I demonstrate how to perform and interpret a hierarchical multiple regression in SPSS. I pay particular attention to the different blocks associated with a hierarchical multiple regression, as well as R squared change and F change.
Just a general comment here ... Your videos are very helpful and straight to the point. I believe you would have a fulfilling career in teaching, if you are not already in that.
I saw many HMR in the research papers contain 3 models: model 1- a main IV; model 2-added some more IVs and model 3- their interactions. If my research doesn't want to investigate the main effects of IV added in the model 2, I just wanna know if there is any moderating effect on the relationship in model 1, can I just combine model 2 and 3. i.e.: model 1: a main IV, model 2- added moderators and the interaction between the main IV and moderators Thanks !!!
Hi - Thanks for the video. It really makes it much more easier to understand... one question though is if I want to keep my demographic variables constant (hence first block) can I also enter my nominal variable & oridinal variables there or only scale variables? F.e. Gender is allowed to be in there? Education? Many many thanks!!
hi there, thanks very much for your video, one question : can i use hierarchical multiple regression to analyse the moderating effect of a variable(A) on a relationship between B and C
For example, if you have 7 blocks interpreting in to 7 models, how do you determine the model to use when either accepting or rejecting the hypothesis?
how would you write the model as a econometric equation? i mean, could you please write the speciffication of the level 1 and 2 equation? pleeease, that way i'd understand everything. Thanks!!
is it implied that the second level is nested within the first level? I'm working with data that has subjects in families in different locations and wish to do a hierarchical multiple regression accounting for this nesting using SPSS and eventually R. So my main concern is if the method in this video is appropriate for nested variables? Also is there a way to obtain the general equation for the fitted model?
These data are not hierarchical - as burgerkinghorn pointed out, this is just using incremental blocking. For hierarchical data (and modeling), some of the data must be grouped at another level, e.g. students grouped by classrooms.
Based on your wide survey of the literature, you have generated enough confidence to state publicly that this is not hierarchical multiple regression, but, instead, "just using incremental blocking" regression. I would encourage you to google scholar "hierarchical multiple regression" and peruse the 1000s of papers that have used hierarchical multiple regression in the same manner demonstrated in this video. You might even take the time to read the very first paper that shows up in the search by Petrocelli (2003). The context in which you are describing "hierarchical data" is more typically referred to as multilevel modeling, which is different to hierarchical multiple regression. Almost certainly, however, I suspect a handful of less than knowledgeable people have used the term hierarchical regression in the context of multiple level modeling and the discipline of statistics is the worse for it.