The article “Super Bowls: Serving Bowl Size and Food Consumption” (Journal of the American Medical Association [ 2005]: 1727– 1728) describes an experiment investigating how the size of serving bowls influences the amount a per-son eats. In this experiment, graduate students at a university were recruited to attend a Super Bowl party. The paper states that as the students arrived, they were “led in an alternating order to 1 of 2 identical buffet tables on opposite sides of an adjoining room. The tables had identical amounts of snacks, such as nuts, pretzels, and chips. All of the snacks contained approximately the same number of calories per gram. On one of the tables the snacks were set out in large serving bowls and on the second table the snacks were set out in smaller serving bowls. The students were given a plate and invited to serve themselves before going to another room to watch the game. When they arrived at the game room, their plates were weighed and the number of calories in the food on the plate was estimated.” The researchers concluded that serving bowl size does make a difference, with those using large serving bowls tending to take more food.
a. Do you think that the alternate assignment to the experimental groups (large serving bowls, small serving bowls) based on arrival time is “close enough” to random assignment? That is, do you think it would tend to create comparable experimental groups?
b. In this study, the research assistant who weighed the plates and estimated the calorie content of the food on the plate was blinded as to which experimental group the plate belonged to and was also blinded as to the purpose of the experiment. Why do you think the researchers chose to incorporate this type of blinding?