Wen and Fan (2015), the proportion of the indirect effect relative to the total effect was calculated as an effect size measure (PM).”
MethodMcLarnon, M. J. W., O’Neill, T., Taras, V., Law, D., Donia, M. B. L., & Steel, P. (2019) · Canadian Journal of Behavioural Science/Revue canadienne des sciences du comportement · doi:10.1037/cbs0000135 · Cited by 42
Hill, N. L., Bhargava, S., Bratlee‐Whitaker, E., Turner, J. R., Brown, M. J., & Mogle, J. A. (2021) · Journal of Alzheimer s Disease · doi:10.3233/jad-210230 · Cited by 32
“As an estimate of effect size, we calculated the proportion of the total relationship between SCD and objective memory (ab + c’) that is uniquely predicted by depressive symptoms (ab) [46].”
Trauma-Related Sleep Problems and Associated Health Outcomes in Police Officers: A Path Analysis
Chopko, B. A., Palmieri, P. A., & Adams, R. E. (2018) · Journal of Interpersonal Violence · doi:10.1177/0886260518767912 · Cited by 40
“We follow advice of Wen and Fan (2015) in calculating effect sizes for mediation models and give the ratio of indirect to total effects.”
MethodLaMotte, A. D., Taft, C. T., & Weatherill, R. P. (2016) · Psychological Trauma Theory Research Practice and Policy · doi:10.1037/tra0000157 · Cited by 30
Walters, G. D. (2017) · International Journal of Social Research Methodology · doi:10.1080/13645579.2017.1305710 · Cited by 30
“The R2 and ĸ2 indices, on the other hand, lack monotonicity or rank preservation, which means that a larger absolute value on the putative effect size indicator does not necessarily represent a stronger effect (Wen & Fan, 2015).”
BackgroundResultInfluentialLin, Y., & Zhou, X. Y. (2022) · Computers and Education Open · doi:10.1016/j.caeo.2022.100110 · Cited by 41
“, [134,135]) defend this agent and assert that “if accompanied by the total effect, the ratio of the indirect effect to the total effect is meaningful where the indirect effect and the direct effect have the same sign in a basic mediation model” ([134], p.”
BackgroundCranmer, G. A., Goldman, Z. W., & Booth‐Butterfield, M. (2016) · Western Journal of Communication · doi:10.1080/10570314.2016.1231931 · Cited by 29
“To help understand the magnitude of the mediation, completely standardized indirect effects and the ratio of each indirect effect to the total effect was also calculated (see Wen & Fan, 2015).”
MethodZhao, C., Ding, N., Yang, X., Xu, H., Lai, X., Tu, X., Lv, Y., Xu, D., & Zhang, G. (2021) · Frontiers in Public Health · doi:10.3389/fpubh.2021.752210 · Cited by 28
“Effect sizes (PM = the ratio of the indirect effect to the total effect) are also reported (67).”
BackgroundExplaining participation in Earth Hour: the identity perspective and the theory of planned behavior
Chan, H., Pong, V., & Tam, K. (2019) · Climatic Change · doi:10.1007/s10584-019-02554-y · Cited by 31
Belief in the immutability of attitudes both increases and decreases advocacy.
Omair Akhtar, B., & Wheeler, S. C. (2016) · Journal of Personality and Social Psychology · doi:10.1037/pspa0000060 · Cited by 29
Schaeuffele, C., Bär, J., Buengener, I., Grafiadeli, R., Heuthaler, E., Strieder, J., Ziehn, P., Knaevelsrud, C., Renneberg, B., & Boettcher, J. (2022) · Cognitive Therapy and Research · doi:10.1007/s10608-021-10272-y · Cited by 24
The Role of Contract Farming in Green Smart Agricultural Technology
Chen, J., & Hong, Z. (2023) · Sustainability · doi:10.3390/su151310600 · Cited by 27
“By referencing Baron’s gradual regression method [37] for checking the mediating effect and the steps in the mediating and moderating model suggested by Wen Zhonglin [37], this paper establishes a model as shown in Equations (1)–(4).”
