Rewrite paragraph

Anderson & Bushman (2001) state a correlation of r= .19 for aggressive behaviors correlating to video game playing. This was for 13 non-experimental trials of this comprehensive study. To add weight and validation to their correlation value, Anderson et al., (2001) added in an experimental study that produced a result of “r = .18, 95% confidence interval (.13, .24)” for 21 experimental tests.

Because of the closeness in r values, there is the illusion the experimental section justifies the non-experimental trials, so the researchers could say: “proportion of variance in Y that can be predicted from X.” (Warner 2013) However, this is not the case. A value of r= .10 is considered small for effect size in the study. A medium r value is .3. With both the experimental and non-experimental results closer to the smaller effect size, this signifies both portions of the study, despite the high CI for results, there is a correlation, but it is weak.

Further subdivision into three subgroups for the non-experimental trials generated higher r values for time spent taking part in video games in general, time spent enjoying violent video games, and for a choice of video =d experimental groups being closely related. Their close correlation confirms overall the playing video games brings about aggressive behaviors, is weak as you cannot tell which if the three sub-groups they were testing for actually produced the aggression.

References:

Anderson, C. A., & Bushman, B. J. (2001). Effects of violent video games on aggressive

behavior, aggressive cognition, aggressive affect, physiological arousal, and prosocial

behavior: A meta-analytic review of the scientific literature. Psychological Science,

12(5), 353–359.

Warner, R. M. (2013). Applied Statistics: From Bivariate through Multivariate Techniques.

Thousand Oaks, CA: SAGE Publications.