Practice 10 questions on WST212 - Mathematical Statistics 212 at University of Pretoria. Free AI-generated quiz on uNotes — track your score, retake anytime.
1In SQL, what is the primary reason for using the HAVING clause instead of the WHERE clause when filtering a report based on a calculated total?
2When preparing data for a logistic regression model in R (such as the Pima Indians Diabetes dataset), which of the following steps are typically necessary for categorical predictors?
3According to the course instructions, what is the consequence of having a single syntax error in your R script upon submission to the autograder?
4A student fits a logistic regression model named 'Q3_model'. Which R command correctly extracts the predicted probabilities (not the log-odds) for a testing dataset named 'df_test'?
5If a medical researcher is more concerned about missing a patient with heart disease (False Negative) than incorrectly diagnosing a healthy patient (False Positive), which performance metric should they prioritize increasing?
6In a logistic regression model output, if a variable has a p-value of 0.034, which of the following is true at a 5% level of significance?
7Given a logistic regression model with the equation logit(p) = -3.59 + (0.10 * BMI). If a patient has a BMI of 30, calculate the predicted probability (p) of being diabetic. Round to four decimal places.
8What happens to the performance metrics of a logistic regression classifier if the classification threshold is increased from 0.5 to 0.7?
9Which of the following SQL keywords are used to change the name of a column in the output report (e.g., labeling a calculated count as 'CountTitle')?
10In RStudio, what is the recommended practice mentioned in the guidelines to perform before running and checking your code for errors to ensure a clean environment?