BackgroundMethodPsychological mediators of avoidance and endurance behavior after concussion.
Terpstra, A. R., Cairncross, M., Yeates, K. O., Vranceanu, A., Greenberg, J., Hunt, C., & Silverberg, N. D. (2021) · Rehabilitation Psychology · doi:10.1037/rep0000390 · Cited by 34
Brailovskaia, J., Ujma, M., Friedrich, S., & Teismann, T. (2019) · Crisis · doi:10.1027/0227-5910/a000596 · Cited by 29
Guo, X., Li, J., Niu, Y., & Luo, L. (2022) · Frontiers in Psychology · doi:10.3389/fpsyg.2022.747296 · Cited by 28
Delgado-Rodríguez, R., Linares, R., & Padilla, M. M. (2022) · Journal of Eating Disorders · doi:10.1186/s40337-022-00643-5 · Cited by 38
“Indirect effect sizes were computed both as completely standardized effects [83] and indirect-to-direct-effect ratio statistics (PM; [84]).”
MethodRelating sex differences in aggression to three forms of empathy
Dryburgh, N. S. J., & Vachon, D. D. (2019) · Personality and Individual Differences · doi:10.1016/j.paid.2019.109526 · Cited by 29
“Tapping” into Goodwill: Enhancing Corporate Reputation through Customer Volunteering
Rodell, J. B., Sabey, T. B., & Rogers, K. M. (2019) · Academy of Management Journal · doi:10.5465/amj.2018.0354 · Cited by 25
Witherow, M. P., Chandraiah, S., Seals, S. R., Sarver, D. E., Parisi, K. E., & Bugán, A. (2017) · The Journal of Sexual Medicine · doi:10.1016/j.jsxm.2017.04.671 · Cited by 32
Panzeri, A., Ferrario, S. R., & Cerutti, P. (2021) · Frontiers in Psychology · doi:10.3389/fpsyg.2021.636129 · Cited by 24
“Moreover, Hedge’s g was supported by the overlapping index (η); that is, it was used to quantify the magnitude of differences between the Kernel density distributions of the groups (Huberty and Lowman, 2000; Wen and Fan, 2015; Pastore and Calcagnì, 2019; Rossi et al., 2020b).”
MethodOgbeibu, S., & Gaskin, J. E. (2022) · FIIB Business Review · doi:10.1177/23197145221121084 · Cited by 40
“However, in some EDMs, the v effects may seem too small to be worth considering for practical implications and decisions (Wen & Fan, 2015).”
BackgroundNimon, K. (2017) · Human Resource Development Quarterly · doi:10.1002/hrdq.21290 · Cited by 25
“For SEM models with indirect effects, authors should consider Zhao et al. ( 2010 ) as well as Wen and Fan ( 2015 ) for guidance on reporting indirect effects.”
BackgroundWalters, G., & Espelage, D. L. (2018) · International Journal of Child Abuse & Neglect · doi:10.1016/j.chiabu.2018.05.006 · Cited by 23
Diamond‐Smith, N., Shieh, J., Puri, M. C., & Weiser, S. D. (2020) · Public Health Nutrition · doi:10.1017/s1368980020000579 · Cited by 25
“To calculate the mediation effect size, the mediation ratio was used as an estimate of the proportion of total effect mediated (36) .”
Win, E., Zainal, N. H., & Newman, M. G. (2021) · Journal of Affective Disorders · doi:10.1016/j.jad.2021.03.086 · Cited by 24
“…effect size refers to the proportion of the indirect effect (a*b) relative to the total effect, c = a*b + c’ i.e., percentage of variance wherein trait anger explained the childhood trauma–adulthood psychopathology relation (Cheung and Lau, 2008; Preacher and Kelley, 2011; Wen and Fan, 2015).”
