In a 1988 artiele, Josef Brada and Ronald Graves built an interesting model of defense spending i...
In a 1988 artiele, Josef Brada and Ronald Graves built an interesting model of defense spending in the Soviet Union just before the breakup of that nation. The authors felt sure that Soviet defense spending was a function of U.S. defense spending and Soviet GNP but were less sure about whether defense spending also was a function of the ratio of Sovict nuclear warheads to U.S. nuclear warheads. Using a double-log functional form, the authors estimated a number of alternative specifications, including (standard errors in parentheses: In SDH,199+0056lnLISD+09ns,+0057InsP, (0.065) (0.032) t0.76 1.80 N- 25 (annual 1960-1984) R-979 DW-0.49 n SDH-2.88 0.10SlnISD1.066InSY N- 25 (annual 1960-1984) R-977 DW-0.43 (0.038) 28.09 where: SDH1 = the CIA's "high" estimate of Soviet defense expenditures in year t (billions of 1970 rubles) USD U.S. defense expenditures in year t (billions of 1980 dollars) ECON3500 SYt Soviet GNP in yeart (billions of 1970 rubles) SPt the ratio of the number of USSR nuclear warheads (NRt) to the number of U.S. nuclear warheads Datafile DEFEND9 a. Use our four specification criteria to determine whether SP is an irrelevant variable. Explain your b. Test both equations for positive first-order serial corelation. Does the high probability of serial c. Someone might argue that because the DW statistic improved when InSP was added, that the serial correlation cause you to reconsider your answer to part a? Explain. correlation was impure and that GLS was not called for. Do you agree with this conclusion? Why or why not? cause you to reconsider your answer to part b? Explain: In SDH,-2.65+0.104 In USD, +1.034 In SY -0.032 In SP d. If we run a GLS version of te eqation, we get the following equation. Does this result (0,087) (0.078) t-20 N-24 adjR 0.986 -0.75 NOTE: The answer is in the textbook Appendix A page507. When you use Eviews to do your GLS estimation, use LS logisdh) c log(usd) log(sy) log(sp) ar(1) for your command. AR(1) will capture the 1 order autocorrelation. Your result might be slightly different, but it's OK. Show me the output for the 3 equations in this question.)
In a 1988 artiele, Josef Brada and Ronald Graves built an interesting model of defense spending in the Soviet Union just before the breakup of that nation. The authors felt sure that Soviet defense spending was a function of U.S. defense spending and Soviet GNP but were less sure about whether defense spending also was a function of the ratio of Sovict nuclear warheads to U.S. nuclear warheads. Using a double-log functional form, the authors estimated a number of alternative specifications, including (standard errors in parentheses: In SDH,199+0056lnLISD+09ns,+0057InsP, (0.065) (0.032) t0.76 1.80 N- 25 (annual 1960-1984) R-979 DW-0.49 n SDH-2.88 0.10SlnISD1.066InSY N- 25 (annual 1960-1984) R-977 DW-0.43 (0.038) 28.09 where: SDH1 = the CIA's "high" estimate of Soviet defense expenditures in year t (billions of 1970 rubles) USD U.S. defense expenditures in year t (billions of 1980 dollars) ECON3500 SYt Soviet GNP in yeart (billions of 1970 rubles) SPt the ratio of the number of USSR nuclear warheads (NRt) to the number of U.S. nuclear warheads Datafile DEFEND9 a. Use our four specification criteria to determine whether SP is an irrelevant variable. Explain your b. Test both equations for positive first-order serial corelation. Does the high probability of serial c. Someone might argue that because the DW statistic improved when InSP was added, that the serial correlation cause you to reconsider your answer to part a? Explain. correlation was impure and that GLS was not called for. Do you agree with this conclusion? Why or why not? cause you to reconsider your answer to part b? Explain: In SDH,-2.65+0.104 In USD, +1.034 In SY -0.032 In SP d. If we run a GLS version of te eqation, we get the following equation. Does this result (0,087) (0.078) t-20 N-24 adjR 0.986 -0.75 NOTE: The answer is in the textbook Appendix A page507. When you use Eviews to do your GLS estimation, use LS logisdh) c log(usd) log(sy) log(sp) ar(1) for your command. AR(1) will capture the 1 order autocorrelation. Your result might be slightly different, but it's OK. Show me the output for the 3 equations in this question.)
