In SPSS standardized regression coefficients are called B , while ordinary ones are called beta. the difference is that in the standardized case the means are all 0s and the SDs are all 1 on the standardized variables ie now the units on the x's are all the same and the B's can be directly compared, but for unstandardized variables the betas can't be. In other words the units have been changed in standardization.

Best, D. Booth PS usually we standardize when we want all the units to be the same.

David Eugene Booth you got a typo :). Unstandardized coefficients are B's and standardized are beta.

Just as a note, it is a bad practice, to NOT write beta in words but to use the greek symbol as this conflicts with the rule in statistics to use greek symbols as unknown population parameters.

Yew Gen Ng With regard to standardized coefficients, we all do that but note that their is a huge literature who criticizes that, e.g.,

King, G. G. (1986). How not to lie with statistics: Avoiding common mistakes in quantitative political science. American Journal of Political Science, 30(3), 666-687. doi:10.2307/2111095

Greenland, S., Schlesselman, J. J., & Criqui, M. H. (1986). The fallacy of employing standardized regression coefficients and correlations as measures of effect. American Journal of Epidemiology, 123(2), 203-208.

Kim, J. O. J.-O., & Mueller, C. W. (1976). Standardized and unstandardized coefficients in causal analysis: An expository note. Sociological Methods & Research, 4(4), 423-438. doi:10.1177/004912417600400402

Greenland, S., Maclure, M., Schlessman, J.J., Poole, C., & Morgenstern, H. (1991). Standardized Regression Coefficients: A Further Critique and Review of Some Alternatives. Epidemiology, 2(5). 387-392.

With regard to indirect effects, there are some proposals of alternative (or at least additional measures). I personally find the percentage of the total effect being mediated quite useful.

de Heus, P. (2012). R squared effect-size measures and overlap between direct and indirect effect in mediation analysis. Behav Res Methods, 44(1), 213-221. doi:10.3758/s13428-011-0141-5

Fairchild, A. J., MacKinnon, D. P., Taborga, M. P., & Taylor, A. B. (2009). R 2 effect-size measures for mediation analysis. Behavior Research Methods, 41(2), 486-498.

Lachowicz, M. J., Preacher, K. J., & Kelley, K. (2018). A novel measure of effect size for mediation analysis. Psychological Methods, 23(2), 244.

Best,

Holger

@Holger thanks for correcting me I am 40 years away from SPSS and should have looked it up not trusted remembering from 40 years ago. Mea culpa Mea Maxima Culpa David

David Eugene Booth 40 years away from SPSS. That is quite a life goal :D. I am striving for that. I am at 12 now :)

Best,

Holger

I was kind of confused initially but Sir @Michael R. Frone seems to have resolved my problem. My metrices are about well-being, self-efficacy all that, I think I shall go for the unstandardized one. Hopefully, I am able to explain to my supervisor and observer. Thank you all for the advices. ^^

Yew Gen Ng There are lot of conflicting stands in either to use standardized or unstandardized estimates in the field of measurements. However, evidences supported the use of unstandardized estimates consistently, especially when concluding on causal relationships. Similarly, standardized coefficients has been utilized because of some certain advantages and wide acceptance. In a nutshell you just need to read so that you can be able to defend your usage of standardized or unstandardized coefficients. Am happy some experts provides some references here, try to read more and relate

Wish you al the best

Ado ABDU Bichi . Thanks sir.