BackgroundWoudstra, A. J., Smets, E. M. A., Verdam, M. G. E., & Fransen, M. P. (2019) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph16234644 · Cited by 23
“Moreover, to give an indication of the extent of the mediating role of the HL domains in the relationship between educational level and decision-making outcomes, we also calculated the percentage of the total effect that was mediated by the HL domains (ab/(ab + c’ × 100%)) [37].”
BackgroundErdol, T. A., & Arıkan, Ç. A. (2022) · Social Psychology of Education · doi:10.1007/s11218-022-09692-9 · Cited by 33
“Additionally, Wen and Fan (2015) stated that the absence of rank preservation in these effect-size measurements has been questioned and was not a reliable method in mediation analyses.”
BackgroundWillems, R. A., Lechner, L., Verboon, P., Mesters, I., Kanera, I. M., & Bolman, C. A. W. (2017) · Psychology and Health · doi:10.1080/08870446.2017.1293054 · Cited by 25
“The proportion of the total effect that was mediated was calculated by dividing the coefficient of the mediated effect by the coefficient of the total effect: a bð Þ c0 þ a bð Þð Þ, as this measure of effect size is preferred for basic mediation models (Wen & Fan, 2015).”
MethodTwo-level moderated mediation models with single-level data and new measures of effect sizes
Liu, H., Yuan, K., & Wen, Z. (2021) · Behavior Research Methods · doi:10.3758/s13428-021-01578-6 · Cited by 22
Self-citationCraig, F., Servidio, R. C., Calomino, M. L., Candreva, F., Nardi, L., Palermo, A., Polito, A., Spina, M. F., Tenuta, F., & Costabile, A. (2023) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph20105906 · Cited by 23
“Finally, we computed each mediation effect size (PM) as the ratio of the indirect effect to the total effect [44].”
MethodKern, B. D., & Graber, K. C. (2017) · Measurement in Physical Education and Exercise Science · doi:10.1080/1091367x.2017.1319371 · Cited by 22
“Effect sizes for the structural model were calculated as the ratio of indirect effect to direct effect (RM) of each TCQ-PE construct with LtC (Wen & Fan, 2015).”
MethodEmotional Clarity, Anxiety Sensitivity, and PTSD Symptoms Among Trauma-Exposed Inpatient Adolescents
Viana, A. G., Candelari, A. E., Woodward, E. C., Raines, E. M., Paulus, D. J., Berenz, E. C., & Zvolensky, M. J. (2017) · Child Psychiatry & Human Development · doi:10.1007/s10578-017-0736-x · Cited by 22
“Following recent recommendations,[47] the ratio of the indirect effect to the total effect (i.”
BackgroundChan, M. C. Y. (2017) · Asia Pacific Journal of Education · doi:10.1080/02188791.2017.1388214 · Cited by 22
“Although there are existing criticisms of this approach, it remains a preferred method in current empirical developments especially when the sample size is large (Wen & Fan, 2015).”
MethodDeLuca, J. S., Hwang, J., Stepinski, L., & Yanos, P. (2020) · Journal of Mental Health · doi:10.1080/09638237.2020.1836556 · Cited by 20
“The strength of the mediation effect5 can be deduced from the ratio of the indirect effect to the total effect (Wen & Fan, 2015), as presented below.”
BackgroundDoes the verified badge of social media matter? The perspective of trust transfer theory
Liao, C. H., Hsieh, J., & Kumar, S. (2023) · Journal of Research in Interactive Marketing · doi:10.1108/jrim-10-2023-0339 · Cited by 21
Chen, Z. J., Bechara, A. O., Worthington, E. L., Davis, E. B., & Csíkszentmihályi, M. (2019) · The Journal of Positive Psychology · doi:10.1080/17439760.2019.1663254 · Cited by 25
Liu, Q., Yang, X., Zhang, C., & Xiong, J. (2024) · Journal of Behavioral Addictions · doi:10.1556/2006.2024.00034 · Cited by 28
Rossi, A. A., Panzeri, A., Fernández, I., Invernizzi, R., Taccini, F., & Mannarini, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-72274-6 · Cited by 26
“This was done using the separation index (1-η) 56,57 measuring the magnitude (effect size) of the difference of a phenomenon 56,58 .”
