control roup

Hi YuchengLiang, I do not think that we need a control group in our study, unless we wanted to manipulate some sort of variable in an experimental group and compare it with a control group. I think that since we do not have a control group, we simply cannot propose that some of the relationships that we found were caused by one another; rather, we can only say they are correlated. I am not sure if others have mentioned a control group in the sense that we should have a 'faking good' profile group in order to reduce the social desirability bias.

If we were to have a control group, I think that that would further our study in the sense that we could look into the relationships between two specific variables, for example people's choice in occupation and gender and see which influences which. Let me know what you think!

PhoebeDychinco (talk)18:11, 4 August 2013

Hi PhoebeDychinco, that is what I am thinking as well. Initially, I misunderstood the limitation someone had mentioned, which is in our study, we lack of a control group. I completely agree with you, in order to find some causality between variables such as occupation and gender, experiment need to be designed. Also in designing a comprehensive research, the combination of LOST data is best persuasive.

YuchengLiang (talk)18:45, 4 August 2013