Mediation analysis using regression

This shows how to get the necessary coefficients for the components of a simple regression model using the regression techniques avaiable in SPSS.

[@arnidajahya325]

thank God finally I found a video with a very clear explanation for a non-statistician like me. keep it up!

[@m.c.4458]

thank you, in 11 minutes you explained this best than many :)

[@piepo5002]

Awesome that you took the time for us to learn this method. Thank you :)

[@MR-yi9us]

Very helpful! Thank you so much! Hoping to see more videos like this!

[@yongtaegpark8164]

Thank you for the clear explanation!

[@joannemamo8177]

Thanks so much for explaining this, it was very helpful :)

[@kofiowususarfo1006]

Thanks, for your perfect explanation

[@freddyfrancoisateba4419]

Amazing course

[@meovy35]

Thank you Prof

[@yuliakryazhevskikh4065]

Thank you for the video! Could you tell please how to explain the data from the table? How to tell if there is a mediation?

[@anandank4144]

Thank you very much sir

[@ahmadkhatiry4836]

Thanks for your video. How can I report the results on a paper?

[@kangma4462]

Hi thanks for sharing this video I wonder whether does this methods apply to pre and post measurements?

[@karlosrato7012]

thks

[@palakmalik93]

What about if we have more than 1 mediator? Do we have to carry it out separately?

[@cerjc1429]

What post-analyses should be used for a mediation analysis?

[@thierrypenverne2010]

Thanks for this good explanation. Do you always to use the standardized (beta) coefficients or can you also use the unstandardized coefficients (b)?

[@power65472]

Hi Thierry, you can use either so long as you are consistent. I prefer standardised since you can compare the effects of different predictors. But if the raw units of measure make sense to your reader the unstandardised can be really useful. If one unit of change in the IV and one unit of change in the DV make sense (one year extra education is associated with how many extra dollars of income) then consider using unstandardised.

[@sq5694]

Hi, thanks for this video. Do you happen to know if Gpower can be used to calculate estimated sample size for a mediation analysis?

[@power65472]

Hi, I'm not really expert in G*Power - even though I'm a stats type and my name is Garry Power. I've used it a bit and find it a bit annoying (and not just that they stole my name). You can certainly find the required sample to test a single coefficient in a multiple regression - and that's probably your best bet. The indirect effect is the product of two coefficients so will need more power than for one, but it's probably as good as you'll get.

[@mohdnotfinotfi2637]

Sir , hopely you so well and very good day

[@mohdnotfinotfi2637]

Prof. me I know your email adress ?

[@karenb8702]

Hi - thank you for this - the coefficient for c' was -.101, however its significance was .127 according to the table, which is higher than p = =.05, can you still consider this a valid beta?

[@jest120]

Nope. Absolutely no. In this case you should write n.s. (non-significant)

[@ChanceShane4]

How can I tell if there’s a significance??

[@Brokenlikefour]

Look for Sig. in the Coefficients table, it is the same as p-value and needs to be < .05 to be significant

[@kavibaarathyvasanthakumar4675]

Hi there, may i know how u get 0.1% and 2.64% for path b and c

[@andrewjason5685]

Thank you for the detailed explanation, but what if I'm using the theory of reasoned action where I have a mediator variable but the path of the framework does not follow the one in your video?

[@power65472]

Hi Andrew, The mediation I described applies only to the most simple models (one IV, one mediator, and one DV). For a more complex model you might need to consider path analysis, or if you have the data for it, structural equation modelling. For multiple mediators, or moderated mediation, but just one IV and one DV, Process can handle it. I only did videos that fit into a course I was teaching a few years back, and we kept to simple models so that's all I've got. Good luck with your analysis.

[@andrewjason5685]

@@power65472 his thanks for your reply, in the theory I'm using there are 2 IVs, 1 mediator and 1 DV, can a regression handle this?

[@power65472]

@@andrewjason5685 Hi Andrew, Tricky to have 2 IVs. Mostly because Process can't handle 2 IVs - and Process is the easiest and best way to estimate and test the indirect effect. Process can take covariates, so that's probably your best option. The covariate is partialled out (it's contribution is eliminated) so you are down to what would happen if all variance contributed by the covariate is removed. I haven't used these much. Best source for this is Hayes's book on Mediation and Moderation using process.

[@Nbl.369]

What if there is a moderator too as in model.7 process There would be another prediction. What That could be probably?

[@Sarika897]

Thank you very much. My lecturer's powerpoints are awful

[@rachelsummerfield]

lol

[@abdallah_ibrahim95]

thank you but how I can report the result

[@dr.shaminisrivastava4213]

How can I predict the meditation model if the value of C' is greater than c

[@power65472]

Hi Shamini, c' can be greater than c if there is some kind of suppression going on. Simplest one is where path a*b is the opposite direction of association compared to path c'. Example I use is student anxiety. High anxiety reduces exam performance, but at the same time, anxiety can increase time spent studying and therefore lead to improved exam performance. If high anxiety leads to increased study which then leads to better exam performance, you have a mediated association. If some anxiety is not associated with more study, then there might also be an independent direct path (path c') that leads to a decrease in exam performance. Path c is the combination of the two and is going to be weaker than either path c' or path a*b. In fact path c might be no association at all (which is why we don't use Barron & Kenny's approach any more). I hope that helps, Garry

[@dr.shaminisrivastava4213]

@@power65472 thank you..the example which I have given is exactly the same as I found in my data. Then how can I predict this c is also significant. How will I write it in my result

[@dr.shaminisrivastava4213]

Please explain it

[@dr.shaminisrivastava4213]

Sir please help me in explaining my result

[@nina5264]

path c: is univariate regression (DV from IV). Why did you say bivariate?

[@power65472]

Hi Hanieh. The association is between two variables (IV and DV) so it is called a bivariate analysis.