MethodLaMotte, A. D., & Murphy, C. M. (2016) · Psychological Trauma Theory Research Practice and Policy · doi:10.1037/tra0000205 · Cited by 21
“PM was provided as an index of effect size of the mediated effect, which represents the ratio of the indirect effect to the total effect, and is recommended by Wen and Fan (2015) in cases when the indirect and direct effects have the same sign.”
Mak, S., Cheung, K., Soh, K., Sit, P., & Ieong, M. (2016) · Educational Psychology · doi:10.1080/01443410.2016.1242712 · Cited by 21
“The indirect effects of JOyREAD, DIVREAD, RFSTRLIT, METASuM and unDREM respectively are 90.48, 5.51, 34.16, 46.87 and 55.26, with corresponding effect sizes PM being 1.085, 0.066, 0.410, 0.562 and 0.663 (see Wen & Fan, 2015 for a correct interpretation of PM when it is greater than (1).”
MethodInfluentialLayh, M. C., Rudolph, K., & Littleton, H. (2019) · Journal of Trauma & Dissociation · doi:10.1080/15299732.2019.1675112 · Cited by 21
“To evaluate the magnitude of the indirect effect we report the standardized indirect effect (Wen & Fan, 2015).”
Cracking the Black Box: Capturing the Role of Expectation States in Status Processes
Kalkhoff, W., Melamed, D., Pollock, J., Miller, B. J., Overton, J., & Pfeiffer, M. (2019) · Social Psychology Quarterly · doi:10.1177/0190272519868988 · Cited by 21
Liu, S., Wang, X., Zou, S., & Wu, X. (2022) · Family Process · doi:10.1111/famp.12757 · Cited by 21
Engagement en la formación docente como impulsor de actitudes inclusivas
Falla, D., Gómez, C. A., & del Pino, C. G. (2022) · Educación XX1 · doi:10.5944/educxx1.30369 · Cited by 20
Black, J. E., Helmy, Y., Robson, O., & Barnes, J. (2018) · Poetics · doi:10.1016/j.poetic.2018.12.005 · Cited by 21
Raines, E. M., Viana, A. G., Trent, E. S., Woodward, E. C., Candelari, A. E., Zvolensky, M. J., & Storch, E. A. (2019) · Journal of Anxiety Disorders · doi:10.1016/j.janxdis.2019.102136 · Cited by 20
DeVries, J. M., Szardenings, C., Doebler, P., & Gebhardt, M. (2021) · Social Sciences · doi:10.3390/socsci10010011 · Cited by 23
“The use of these ratios is preferred for consistent mediation effects where there are more than 500 cases (Wen and Fan 2015), and our large database provides us plenty of cases.”
BackgroundWang, J., Yu, S., Li, M., Cheng, Y., & Wang, C. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph192013401 · Cited by 19
Jiang, Y., Gao, J., Wu, S., & Jiao, K. (2022) · CATENA · doi:10.1016/j.catena.2022.106761 · Cited by 19
Yu, R., Wang, M., & Hu, J. (2023) · Journal of Educational Computing Research · doi:10.1177/07356331221137107 · Cited by 27
“Regarding the effect size of the mediators, the proportion mediated (PM), i.e., the ratio of the indirect effect to the total effect, was computed as the main indicator (Wen & Fan, 2015).”
MethodNocebo responses to high-voltage power lines: Evidence from a prospective field study
Porsius, J. T., Claassen, L., Woudenberg, F., Smid, T., & Timmermans, D. R. M. (2015) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2015.11.038 · Cited by 19
The Role of Self-Compassion Among Adaptive and Maladaptive Perfectionists in University Students
Kawamoto, A., Sheth, R., Yang, M., Demps, L., & Sevig, T. (2023) · The Counseling Psychologist · doi:10.1177/00110000221129606 · Cited by 19
“The effect sizes were calculated using PM, the proportion of variance explained through a mediator, as our results met the conditions to use this measure (Wen & Fan, 2015).”
