Poor Household’s Demand for Cheap Dietary Staples

Predictive Analytics: Poor Household’s Demand for Cheap Dietary Staples

Ramses Y. Armendariz

University of Illinois, Urbana-Champaign

Last Revised FALL 2020 Predictive Analytics (Armendariz) 1

What is the Final Project?

• You will predict the impacts of changes in prices of dietary staples. • You will calibrate a model of the demand for cheap dietary staples of the extreme poor.

• You will simulate the demand to extract some predictions.

• The demand model is given to you: 𝑏 = 𝑖 𝛽𝛼𝑏𝑝𝑚−𝑝𝑏𝛼𝑚 +𝑝𝑚𝑝𝑏 1−𝛽 ҧ𝑐

𝑝𝑏 𝛼𝑏𝑝𝑚−𝑝𝑏𝛼𝑚 • The parameters in this model are ҧ𝑐,𝛽,𝛼𝑏, and 𝛼𝑚. • The economic statistics in this model are 𝑖,𝑝𝑚,and 𝑝𝑏.

• You will calibrate for the values of the parameters to fit this model to the data (Jensen and Miller, 2008). • You will use the method of moments to calibrate the parameters.

• Once you have calibrated for the parameters, you will simulate some predictions: • You will graph the demands for cheap dietary staples of the extreme poor.

• You will graph the Income-Consumption Curves and Engel Curves.

• You will graph the Indifference Curves of the household.

• You will estimate the Willingness To Pay for a policy that drops the price of the staple by 1%.

Last Revised FALL 2020 Predictive Analytics (Armendariz) 2

The Model

• This model characterizes a household that faces the following economic problem:

• max 𝑏,𝑚

𝛼𝑏𝑏 + 𝛼𝑚𝑚 − ҧ𝑐 𝛽 𝛿𝑚 1−𝛽 s.t.: 𝑝𝑏𝑏 + 𝑝𝑚𝑚 ≤ 𝑖 and 𝑏,𝑚 ≥ 0.

• The following two equations characterize the solution to that economic problem

• 𝑏 = 𝑖 𝛽𝛼𝑏𝑝𝑚−𝑝𝑏𝛼𝑚 +𝑝𝑚𝑝𝑏 1−𝛽 ҧ𝑐

𝑝𝑏 𝛼𝑏𝑝𝑚−𝑝𝑏𝛼𝑚 𝑚 =

𝑖−𝑝𝑏𝑏

𝑝𝑚

• Intuition of the model: • Households have Cobb-Douglas preferences for hunger satiation (𝛼𝑏𝑏 + 𝛼𝑚𝑚 − ҧ𝑐) and flavor (𝛿𝑚).

• Households must go to the markets to buy a cheap dietary staple, 𝑏, and a superior composite good, 𝑚. • Households want to avoid consuming a quantity of calories ҧ𝑐.

• This model enables us to do the following: • Extrapolate the demands for dietary staples of the extreme poor.

• Extrapolate the demands for total caloric intake.

• Extrapolate the preferences (indifference curves) for food of households.

• Estimate the Willingness To Pay for subsidies on dietary staples.

Last Revised FALL 2020 Predictive Analytics (Armendariz) 3

The Project

• Your project report must be between 6 to 10 pages. • The point of you report is to explain how to replicate your results.

• Cite all the sources you used and the people you worked with.

• I will add some instructions on how to calibrate the model and generate some predictions in Compass. • The instructions I share in Compass are to create the whole project using Excel.

• Our student TA, Francis, has created instruction on how to simulate the model using R.

• The due date for the project is the date of the final exam: December 12th, 2020 at 11:00 PM.

• To know more about this project, you can click on the paper located in this link: • https://www.drarmendariz.com/research

Last Revised FALL 2020 Predictive Analytics (Armendariz) 4