Description

Question 1.

 COVID-19 Data for project 2 has been posted in Learn. Please download the dataset named as “student_ID.csv”. For example, if your student ID is 12345, you should download and use the data file “covid_12345.csv”. A detailed data description file, named “project 2 dataset description”, is also available in Learn. All the variables are categorical and some of the variables have invalid labels. You might want to pay attention to this when processing the data.

1. A survey done by Research Co. in January of 2020 found that 25% of Canadians ordered prepared food by delivery service at least once during the reference week. Does the data support the claim that ordering food by delivery service has declined? Construct a formal hypothesis test. What kind of test conclusion you can draw and also give an appropriate interpretation of the p-value. Provide the required assumptions for the inference you just conducted. 

2. What is the probability of being concerned about the effect of COVID-19 on one’s own health conditioning on having a compromised immune system? Also try to calculate the probability of being concerned about the effect of COVID-19 on one’s own health providing having a chronic condition. Test whether these two probabilities are the same or not, and provide intuitive explanations on how these conditional probabilities compare to the unconditional probability of being concerned about the impact of COVID-19 on your own health. 

3. Let being concerned about the effect of COVID-19 on one’s own health be the dependent variable Y and having a compromised immune system be the independent variable X. Build a regression model without control variables. What is the estimated coefficient of having a compromised immune system? Interpret the meaning of this estimated coefficient. 

4. Based on the regression in (3), add control variables you think are necessary with a brief explanation, in economics sense, why those variables are necessary. How can you test if those variables are indeed necessary? With additional control variables what is the estimated coefficient of having a compromised immune system? Interpret the meaning of the estimated coefficient. What is the R 2 and what is the adjusted R 2 ? 

5. Construct a test to examine the difference between: 1) the effect of having a compromised immune system on being concerned about the effect of COVID-19 on one’s own health; 2) the effect of having a chronic condition on being concerned about the effect of COVID-19 on one’s own health. Explain the test results and discuss what do you learn from those results.