lecture6_140b_2011

lecture6_140b_2011 - Olivier Deschenes, UCSB, Econ 140B,...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

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

Unformatted text preview: Olivier Deschenes, UCSB, Econ 140B, Winter 2011 Lecture 6: Panel Data Also called longitudinal data Observe n cross-sectional units (person, firm, state) at T different points in time Notation will now keep track of cross-sectional units and time period: (Y it ,X it ): i=1,,n and t=1,,T Chapter 10 in S&W Olivier Deschenes, UCSB, Econ 140B, Winter 2011 Examples: A panel dataset contains observations on multiple entities (individuals), where each entity is observed at two or more points in time Hypothetical examples : Data on 420 California school districts in 1999 and again in 2000, for 840 observations total Data on 50 U.S. states, each state is observed in 3 years, for a total of 150 observations Data on 1000 individuals, in four different months, for 4000 observations total Olivier Deschenes, UCSB, Econ 140B, Winter 2011 Example of how a panel data file looks: id year female age educ married lnwage 6 85 No 25 16 No 1.96667 6 86 No 26 16 No 2.065892 6 87 No 27 16 No 2.12483 6 88 No 28 16 No 2.189966 6 89 No 29 16 No 2.202586 28 84 Yes 20 11 No 1.621872 28 85 Yes 21 11 No 1.861165 28 86 Yes 22 11 Yes 1.882414 28 87 Yes 23 11 Yes 1.880701 28 88 Yes 24 11 Yes 1.986032 20 82 Yes 23 14 No 2.10249 20 83 Yes 24 17 No 2.250023 20 84 Yes 25 16 No 2.068311 20 85 Yes 26 14 No 2.307221 20 86 Yes 27 15 No 2.361061 Yikes Olivier Deschenes, UCSB, Econ 140B, Winter 2011 Notation: A double subscript distinguishes cross sectional units (i) and time periods (years) i = units, n = number of entities, i = 1,, n t = time period (year), T = number of time periods t =1,, T Data: Suppose we have 1 regressor. The data are: ( X it , Y it ), i = 1,, n , t = 1,, T Olivier Deschenes, UCSB, Econ 140B, Winter 2011 Panel Study of Income Dynamics Available online at: http://psidonline.isr.umich.edu/ Began in 1968, annual survey Focuses on individuals and family unit The sample size has grown from 4,800 families in 1968 to more than 7,000 families in 2001 Information on labor market outcomes, wealth, family dynamics, etc At the conclusion of 2003 data collection, the PSID will have collected information about more than 65,000 individuals spanning as much as 36 years of their lives Olivier Deschenes, UCSB, Econ 140B, Winter 2011 National Longitudinal Survey of Youth Information online at: http://www.bls.gov/nls Started in 1979, annual/biennial interviews Sample of 12,686 young men and women who were 14- 22 years old when they were first surveyed in 1979 Detailed data on labor market activities, marital status, fertility, educational investments and achievements, health conditions, etc Olivier Deschenes, UCSB, Econ 140B, Winter 2011 Balanced panel : all cross-sectional units are observed in every time period Unbalanced panel : not all cross-sectional units are observed in every time period Unbalancedness may cause some statistical issues (not in this class) Olivier Deschenes, UCSB, Econ 140B, Winter 2011...
View Full Document

Page1 / 74

lecture6_140b_2011 - Olivier Deschenes, UCSB, Econ 140B,...

This preview shows document pages 1 - 8. Sign up to view the full document.

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