We generally use a statistcal technique called regression analysis.
This is where we have a dependent variable (in our study it is depressive or anxious symptom severity) and we test the strength of correlation with “predictor” variables, such as phone use, exercise, diet etc
This tells us
a) is there a correlation between the dependent variable and a predictor (e.g. is depression associated with mobile phone use?) and
b) how much more likely am I to be depressed if I use my phone more? (this is the size of the effect)
However, this is an average model and can’t predict what will happen for every person
Comments