MethodCognitive mechanisms in cannabis-related paranoia; Initial testing and model proposal
Newman‐Taylor, K., Richardson, T. H., Sood, M., Sopp, M., Perry, E., & Bolderston, H. (2020) · Psychosis · doi:10.1080/17522439.2020.1757742 · Cited by 17
Bidstrup, H., Brennan, L., Hindle, A., Kaufmann, L. M., & Garcia, X. D. L. P. (2022) · Obesity Surgery · doi:10.1007/s11695-022-06245-z · Cited by 17
“Reporting appropriate and meaningful estimates of effect sizes for mediation is a complex topic [57, 58].”
BackgroundDesconexión moral cívica, empatía y actitudes de futuros docentes hacia la diversidad cultural
Cabrera-Vázquez, A., Romera, E. M., Ruiz, R. O., del Pino, C. G., & Falla, D. (2022) · Aula Abierta · doi:10.17811/rifie.51.3.2022.285-292 · Cited by 22
“El efecto total informó de la relación entre la variable dependiente e independiente, mientras que la relación entre el efecto indirecto y el efecto total (PM) indicó la medida del efecto de mediación (Wen y Fan, 2015).”
BackgroundLiu, L., Wang, W., Lian, Y., Wu, X., Li, C., & Qiao, Z. (2023) · Archives of Suicide Research · doi:10.1080/13811118.2023.2237088 · Cited by 17
“Specifically, P M is defined as the ratio of the indirect effect to the total effect (Wen & Fan, 2015).”
Ng, M. H. S., Zainal, N. H., & Newman, M. G. (2024) · Journal of Anxiety Disorders · doi:10.1016/j.janxdis.2024.102826 · Cited by 18
“Mediation effect sizes were presented as a proportion of indirect effect ( a × b ) relative to total effect ( c = a × b + c ’ ) (Preacher & Kelley, 2011; Wen & Fan, 2015).”
BackgroundWalters, G. D. (2016) · Criminal Justice and Behavior · doi:10.1177/0093854816677566 · Cited by 17
“…there are conditions under which one approach may prove more accurate than another approach (Fairchild, MacKinnon, Taborga, & Taylor, 2009; Wen & Fan, 2015) and conditions, such as inconsistent mediation where the direct and indirect effects have opposite signs (MacKinnon et al., 2007),…”
BackgroundPornography, religiosity, and social work
Droubay, B. A., & Butters, R. P. (2019) · Journal of Social Work · doi:10.1177/1468017319852599 · Cited by 17
“…recommended reporting “the magnitude of the indirect effect relative to the maximum possible indirect effect” (i.e., kappa-squared; p. 104); however, Wen and Fan (2015) subsequently found that kappa-squared should not be used because of its lack of rank preservation, so this approach has fallen…”
BackgroundPositive relations mediate the bidirectional connections between depression and anxiety symptoms
Barber, K. E., Zainal, N. H., & Newman, M. G. (2022) · Journal of Affective Disorders · doi:10.1016/j.jad.2022.12.082 · Cited by 17
“The mediation effect size was the ratio of the indirect effect (a*b) to the total effect (c = a*b + c’) (Preacher and Kelley, 2011; Wen and Fan, 2015).”
BackgroundRoemer, E. J., West, K. L., Northrup, J. B., & Iverson, J. M. (2018) · Developmental Science · doi:10.1111/desc.12767 · Cited by 16
“To compare the models, the ratio of the indirect to total effect (a measure of effect size recommended for basic mediation models; Wen & Fan, 2015) was calculated.”
