The level of measurement for the data set is interval. Each of the faces were ones that participants had never seen before, establishing equal intervals of recalling them. Although there were factors such as attractiveness, race or age that were unique to each of the photographs that could’ve disrupted the equal intervals, the original experiment used interval measurement for their data set so I chose to also use interval measurement. The main measure of central tendency was mean. The median was …show more content…
During some of the data collection sessions, there were noises that came as students from the hallway walked past us. This could’ve distracted the participant, thwarting his/her ability to concentrate on the experiment. We tried to control researcher bias by creating scripts for each part of the experiment. However, because it was independent measures, the way in which the scripts were read may have differed for each participant. In addition, I noticed demand characteristics when participants were asked to respond with “yes” or “no” to indicate if they remembered the photos. Participants were much more confident in responding affirmatively with “yes” than “no”. A strength of the experiment was that participant variability was thoroughly controlled because of the independent measures design. Ecological validity was very low because of the controlled setting of the experiment. In a real life setting, variables such as attitude, dress or facial expressions could affect the ability to recall faces besides gaze direction. The population validity is limited to the sample age group of high school juniors and