A study is designed to test the effect of light level on exam performance of students. The researcher believes that light levels might have different effects on males and females, so wants to make sure both arc equally represented in each treatment. The treatments are fluorescent overhead lighting, yellow overhead lighting, no overhead lighting (only desk lamps).

(a) What is the response variable?

(b) What is the explanatory variable? What arc its levels?

(c) What is the blocking variable? What arc its levels?

a) In this study, the response variable is the result of the student's exams, the performance of students itself. The response variable is the main focus of the question you have done in a statistical study. In this case, you want to know how lights affect students performance. The main focus is on the student's exam performance.

b) The explanatory variables are the type of illumination given to the students while performing the exams. In this particular case yellow overhead lighting, fluorescent overhead lighting and only a desk lamp without any overhead lighting. We can consider that the variable itself is the illumination level and the color of it. An explanatory variable is a variable that can not be considered independent of any other for sure. In this case, we don't know if the effect of the overhead lights is independent of the desk lamps, or there are other variables such as external light, tiredness of students, usage of glasses, etc).

c) The blocking variable is the gender of the students. In this case, male and female. The blocking variables are those that allow arranging the controlled population in group (blocks) that has similar characteristics. In this way we can reduce unexplained variability, therefore reduce the possibility of getting mistaken thesis to the problem.

In this problem, the researcher believes that light levels might have different effects on males and females. Therefore by separating people in groups of males and females, we can test that theory without risks of getting another thesis if the study is done without splitting the test population.