This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Stata: Regressions, Tests, Omitted Variable Bias and Measurement Error Econ 142 Spring 2008 Raymundo M. Campos-Vazquez February 12, 2008 Contents 1 Today 1 2 Graphs 2 3 Regressions 2 4 Omitted Variable Bias 3 5 Measurement Error 3 1 Today Today we will analyze a small sample of the MORG dataset for year 2004. This sample focuses on individuals 21-60 with a valid wage. We are going to analyze four things today: (1) Graphs, (2) Regressions and Statistical Tests, (3) Omitted Variable Bias problem, and (4) Measurement Error. & Start a do-&le and log &le. & Open the dataset. Describe the dataset. Variables are state, age of individual, industry and occupation identi&ers, hrwage, unionn membership, years of schooling, and dummy variables for female and foreign born. 1 2 Graphs 1. Graph the relationship between wages and education. Include a scatter plot and a linear &t between hrwage and education. Is there any sign of heteroskedasticity? 2. Create a histogram for wages (25 bins). Does it look like a normal distribution? 3. Repeat (1) and (2) but using the natural logarithm of wages. Call this variable logwage....
View Full Document
- Spring '08