sol_API-202A+Assignment+2+S09

sol_API-202A+Assignment+2+S09 - API-202A Empirical Methods...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon
1 API-202A Empirical Methods II Spring 2009 Assignment 2 Suggested Solutions Section I: Smoking and Cancer (The answer below is more complete than what you were asked for.) X i XX i () i 2 Y i Y Y i 2 ) ( Y Y i * ( ) XXY Y ii  1 (Holland) 460 -236 55696 245 -15 225 3540 2 (Finland) 1115 419 175561 350 90 8100 37710 3 (GB) 1145 449 201601 465 205 42025 92045 4 (Canada) 510 -186 34596 150 -110 12100 20460 5 (Norway) 250 -446 198916 90 -170 28900 75820 (...) 3480 666370 1300 91350 229575 (...) / N 696 260 1. a) 1 1 2 1 ( ) 229575 ˆ 0.3445 666370 n i n i i Y Y  b) 01 ˆˆ 260 (0.3445)(696) 20.23 YX     c) 1: Holland 11 22 33 44 ˆ ˆ 20.23 (0.3445)( ) 20.23 (0.3445)(460) 178.7 ˆ 20.23 (0.3445)( ) 20.23 (0.3445)(1115) 404.4 ˆ 20.23 (0.3445)( ) 20.23 (0.3445)(1145) 414.7 ˆ 20.23 (0.3445)( ) 20.23 (0.3445)(510  55 ) 195.9 20.23 (0.3445)( ) 20.23 (0.3445)(250) 106.3 d) 1: Holland 1 2 3 4 5 ˆ ˆ ˆ 245 178.7 66.3 ˆ 350 404.4 54.4 ˆ 465 414.7 50.3 ˆ 150 195.9 45.9 ˆ 90 106.3 16.3 iii uYY u u u u u
Background image of page 1

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

View Full DocumentRight Arrow Icon
2 (2a) Here is the STATA regression. The relevant estimates are shaded: next to _cons is 0 ˆ , next to smoke is 1 ˆ , and next to R-squared is the R 2 of this regression. . reg cancer smoke, robust Regression with robust standard errors Number of obs = 5 F( 1, 3) = 22.59 Prob > F = 0.0177 R-squared = 0.8658 Root MSE = 63.921 ------------------------------------------------------------------------------ | Robust cancer | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- smoke | .3445158 .072487 4.75 0.018 .1138297 .5752019 _cons | 20.217 52.79902 0.38 0.727 -147.813 188.247 ------------------------------------------------------------------------------ The computer generates regression coefficients the same way you did, by crunching the numbers. The computer will crunch any set of numbers you feed it, whether or not the calculations make sense. For example, if you type “regress smoke cancer” it will produce estimates of the effect of cancer in 1950 on smoking in 1930, which makes no sense. It is the job of the econometrician (you) to think through the model clearly before turning it over to the computer. In other words, Stata knows only that the first variable after the “regress” command is the dependent variable. It knows nothing about what the variable names represent, but just does the calculation assuming that the first variable listed is the dependent variable, whether or not that makes any sense. 2b) The r2 reported by Stata means that 86% of the differences that we observed in lung cancer deaths rate in 1950 among the 5 countries in the sample can be related to their differences in p/c cigarette consumption in 1930. This relationship is not necessarily causal as we have not necessarily identified the causal effect.
Background image of page 2
3 Section II – Random Assignment A complete answer to this question will include a do-file and a log file. Here is a sample do-file. #delimit ; cd "C:\My Documents\Assignment 2"; log using ps2,text replace; use "Jamaica 2002 short.dta", clear; gen aux=uniform(); sort aux; gen treatment=(_n<=_N/2); ttest age, by (treatment) unequal; ttest female, by (treatment) unequal; ttest hhsize, by (treatment) unequal; ttest cons, by (treatment) unequal; log close; Note this log file is over-written with each iteration, as instructed by this command: .log using ps2,text replace; If you instead write .log using ps2,text append; You will get a log file that appends each additional set of t-tests instead of overwriting the last one.
Background image of page 3

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

View Full DocumentRight Arrow Icon
Image of page 4
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 04/12/2009 for the course HKS API202A taught by Professor Levy during the Spring '09 term at Harvard.

Page1 / 12

sol_API-202A+Assignment+2+S09 - API-202A Empirical Methods...

This preview shows document pages 1 - 4. Sign up to view the full document.

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