MethodBoffa, J. W., & Schmidt, N. B. (2018) · Behaviour Research and Therapy · doi:10.1016/j.brat.2018.12.007 · Cited by 16
Røed, M. H., Vik, F. N., Hillesund, E. R., Lippevelde, W. V., & Øverby, N. C. (2020) · Food & Nutrition Research · doi:10.29219/fnr.v64.3730 · Cited by 17
“To estimate the size of the indirect effect (mediated effect), the ratio of the indirect effect to the total effect was computed by dividing the product of coefficient (αβ) by the overall association (τ-coefficient) (43).”
MethodHubner, S., Rudic, B., & Baum, M. (2021) · The International Journal of Human Resource Management · doi:10.1080/09585192.2021.1893785 · Cited by 16
“Although this requires cautious interpretation, in certain conditions (sample size should be at least 500, the total effect should be larger than the indirect effect and of same sign) PM is seen as an appropriate effect size measure (Hayes, 2013; Wen & Fan, 2015).”
BackgroundMahoney, A. E. J., Hobbs, M. J., Williams, A. D., Andrews, G., & Newby, J. M. (2018) · Behaviour Change · doi:10.1017/bec.2018.13 · Cited by 15
Falla, D., Ruiz, R. O., & Romera, E. M. (2023) · Current Psychology · doi:10.1007/s12144-022-04229-x · Cited by 19
“Finally, the mediation effect was calculated through the relationship between the indirect effect and the total (Wen & Fan, 2015).”
MethodXie, S., Zhou, Y., Yin, Y., Shao, R., Fang, L., & Shao, W. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2023.1023662 · Cited by 15
Bedaso, A., Adams, J., Peng, W., & Sibbritt, D. W. (2023) · BMC Pregnancy and Childbirth · doi:10.1186/s12884-023-05708-0 · Cited by 20
“PM is the ratio of the indirect effect to the total effect and can be interpreted as the percent of the total effect accounted for by the indirect effect [58, 59].”
BackgroundAnniko, M. K., Boersma, K., & Tillfors, M. (2017) · Nordic Psychology · doi:10.1080/19012276.2017.1323665 · Cited by 14
“The ratio of the indirect effect to the total effect (PM) was used for effect size as recommended by Wen and Fan (2015).”
BackgroundMethodRevisiting Work Engagement from a Moderated-Mediation Vantage Point
Tziner, A. E., Shkoler, O., & Zur, B.-E. B. (2019) · Journal of Work and Organizational Psychology · doi:10.5093/jwop2019a22 · Cited by 25
Janovsky, T., Clark, G. I., & Rock, A. J. (2019) · Australian Psychologist · doi:10.1111/ap.12390 · Cited by 18
Kazemi, A., & Corlin, T. E. (2021) · Journal of Health Organization and Management · doi:10.1108/jhom-10-2020-0393 · Cited by 15
Jin, S., & Miao, M. (2021) · Journal of Interpersonal Violence · doi:10.1177/08862605211063000 · Cited by 18
“Furthermore, according to Preacher and Kelley (2011) as well as Wen and Fan (2015), the ratio of the indirect effect to the total effect and the residual-based standardized gamma were estimated to represent the effect size for mediation effects, using the MBESS package (Kelley,”
MethodA time for creativity: How future-oriented schemas facilitate creativity
Koh, B., & Leung, A. K. ‐. (2019) · Journal of Experimental Social Psychology · doi:10.1016/j.jesp.2019.103816 · Cited by 16
Park, S., Greene, M. C., Melby, M. K., Fujiwara, T., & Surkan, P. J. (2019) · Journal of Interpersonal Violence · doi:10.1177/0886260519875561 · Cited by 14
“We adopted a calculation of effect sizes for mediation models and presented the ratio of indirect to total effects (Wen & Fan, 2015).”
