A key reference on this topic is Baron, R. M., & Kenny, D. A. (1986). The moderator-mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of Personality and Social Psychology, 51, 1173-1182.

This site is clear

http://www.uni.edu/butlera/courses/org/modmed/moderator_mediator.htm

as actually is Wikpaedia

http://en.wikipedia.org/wiki/Mediation_%28statistics%29

which appears quite well up to date.

Hi Amer,

Mediator variable is the middle variable / "middleman" between an independent variable (IV) and a dependent variable (DV).  Objective of the mediator variable is to explain the relationship between IV & DV e.g. IV is not directly influencing DV but rather IV is indirectly influencing DV through mediator variable.  Pictorially, Independent variable --> Mediator variable --> Dependent variable. For example, salary (IV) is positively influencing education (mediator variable) and then education is positively influencing health-screening expenses (DV).  When the effect of education is removed, the relationship between salary and health-screening disappears.

Moderator variable is a third party variable that modify the relationship between an independent variable (IV) and a dependent variable (DV).  Objective of the moderator variable is to measure the strength of the relationship between the IV & DV.  Pictorially, moderator variable's arrow line is pointing to the mid point of the arrow-lined relationship between independent variable --> dependent variable.  For example, if age is a moderator variable between salary (IV) and health-screening expenses (DV), then relationship between salary & health-screening can be stronger for older men and less strong for younger men.

Regards,

Fung

So, mediators are the variables in between the effect of IV/DV (although not necessary completely) and moderators are influencing the relationship between the IV/DV - for example determining the strength the influence the IV has on de DV. 

In the theory you should be able to determine where your variable of interest is in your overall model. Modelling the expected relations between your variables  >> based on theory

I would very strongly recommend this book

Andrew Hayes Introduction to Mediation, Moderation, and Conditional Process Analysis: A Regression-Based Approach

see http://www.afhayes.com/introduction-to-mediation-moderation-and-conditional-process-analysis.html

and the SPSS, MPLUS  and SAS macros that go with it

http://www.processmacro.org/

Baron & Kenny (1986) highlighted the importance of not using the terms moderator and mediator interchangeably.

Baron & Kenny (1986) wrote:

“The moderator function of third variables, which partitions a focal independent variable into subgroups that establish its domains of maximal effectiveness in regard to a given dependent variable. The mediator function of a third variable, which represents the generative mechanism through which the focal independent variable is able to influence the dependent variable of interest.”

Moderating Variable- moderator is a variable which will cancel the relationship with two variables. Moderator is a variable which will refuse the degree of relationship between two variables. Moderator can be totally canceled the relationship between two variables.

Moderating - changing

Eg: You feel sleep in the class after having a heavy lunch. So there is a relationship. But assume you don’t feel sleep in the class after having a huge lunch. The answer is the moderator, may be the interesting nature of the lecturer or exam fear.

Intervening variable alternatively called mediating variable

Intervening variable – Assume training and job performance, the relationship is positive. Greater the job training better the job performance. How does the training increase the job performance? If you have an answer, then the answer is the intervening variable. Learning is the acquisition of new knowledge and attitude. So training will result in learning which will result in job performance.

For more details please refer the articles given below.

References

Frazier, P.A., Tix, A.P. and Barron, K.E., 2004. Testing moderator and mediator effects in counseling psychology research. Journal of counseling psychology, 51(1), p.115.

Baron, R.M. and Kenny, D.A., 1986. The moderator–mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of personality and social psychology, 51(6), p.1173.

Thank you all for sharing insightful knowledge about mediating and moderating variables. Really helpful.

