NOTE: SPSS will sometimes report numbers in scientific notation, for example: 4.
ID: 3270017 • Letter: N
Question
NOTE: SPSS will sometimes report numbers in scientific notation, for example: 4.03E4. This is a shorthand method of representing large (or very small) numbers.
4.03E4 = 4.03 * 10^4 = 4.03 * 10000 = 40300
1 You want to conduct a study to determine if a deitary protein supplement, SupplementA, is effective at increasing strength. You find a group of 40 people, 20 of whom use SupplementA on a regular basis, and 20 of whom do not. Other than the supplement, their diets and training regimens are comparable. You run an independent samples t-test, and find a statistically significant difference; on average, people who take SupplementA on a regular basis are indeed stronger. While reviewing the data, you find that the group that was on the supplement consisted of 17 men and 3 women, while the group that was not on the supplement consisted of 16 women and 4 men. Do you see anything wrong with the design of this study? Can you think of any way to correct it? You do not have to do any calculation for this question.
2 I have stated before that ANOVA is a form of linear regression. Suppose I wanted to examine the study habits of college students. I conduct a survey, and assess the average time spent studying (per night, in hours) of students. I want to see if there is a difference in mean study time between any of the grades (Freshmen, Sophmore, Junior, Senior), and I decide to use an ANOVA to test this. In other words, I want to see if grade-level is related to time spent studying- do certain grades stuy more than others? Think about this problem in the linear regression setting- what would the independent and dependent variables be? Give both their name and type. You do not have to do any calculation for this question. Do not worry about post hoc testing.
Explanation / Answer
1.
Yes the design of the model is wrong. The dependent variable of the design, strength also depends on other variables such as age and gender. On average, the strength of men are greater than the strength of women. So, the age and gender seems to be confounding variables in the study. In the experiment study, the group that was on the supplement consisted of 17 men and 3 women, while the group that was not on the supplement consisted of 16 women and 4 men. So, it is obvious that there is a bias based on the confounding variable gender, and the strength of first group is greater than the second group and it cannot be determined that the difference in strengths between the two groups is due to gender or due to protein supplement, SupplementA.
To correct it, divide the people based on their gender into two different groups and randomly assign same number of men and women in the groups who take SupplementA and who do not take SupplementA.
2.
Dependent variables - A continuous numerical variable - Time spent studying (per night, in hours)
Independent variables - A categorical variable - Grade with four levels - Freshmen, Sophmore, Junior, Senior
Related Questions
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.