MethodIronson, G. H., Fitch, C., Banerjee, N., Hylton, E., Ivardic, I., Safren, S. A., & O’Cleirigh, C. M. (2019) · Child Abuse & Neglect · doi:10.1016/j.chiabu.2019.104187 · Cited by 20
Gaume, J., Magill, M., Gmel, G. E., & Daeppen, J. (2021) · Journal of Consulting and Clinical Psychology · doi:10.1037/ccp0000666 · Cited by 14
Exploring the Role of Attitudinal Factors in Electric Vehicle Timeshare Rentals Adoption
Wang, S., Lin, Q., Zhou, Z., & Nie, C. (2022) · Applied Sciences · doi:10.3390/app13010012 · Cited by 14
Sorgdrager, F. J. H., Buning, J. W., Bos, E. H., van Beek, A. P., & Kema, I. P. (2018) · The Journal of Clinical Endocrinology & Metabolism · doi:10.1210/jc.2018-00582 · Cited by 15
Meehan, A. J., Maughan, B., & Barker, E. (2019) · Journal of Psychopathology and Behavioral Assessment · doi:10.1007/s10862-019-09756-9 · Cited by 14
“Effect sizes for indirect pathways were represented by P M, or the ratio of indirect effect to total effect, as recommended by Wen and Fan (2015) for multiple-mediation models with large samples (N > 500).”
BackgroundDynamic change meets mechanisms of change: Examining mediators in the latent change score framework
Hilley, C. D., & O’Rourke, H. P. (2022) · International Journal of Behavioral Development · doi:10.1177/01650254211064352 · Cited by 13
“…mediation effect sizes tend to perform poorly (Miočević et al., 2018) and κ2 (a ratio of the estimated mediated effect to a maximum possible mediated effect; Preacher & Kelley, 2011) has been shown to be non-monotonic (Wen & Fan, 2015) and has not been extended for use with longitudinal models.”
BackgroundGuglielmi, R., & Brekke, N. (2017) · Journal of Educational Psychology · doi:10.1037/edu0000238 · Cited by 13
Plasma tau predicts cerebral vulnerability in aging
Cantero, J. L., Atienza, M., Ramos‐Cejudo, J., Fossati, S., Wısnıewskı, T., & Osorio, R. S. (2020) · Aging · doi:10.18632/aging.104057 · Cited by 13
“com 21016 AGING effect to the total effect (PM) was used as a measure of the effect size [45].”
MethodChen, X. (2021) · The British Journal of Criminology · doi:10.1093/bjc/azab028 · Cited by 13
Galardo, L., & Trottier, M. (2022) · Construction Management and Economics · doi:10.1080/01446193.2022.2037674 · Cited by 13
“As suggested by Wen and Fan (2015), standardized coefficients for indirect effects are reported for each model.”
BackgroundMethodPredicting Academic Cheating with Triarchic Psychopathy and Cheating Attitudes
Golub, T. L., Petričević, E., & Sokić, K. (2019) · Journal of Academic Ethics · doi:10.1007/s10805-019-09338-0 · Cited by 18
Töpfer, N. F., & Wilz, G. (2020) · The Journal of Positive Psychology · doi:10.1080/17439760.2020.1716047 · Cited by 13
“However, many authors have argued against using this effect size measure as it is not constrained between 0 and 1 (and, thus, cannot be interpreted as a proportion) and is only meaningful when the indirect effect and the direct effect have the same sign (e.g. Hayes, 2018; Wen & Fan, 2015).”
BackgroundLeonardis, J. M., Lyons, D. A., Kidwell, K., Giladi, A. M., Lipps, D. B., & Momoh, A. O. (2020) · Plastic & Reconstructive Surgery · doi:10.1097/prs.0000000000007486 · Cited by 12
Alcañiz‐Colomer, J., Moya, M., & Valor‐Segura, I. (2022) · Current Psychology · doi:10.1007/s12144-022-03804-6 · Cited by 12
He, Y., Wang, R., Mo, L., & Feng, L. (2024) · Journal of Nursing Management · doi:10.1155/2024/6774939 · Cited by 16
Walters, G. D. (2018) · Criminal Justice Review · doi:10.1177/0734016817753266 · Cited by 12
Yeh, V., Mayberry, L., Bachmann, J., Wallston, K., Roumie, C., Muñoz, D., & Kripalani, S. (2018) · Journal of general internal medicine · doi:10.1007/s11606-018-4767-1 · Cited by 10
Pardo, J. V., Nyabwari, S. M., Lee, J. T., & Initiative, A. D. N. (2020) · Cerebral Cortex Communications · doi:10.1093/texcom/tgaa020 · Cited by 13
“, ratio of indirect effect to total effect) was used as a measure of the effect size of the mediation (Wen and Fan 2015).”