Another way to think about this issue is that a moderator variable is one that influences the strength of a relationship between two other variables, and a mediator variable is one that explains the relationship between the two other variables. As an example, let's consider the relation between social class (SES) and frequency of breast self-exams (BSE). Age might be a moderator variable, in that the relation between SES and BSE could be stronger for older women and less strong or nonexistent for younger women. Education might be a mediator variable in that it explains why there is a relation between SES and BSE. When you remove the effect of education, the relation between SES and BSE disappears.

http://psych.wisc.edu/henriques/mediator.html

I would like recommend you to read Baron and Kenny (1986).

In simple way... we can distinguish the moderator variabel if ot will make stronger the effect pr relation IV to DV. Example age will be moderating relation stress with endurance, for the younger stress will freater effect to endurance and not for the older.

Mean while mediating will explain how the relation IV and DV through mediator variable. If there is no mediator variable there will be no relation IV and DV

Does the mediating need to design questions in the questionnaire?

Thanks Dr. Han Ping Fung,

In the most easiest way you have explained the difference between the both variables, this will help us to understand properly.

thank you Dr Han!

YES..ITS EASY TO UNDERSTAND....THANK YOU

http://psych.wisc.edu/henriques/mediator.html

the answers were very informative and interesting too. one thing i wanted to add here which is that how do we researchers know from our study for instance through our literature review that either mediator or moderator will be suitable for our own theoretical model. Answer to this question will be highly appreciated.

thank you

Many individuals have responded your answers. Another way to distinguish both is their relationship with IV and DV.

In both case, IV and DV have direct relationship but when you introduce MeV or MoV as third variable, other relationships also expected.

For MeV, there exist relationship with IV as well as DV but for MoV, no relationship exists with IV. If theory support this relationship, then it might be MeV but not MoV. If IV and DV has no direct relationship but third variable is linked with IV and DV then, third variable will be intervening variable but not MeV.

There is a issue that i found confusing when people talk about mediator (M). As Mr. Han Ping Fung said, when you remove M, the relationship between IV and DV disappears.

But in my opinion, for mediation analysis, when you add M, the relation between initial IV and DV should be disappeared/ insignificant (fully mediation) or at least weaken because mediator is the main reason causing the relation between IV and DV.

The way of testing mediation or moderation is the same at the end of the day.

Thanks to Dr Dat Quoc Trinh..meaningful argument

A Moderating Variable (MV) is one, which has a significant contingent effect on the independent variable-dependent variable relationship. It modifies the expected relationship between the IV and DV. If the expected relationship does not become true due to the presence of a third variable, that third variable will be the MV. For example, training of production workers will result in higher productivity. Hence there is a positive relationship between two variables. But this positive relationship becomes untrue for trainees who have no motivation to learn and becomes true only for trainees who have motivation to learn. Thus, motivation to learn becomes the MD. Absence of motivation to learn variable cancels the expected positive relationship between the two variables.

An Intervening Variable has a time dimension (a temporal quality) to the IV in a situation. It is the variable that surfaces at a time t2 as a function of the IV. It helps to explain the relationship between the IV and the DV. First, independent variable activates (time 1), then intervening variable activates (time 2). Then dependent variable will activate (time 3). For example, due to more training employees’ competence will increase. Due to the increased competence, employee productivity will get increased. Employees’ competence will explain how more training affects employee productivity. Here employees’ competence will be the intervening variable.

With great answers above, I just want to add a little. In very simple words:

Mediation explains "HOW" one variable is related with an output and this "how" is supported necessarily with Theoretical Logic (Theory) relevant to the field of study e.g., in Motivational Theories; Psychological or Social Motivation intervenes between many contextual and individual factors and Employee Outcomes.

Moderation, on the other hand, explains "For Whom" condition in a theoretically backed relationship. For example, if Self-efficacy is a moderator in a study, the researcher, according to the theoretical logic, would look for the change in the relationship for those who are high in self-efficacy or low in self-efficacy.

Dear Mr. Muhammad, your answer is interesting. Let me add another point. Assume that a student who had a heavy lunch went on sleeping in the class where a lecture was being carried out. How did heavy lunch make the student sleepy in the class room? It is because of a certain biological reaction (the digestive process) in the body. This is the mediating or intervening variable. Hence mediating variable is concerned with 'How'.

