Week 3 practice questions

Week 3 practice questions Suppose you have a dataset, named students_data, with 60 rows. There are 4 variables in this dataset: Name: name of the student Sex: male or female Handedness: right or left Extroverted: students’ self-rated score of how extroverted they are, on a scale of 1 - 10, with 10 being the most extroverted 1. What does each row of the dataset represent? [Choose all that apply] a. An observation b. A variable c. A student d. A rating of how extroverted they are 2. If we added a new summary variable named Extroverted_binary to the dataset that categorized whether students’ extroverted scores were above 5 or below 5, how would that affect the number of rows? How would that affect the number of columns? a. It would increase the number of rows, but NOT change the number of columns b. It would decrease the number of rows, but NOT change the number of columns c. It would NOT change the number of rows, but increase the number of columns d. It would NOT change the number of rows, but decrease the number of columns e. Neither the number of rows nor the number of columns will change 3. The table below shows the first six rows of the dataset: Name Sex Handedness Extroverted Adam Male Left 10 Emma Female Right 9 Dave Male Right 4 Joseph Male Right 9 Elizabeth Female Left 1 Amelia Female Right 3 Suppose we run the code below: students_data_new <- filter(students_data, Sex == “male”) Compared to the original students_data , the number of rows in students_data_new would:

a. Increase b. Decrease c. Stay the same d. We cannot know based on the 6 rows of the dataset provided 4. Look at this line of code: students_data$Sex_shuffled <- shuffle(students_data$Sex) a. What is this line of code doing? This line of code randomly reorganizes the Sex variable and puts it into a new variable named Sex_shuffled in the students_data dataset. b. If you know a students’ value on Sex_shuffled, do you think it would help you make a better guess of that students’ Extroverted score? Why or why not? No, knowing a students’ value on Sex_shuffled would not help make a better guess of that students’ Extroverted score, because there is no relationship between Sex_shuffled and Extroverted. 5. We ran the code below. students_data$Sex_shuffled <- shuffle(students_data$Sex) gf_histogram (~Extroverted,bins=10, data = students_data)%>% gf_facet_grid (Sex_shuffled~.)%>% gf_model(Extroverted~Sex_shuffled) Here’s a histogram that shows the relationship between Sex_shuffled and Extroverted. It looks like Sex_shuffled predicts some variation in Extroverted. Why do you think this is? Do you think this relationship exists in the DGP? This is purely random. This relationship does not exist in the DGP. 6. Aliya used the shuffle() function to shuffle the Extroverted variable from students_data . Each time Aliya shuffled, they calculated the mean difference in Extroverted scores between the female group and the male group. Aliya then repeated this process 1000 times and made a distribution of these 1000 shuffled mean differences. Explain in your own words, where this