摘要：When researchers fail to control for confounding factors, the causes of behavior can be more apparent than real, even in experimental research. The current study replicates an experiment by Weinstein, Przybylski, and Ryan (2009) with the goal of demonstrating that their main finding could have resulted from differences in people's prosocial propensity. In their research, they found their hypothesized interaction effect: depending on the extent of immersion, participants presented with images of nature were found to be more prosocial in both their actions and in their declarations. Our sample of 175 adults (M age=29.7 yr., SD=11.7; 97 men, 78 women) was approached personally, randomly assigned to viewing either urban or nature images, and instructed to immerse themselves in the respective images. Using two formally distinct measures of participants' prosocial propensity (i.e., before and after the intervention), the hypothesis that individual differences in people's prosocial propensity can bias conclusions about the origins of prosocial behavior in experimental research was supported. To avoid invalid conclusions, the prosocial propensity levels of research participants should be controlled for.
