This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Name: Peter the Anteater UC ID Number: XXXXX Problem Set 3 Econ 122 B – Applied Econometrics Due Thursday November 4 th at the beginning of lecture FIRST STEP: PLEASE TYPE YOUR NAME and UCI ID IN THE UPPER RIGHT CORNER OF THIS DOCUMENT. Just erase “Peter the Anteater” and type your name. The following problem set will use the lowbirth eviews workfile. For all questions, please paste the necessary output from eViews and answer the question below the output. You will then print this out, staple it , and hand it in on the due date. Preliminary Setup: Structure the unstructured dataset to make it a panel structure in Eviews (hint –click on “Proc” and then “Structure/Resize Current Page”). Please start your answers on a new page, pasting the regression output and your answers to the questions. 1. Regress lowbrth on afdcprc , log( physicpc ), log( bedspc ), log( pcinc ), and log( popul ), where the dependent variable is lowbrth , the percentage of births that are classified as low birth weight and the key explanatory variable is afdcprc , the percentage of the population in the welfare program, Aid to Families with Dependent Children (AFDC). The other variables, which act as controls for quality of health care and income levels, are physicians per capita, hospital beds per capita, per capita income, and population. What is the sign on the coefficient of afdcprc? Does this result make sense? What could be driving this result? Dependent Variable: LOWBRTH Method: Least Squares Date: 10/25/10 Time: 11:49 Sample: 1 100 Included observations: 100 Variable Coefficient Std. Error tStatistic Prob. AFDCPRC 0.151883 0.089779 1.691734 0.0940 LOG(PHYSICPC) 0.325460 0.6603660.492848 0.6233 LOG(BEDSPC) 0.271509 0.522233 0.519901 0.6044 LOG(PCINC) 1.194955 0.7711161.549643 0.1246 LOG(POPUL) 0.078587 0.639147 0.122956 0.9024 C 17.56818 5.831875 3.012441 0.0033 Rsquared 0.215386 Mean dependent var 6.707000 Adjusted Rsquared 0.173651 S.D. dependent var 1.166039 S.E. of regression 1.059973 Akaike info criterion 3.012489 Sum squared resid 105.6130 Schwarz criterion 3.168799 Log likelihood 144.6244 HannanQuinn criter. 3.075750 Fstatistic 5.160828 DurbinWatson stat 1.386341 Prob(Fstatistic) 0.000315 Low birthweights are caused by poor maternal nutrition and prenatal care. The AFDC program provides income support to poor women with children, so it should lead to improved maternal nutrition and therefore lower birthrate. The sign on AFDCPRC is positive, which implies that increasing the percentage of the population in the AFDC program is associated with an increase in the percentage of low birth weights. program is associated with an increase in the percentage of low birth weights....
View
Full Document
 Spring '10
 DAVIDBROWNSTONE
 Econometrics, Regression Analysis, standard errors, EViews, Schwarz, Low birth weight paradox

Click to edit the document details