Lab 10 Exercises - Nonlinear models and Dummy Variables

Lab 10 Exercises - Nonlinear models and Dummy Variables -...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Lab 10: Data Manipulations and Non-Linear Models Objectives: It is not unusual to have to make some modifications to your data before estimation. In the first part of the lab, we’ll use Minitab to do some data manipulations. The second part of the lab will introduce you to estimation of nonlinear models by again manipulating the data in Minitab and then estimating using OLS . There is a practice problem set posted on the website and attached below as well. Bring the practice problem to the lab; you should be able to complete these problems. We’re not collecting all these answers, but you should be able to write answers to these problems following lab and lectures. Data : CPS 2004 New England Private.xlsx and Lab 8 Exercises.xls . or your Lab 9 minitab project. More Dummy Variables and Nonlinear Models 1. The data set CPS 2004 New England Private.xlsx is an Excel file containing a sample of private wage data for New England workers, all sectors. CPS 2004 New England Private.mtw is the same data, but is a Minitab Worksheet. Choose File and Open Worksheet in Minitab . The data set contains a number of variables including: wage = the individual’s 2004 wage in $/hour; yrsed = the individual’s education in years; hours = the number of hours worked in a typical week; age = the individuals age in years; ex = the potential experience for an individual in years; as well as dummy variables: fe indicates whether or not the individual was female; hinspd indicates the individual received paid health insurance; unioncov indicates the individual was covered by a union contract; union indicates whether or not the individual was a member of a union; and pension indicates the individual had retirement benefits. 2. Specify and estimate the two models that are required to answer the question: Do women earn lower starting salaries and lower raises ? This question is asked in part c of the practice problem that was posted with this lab. It requires that you estimate two models and then use of an F-test to choose between the two models; you will determine whether women earn lower wages and lower raises than equally qualified males. The first model is given in the text for the problem set. It relates wages to two independent variables, education and experience. (Define a raise as the returns to an additional year of experience.) 3. Specify and estimate the second model needed to answer the question posed in the practice problem, part c . This model requires that you include a dummy variable ( fe ) and an interaction term ( feex ). How do you create the interaction term that is required? You should have no problems completing this given our work in lab last week. Copy the results for these two regressions into Word and write a paragraph interpreting the estimated coefficients for the variables fe and feex. Are these individual effects statistically different from zero? What hypothesis test would you specify and complete to answer this question?
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 12/08/2011 for the course ECON 312 taught by Professor Daniellass during the Winter '10 term at UMass (Amherst).

Page1 / 5

Lab 10 Exercises - Nonlinear models and Dummy Variables -...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online