Introduction to Statistics

Collect data appropriate to a specified purpose, and recognize limitations in existing data.
Explain the benefits of the statistical approaches used to identify relationships between variables.
Analyze data using appropriate graphs and numerical tools (primarily multiple regression).
Derive appropriate, actionable conclusions from data analysis.
Present results and conclusions in both technical and non-technical terms, in writing and orally.

Describe the role of statistical thinking and methods for problem solving.
Discuss the value of understanding, quantifying, and reducing variation.
Develop an understanding of how statistics is integral to research in economics.
Determine the appropriate questions statistical consultants should ask.
Develop the ability to read scientific literature

Materials:

Computer lab space is needed to conduct the experiment, which can be done inside or outside of the regularly scheduled class time.
Students are required to read the "Cash for Condoms" chapter in the following textbook: Easterly, W (2001). The Elusive Quest for Growth, MIT Press, pp. 87-99. We place two or three books on 2-hour reserve at our library.
Students are required to pull data from the website http://web.worldbank.org. Most institutions will have access to 695 variables and 45 years of data while only 54 variables for 5 years is available for free. While not required, contacting your own librarian for instructions to access the entire data set will improve the quality of the lab.
While not required, this lab may benefit by asking an econometrics professor (or statistician if you are an economics class) to visit the class to discuss the reading and identify appropriate research questions.

Cash for Condoms Lab :

William Easterly, Senior Fellow at the Center for Global Development and the Institute for International Economics, is a prominent economist who has significant experience in economic development. In his book, Easterly shows that many attempted "solutions" to economic development in poor countries have violated basic principles of economics.

Cash for Condoms Lab: Printable Student Version
Some older versions of Adobe Acrobat may have some trouble displaying the pdf files. You can download the most recent version of Adobe Acrobat Reader at www.adobe.com.

2002 Worldbank Data

The worldbank http://web.worldbank.org has collected data for several years that track socio-economic data on most countries. To pull data for this lab, go to the Worldbank Data & Statistics page and select the quick query link (or directly go to http://devdata.worldbank.org/data-query/). This will allow you to select data from multiple countries, variables and years. As mentioned earlier, most institutions have a license to pull much more data than is freely available on the web. Contact your librarian for details. Descriptions of each variable is available by selecting “Technical notes” on the Worldbank Data & Statistics page.

Instructors Notes:

Prerequisites: Before conducting this lab, students should be familiar with variable selection in multiple regression, heteroskedasticity, multicollinearity, and transformations. It is also important to discuss using interaction terms in regression models (note that interactions are not currently discussed in the Cars: Introduction to Multivariate Regression Lab).

Class Discussion: This text is very readable for the general population. Ask students to identify assumptions that are made throughout the chapter. For example:

Free condoms will lower fertility rates
lower fertility rates will reduce population growth.
A slower population growth in third world countries will improve economic growth.

Students my want to test these assumptions with the data provided or a variety of other possible questions.

While there are many other variables to choose from, it is important for students to recognize some variables have too many blank entries to be easily used in most analyses. Some variables deleted from the provided 2002 data set only had information for a few countries. Most recent years tend to have a few more blank entries.

Invite an economist to the class (or a statistician if you are an economist) to answer student questions that are beyond your scope of knowledge.

It was very helpful for my students to hear from a researcher that he/she did not know all of the answers to their questions.
My students seemed to be somewhat surprised that they could contribute to science by conducting a study that has never been specifically studied before. Having a scientist in each field enforce the idea that science in not just a collection of facts but an ongoing exploratory process was very helpful for my students.

Grading: I would suggest 50 points for the entire lab (this is the same value as an exam in my course).

5 points for Day 1, the review of Cash for Condoms question
10 points for Identifying relevant background
10 points for Exploratory Data Analysis and Model Development of the provided data set
5 points for appropriate comments and suggestions on other student papers or posters
20 points for the final paper or poster

Cash for Condoms - Econometrics

Impacts of Population Control on Economic Growth in Third World Countries