Assume that the same student who had the same heavy lunch did not go on sleeping (did not feel sleepy) in the next class (next day). Why? It is because of the interesting lecture. Here the interesting lecture is the moderator. Hence the moderating variable is concerned with 'Why".

Dear Prof. Opatha thanks for beautiful explanation of moderation as WHY. However, where "why" explains moderation well, I think "For Whom" also explains moderation in more simple way.

For even in the example provided above i.e., heavy lunch might cause sleepiness in students through the natural digestive process, however only for those who (condition or moderation) feel the lecture is not interesting and not for those who take the lecture interesting.

I found the "How" & "For Whom" logic and understanding form the reference given below:

MacKinnon, D. P. (2011). Integrating mediators and moderators in research design. Research on Social Work Practice, 21(6), 675-681.

Best Regards

Dear Muhammad,

Yes I agree with you. Thank for your reference.

Best wishes!

syukran thanks. terimakasih

I had read some information regarding the mediating and moderating research. Is it OK if I say

If the previous research confirmed that the relationship between iv and dv was significant, you should look on mediating variable in order to strengthen the relationship.

However, when the relationship was not confirmed by the previous researches, you should look on moderating variable. tq

Dear Shahri Abu Seman you missed the word "Consistent or Inconsistent" in the explanation; if the relationship between 2 variables is Consistently Significant (in empirical sense) then can use Mediation and if the relationship is Inconsistent then use Moderator. This explanation fits well in Baron and Kenny's (1986) seminal paper on moderation and mediation.

However, time has changed and so researchers need to change as well. With the phenomenal advancements in Research Design and Statistical Analysis tools, it is now researchers' duty to build a solid foundation of their basic research (Quantitative / Positivist) on well-grounded theories while conceptualizing mediation and/or moderation in their studies.

So, In my personal viewpoint, conceptualizing mediation or moderation merely on the basis of consistency (inconsistency) in statistical results is a least effective way to produce scientific knowledge for the practical implications in the real business world.

Please have a look on the articles given below to better understand the topic.

Best Regards

Hayes, A. F. (2009). Beyond Baron and Kenny: Statistical mediation analysis in the new millennium. Communication monographs, 76(4), 408-420.

Zhao, X., Lynch, J. G., & Chen, Q. (2010). Reconsidering Baron and Kenny: Myths and truths about mediation analysis. Journal of consumer research, 37(2), 197-206.

MacKinnon, D. P. (2011). Integrating mediators and moderators in research design. Research on Social Work Practice, 21(6), 675-681.

Memon, M. A., Cheah, J.-H., Ramayah, T., Ting, H., & Chuah, F. (2018). Mediation Analysis Issues and Recommendations. Journal of Applied Structural Equation Modeling, 2(1), i-ix.

Tq Dr Muhammad. Thank for your reference.

Thank you everyone for for the wonderful explanation. God blessed everyone

Thank you all. I am now informed. God bless

thanks for vary valuable descriptions.

Wow! thanks as I am also learning. Both intervening and moderator makes the relationship more complex but adds value to the link between IV and DV.

I like the How? and Why? as the standard explanation of explain relationship vs influencing strength is somewhat confusing to a green horn like me. :D

all of these explanations are very useful.

thank you all learned people here

i have tabulated my mediator and moderator lists from past researchers. I have also total up the frequency for each mediator and moderator. My question is, is my action correct by determining the mediator or moderator im gonna apply in my study using the variable that had very least studied in past research?

"A good or bad "mother in law" can moderate (weaken or strengthen) the relationship of husband and wife, whereas, the children can mediate the relationship of husband and wife" My basic understanding on moderator & mediator..