MethodWord Meaning Contributes to Free Recall Performance in Supraspan Verbal List-Learning Tests
Cremona, S., Jobard, G., Zago, L., & Mellet, E. (2020) · Frontiers in Psychology · doi:10.3389/fpsyg.2020.02043 · Cited by 13
“Since the first method of calculation was criticized (Wen and Fan, 2015), here, κ2 was calculated according to Talloen’s proposition (Talloen W. Effect size measures for mediation models: a critical evaluation of κ2.”
MethodBartek, M. E., Zainal, N. H., & Newman, M. G. (2021) · Journal of Affective Disorders · doi:10.1016/j.jad.2021.04.091 · Cited by 12
“The mediation effect size was the ratio of the indirect effect (a*b) to the total effect, c = a*b + c’, expressed as percentage of variance of the T2 marital instability mediator accounted for as a mediator of the T1 parental affection–T3 MDD relation (Preacher and Kelley, 2011; Wen and Fan, 2015).”
BackgroundBaranik, L. E., Zhu, Y., Wang, M., & Zhuang, W. (2021) · Journal of Managerial Psychology · doi:10.1108/jmp-05-2020-0279 · Cited by 15
Walters, G. D. (2017) · Emerging Adulthood · doi:10.1177/2167696817739019 · Cited by 13
“The effect size measures used to assess indirect effects, however, are hampered by several rather serious flaws to include nonindependence and lack of monotonicity (Preacher & Kelley, 2011; Walters, 2018-a; Wen & Fan, 2015).”
BackgroundBraitman, A. L., & Lau‐Barraco, C. (2019) · Alcoholism Clinical and Experimental Research · doi:10.1111/acer.14248 · Cited by 12
“The size of this effect may be best expressed as the ratio of the indirect effect to the total effect, given that the indirect and direct effects are of the same direction (Wen & Fan, 2015).”
BackgroundCiber-rumor y síntomas internalizantes en la adolescencia: efecto mediador de la resiliencia
Bravo, A., Alcaide, F. C., Ruiz, R. O., & Romera, E. M. (2022) · Psychology Society & Education · doi:10.21071/psye.v14i1.14168 · Cited by 17
Metadata
- Authors
- Wen, Z., & Fan, X.
- Affiliations
- South China Normal University (CN)
- University of Macau (MO)
- Venue
- Psychological Methods
- Published
- 2015
- Volume
- 20
- Issue
- 2
- Pages
- 193-203
- ISSN
- 1082-989X (ISSN-L)
- 1939-1463
- OpenAlex
- W2155202060
- Cited by
- 350
- References
- 23
- Citations by year
- 2026: 20 · 2025: 23 · 2024: 28 · 2023: 31 · 2022: 43 · 2021: 41 · 2020: 30 · 2019: 47 · 2018: 33 · 2017: 38 · 2016: 14 · 2015: 2
- FWCI
- 25.81
- Type
- journal article
- Language
- en
- Update notices
- correction (2015-05-11)
- Open access
- closed
- Locations
- Psychological Methods (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (31271116 and 31400909)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Social Sciences › Decision Sciences › Management Science and Operations Research › Psychometric Methodologies and Testing
- Keywords
- indirect effects, rank preservation, monotonicity, multiple mediation, effect size measures, mediation analysis
- MeSH terms
- Behavioral Sciences, Humans, Statistics as Topic, Models, Statistical, Confidence Intervals
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