ECON399
Introductory Econometrics
LAB 1
ECON399 D5/D6 – INTRODUCTORY ECONOMETRICS
To be held week of 23rd Sept 2025
Complete by Noon, Sept 28th 2025
Instructions
1. Collecting data is an important part for most economic analysis. This lab will help you learn how to fetch data from open source databases, i.e. internet. In this exercise, we are going to collect data from CANSIM (Canadian Socio-economic Information system), maintained by U of T at CANSIM@CHASS. This lab will also help you to initiate any project that will interest you through data manipulation.
2. Let’s start with a virtual project on the study of international migration. We are interested in factors that determine the number of immigrants who entered Canada. We could retrieve data online from U of A library website:
• Go to https://www.library.ualberta.ca
• Click on “Databases” and search for data set “CANSIM” by typing in a
database search bracket “CANSIM” As results of your search are listed, click on “CANSIM (via CHASS)” and input your CCID and passwords, in a new window, choose “Access Database”, choose “CANSIM Multidimensional View”, then “English”, then choose “CANSIM Multidimensional @ CHASS Main Menu”
• On this page, you could find data that interests you by using search by “Suggested Text Search”; by subjects or by keywords.
• For this lab session, we collect the following information for our purpose.
i. Click on “Download/Retrieve Multiple Series”
ii. Write the variable serial number “1” in the box under “Series by numbers or/and ranges:”
iii. Specify the time span of the data: 1976-2012
iv. Under “Output display”, choose “As a record set” and “Normal”
v. Under “Output format”, choose “plain text”
vi. Click “submit”
vii. In the new pop-up window, save the link as “pop_ 1976_2012.txt”
viii. This txt data file will contain information on quarterly population size of Canada from 1976 through 2012.
ix. Repeat the above steps and save the following variables as well:
v16 (immigrants, quarterly); v1997756 (GDP index, quarterly); v2062815 (unemployment rate, monthly data)
x. Read these data into stata separately. Save them as stata files
separately. Note: before reading the txt data into stata, you need to open the txt file first and edit the data so that the data record start from the very first line!
xi. Name the variables following these conventions: pop (population); gdp (GDP); ue (unemployment rate).
Tasks
1. Convert quarterly (monthly) data into annual data for EACH STATA FILE. You can take averages over 4 quarters for a year.
2. Keep variables of interests only: for each saved stata file, keep “date”, “pop”, “gdp”, “ue”, “immig”
3. Merge the stata files into one data file that contains all the variables.
4. Generate new variables:
a. Pop/1000000 (call it “pop_mil” for population in millions)
b. Immig/1000 (call it “immig_ 1000” for number of immigrants in thousands)
c. Gdp/pop_mil (call it “gdp_permil” for gdp index per million population)
5. Run correlations between population in millions and immigrants in thousands, does this mean that immigration helps Canada to maintain population growth?
6. Run correlations between immigrants in thousands and gdp per million, does the result make sense? Why?
7. Run correlations between immigrants in thousands and ue, comment.
8. Discuss the results, what do we miss if we would like to say something on factors affecting migration flows to Canada?