Old question and answer but still helpful. Thank you all

The mediator: when the effect of independent variable on the dependent variables channels through another variable, we call it the mediator effect. Example: when we consider the effect of gender on income, we see that the females are usually are paid less. Here we can have one mediator: academic field. As we know, the women are more interested social science rather than engineering fields which usually are highly paid. So here, academic field can be a mediator between the effect of gender on income, so that we say the effect of gender on income channels through academic field. The moderator variable is a variable that partly affects the link between independent and dependent variable so that we say the effect of independent on dependent is partly moderated by the moderator. The effect of gender on income can be moderated by family status. So that the individuals from higher social origins can be employed in the professions with higher level of payments so that we expect that the income of females who belong to rich families be higher than those belonging to poor families. Here, the social origin can be a moderator between gender and income.

Good luck

There can be two types of moderations such as categorical moderation and continuous moderation. Categorical moderations may act as multi-group analysis whilst continuous moderation may intervene as an independent variable between another independent variable and a dependent variable.

A moderator is a pre-existing variable that influences the relationship you are studying. It explains how some pre-existing characteristic influences the strength or direction of the relationship you're observering.

A mediator is a variable that changes as a result of your experiment. It explains WHY the change in your idenpendent variable produces a change in your dependent variable.

The key difference: a moderator does not change as a result of your experiment, whereas a mediator changes when your independent variable changes.

Moderator examples from social science: age, gender, personality traits, level of education, political beliefs.

Mediator examples: anger, fear, perceived social impact.

Thanks Mr hand ping fung. You are great teacher

A mediating variable explains the relation between the independent (predictor) and the dependent (criterion) variable. ... A moderator is a variable that affects the strength of the relation between the predictor and criterion variable. Moderators specify when a relation will hold

Say for instance, "Teacher hiring practices and educational efficiency".

Then the Independent variable is Teacher hiring practices and

the Dependent variable will be Educational efficiency.

The moderating variable thus, could be job satisfaction or the skills acquired by the teacher.

https://www.psychologyinaction.org/psychology-in-action-1/2015/02/06/mediating-and-moderating-variables-explained

Mediating and Moderating Variables Explained by Tawny Tsang February 6, 2015

agree with Muhammad Naveed

Hello i am studying my masters and lost between mediator and moderator, my topic the effect of organizational climate and employee engagement on employee performance can i consider organizational climate as mediator or moderator can you please help me:)

Olá Maria Luiza Felix Pessoa tudo bem? Teoricamente (conceitualmente) uma variável mediadora se manifesta quando não há como separar a relação teórica/prática desta, com outras duas variáveis, por exemplo: Para haver um dispêndio energético durante a transição da caminhada para a corrida em sujeitos não treinados, necessariamente (fisiologicamente) a frequência cardíaca irá aumentar proporcionalmente ao dispêndio energético. Logo, podemos compreender que a relação entre a atividade física (corrida) com o dispêndio energético é mediada pelo aumento ou redução da frequência cardíaca. Já um fator/variável moderadora é um aspecto o qual pode ou não interferir na relação entre duas variáveis, no entanto, isso não gera dependência para a relação acontecer sempre. Por exemplo: a idade cronológica pode afetar a relação entre a percepção de bem-estar com o nível de atividade física. No entanto, se retirarmos a idade da relação ou adicionarmos ela, em tese, o bem-estar ainda poderá se associar com a atividade física. Mediador (relação muito bem estabelecidade de dependencia entre 3 variaveis). Moderador (é uma terceira variável bem mais hipotética). Espero ter ajudado. Um abraço.

Many aspects of both relationship have already been mentioned in above comments. In in a nutshell, the mediation relationship is always causal, but moderating relationship is not.

While understanding the distinction between mediator and moderator variables, what word should we use to encompass both in order to refer to variables (in general) that "mediate" something? Would it be fine to say mediating variables as an all-encompassing term? My problem is mediating might might lead people to associate this with mediator variables only (and not mediator and moderator)