I am looking for some support with understanding the results of a hierarchical regression analysis.

 

Background: I am testing a model which suggests that perspective taking, empathic concern and psychological flexibility predict DV-1. The hypothesis is therefore that all three predictors together (perspective taking, empathic concern and psychological flexibility) will be the best predictor of the DV-1.

 

Initially, correlational analyses were used to test hypotheses about the relationships of the variables and DVs in the study. Hierarchical analyses were only calculated when there were multiple correlations between variables and the DVs.  

 

For DV-1, a demographic variable that was significantly correlated with the DV was included in the first step. Then each step added one predictor variable, in line with the order hypothesised in the model being tested. Each step of the hierarchical regression accounted for an increase in the variance of the DV. Each step was statistically significant and the overall model was also significant. I am confused about the significance of the co-efficients for the significant model, however. Three of the four predictors were significant. Does this mean that only the three predictors (two of which are in the model and one was the demographic variable) are relevant to the model? So in this case, that it is only two of the three predictors that predict the DV, therefore the model is not supported? I am trying to think about the clinical implications of this so if only two of the predictors are significant for the model, is it only these two that should be targeted in an intervention?

 

I think the model being significant but only some of the predictors within the model being significant is what has confused me.

 

Thank you

 

 

---

To unsubscribe from the PSYCH-POSTGRADS list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=PSYCH-POSTGRADS&A=1