问题如下图：
选项：
A. 
B. 
C. 
解释：
由这道题想请教一个更广的范围，这道题出现了滞后项，所以
1、只出现滞后项时，是不是obervation应该取n-1？
2、如果同时出现滞后项和非滞后项的自变量，n到底应该为n还是n-1呢？
NO.PZ2015120204000019问题如下Excess stomarket returnt=a0+a1fault sprea-1+a2Term sprea-1+a3Pres party mmyt-1+etfault spreis equto the yielon Bbon minus the yielon Abon. Term spreis equto the yielon a 10-yeconstant-maturity US Treasury inx minus the yielon a 1-yeconstant-maturity US Treasury inx. Pres party mmy is equto 1 if the US Presint is a member of the mocratic Party an0 if a member of the RepublicParty.The regression is estimatewith 431 observations.Exhibit 1.Multiple Regression OutputExhibit 2. Table of the F-stribution (CriticValues for Right-HanTail Area Equto 0.05) Numerator: 1 annominator: 2 Is the regression mol a whole significant the 0.05 level?A.No, because the calculateF-statistic is less ththe criticvalue for F.B.Yes, because the calculateF-statistic is greater ththe criticvalue for F.C.Yes, because the calculateχ2 statistic is greater ththe criticvalue for χ2. B is correct.The F-test is useto termine if the regression mol a whole is significant.F = Mesquare regression (MSR) ÷ Mesquareerror (MSE)MSE = SSE/[n – (k + 1)] = 19,048 ÷ 427 = 44.60MSR = SSR/k = 1071 ÷ 3 = 357F = 357 ÷ 44.60 = 8.004The criticvalue for grees of freem of 3 an427 with α=0.05 (one-tail) is F = 2.63 from Exhibit 2. The calculateF is greater ththe criticvalue, anChiesa shoulrejethe null hypothesis thall regression coefficients are equto zero. 题目表格中的T统计是做什么用的？是怎样计算出来的？谢谢！
NO.PZ2015120204000019问题如下Excess stomarket returnt=a0+a1fault sprea-1+a2Term sprea-1+a3Pres party mmyt-1+etfault spreis equto the yielon Bbon minus the yielon Abon. Term spreis equto the yielon a 10-yeconstant-maturity US Treasury inx minus the yielon a 1-yeconstant-maturity US Treasury inx. Pres party mmy is equto 1 if the US Presint is a member of the mocratic Party an0 if a member of the RepublicParty.The regression is estimatewith 431 observations.Exhibit 1.Multiple Regression OutputExhibit 2. Table of the F-stribution (CriticValues for Right-HanTail Area Equto 0.05) Numerator: 1 annominator: 2 Is the regression mol a whole significant the 0.05 level?A.No, because the calculateF-statistic is less ththe criticvalue for F.B.Yes, because the calculateF-statistic is greater ththe criticvalue for F.C.Yes, because the calculateχ2 statistic is greater ththe criticvalue for χ2. B is correct.The F-test is useto termine if the regression mol a whole is significant.F = Mesquare regression (MSR) ÷ Mesquareerror (MSE)MSE = SSE/[n – (k + 1)] = 19,048 ÷ 427 = 44.60MSR = SSR/k = 1071 ÷ 3 = 357F = 357 ÷ 44.60 = 8.004The criticvalue for grees of freem of 3 an427 with α=0.05 (one-tail) is F = 2.63 from Exhibit 2. The calculateF is greater ththe criticvalue, anChiesa shoulrejethe null hypothesis thall regression coefficients are equto zero. 关于criticvalue查表怎么判断1和2？为什么不是1＝427，2＝3，因而得到criticvalue＝8.53。进而选A？考试时通常会给出t-critical和F-critical吗？
NO.PZ2015120204000019 问题如下 Excess stomarket returnt=a0+a1fault sprea-1+a2Term sprea-1+a3Pres party mmyt-1+etfault spreis equto the yielon Bbon minus the yielon Abon. Term spreis equto the yielon a 10-yeconstant-maturity US Treasury inx minus the yielon a 1-yeconstant-maturity US Treasury inx. Pres party mmy is equto 1 if the US Presint is a member of the mocratic Party an0 if a member of the RepublicParty.The regression is estimatewith 431 observations.Exhibit 1.Multiple Regression OutputExhibit 2. Table of the F-stribution (CriticValues for Right-HanTail Area Equto 0.05) Numerator: 1 annominator: 2 Is the regression mol a whole significant the 0.05 level? A.No, because the calculateF-statistic is less ththe criticvalue for F. B.Yes, because the calculateF-statistic is greater ththe criticvalue for F. C.Yes, because the calculateχ2 statistic is greater ththe criticvalue for χ2. B is correct.The F-test is useto termine if the regression mol a whole is significant.F = Mesquare regression (MSR) ÷ Mesquareerror (MSE)MSE = SSE/[n – (k + 1)] = 19,048 ÷ 427 = 44.60MSR = SSR/k = 1071 ÷ 3 = 357F = 357 ÷ 44.60 = 8.004The criticvalue for grees of freem of 3 an427 with α=0.05 (one-tail) is F = 2.63 from Exhibit 2. The calculateF is greater ththe criticvalue, anChiesa shoulrejethe null hypothesis thall regression coefficients are equto zero. 因为自变量多么？
NO.PZ2015120204000019 Yes, because the calculateF-statistic is greater ththe criticvalue for F. Yes, because the calculateχ2 statistic is greater ththe criticvalue for χ2. B is correct. The F-test is useto termine if the regression mol a whole is significant. F = Mesquare regression (MSR) ÷ Mesquareerror (MSE) MSE = SSE/[n – (k + 1)] = 19,048 ÷ 427 = 44.60 MSR = SSR/k = 1071 ÷ 3 = 357 F = 357 ÷ 44.60 = 8.004 The criticvalue for grees of freem of 3 an427 with α=0.05 (one-tail) is F = 2.63 from Exhibit 2. The calculateF is greater ththe criticvalue, anChiesa shoulrejethe null hypothesis thall regression coefficients are equto zero. 老师没有找到题目中k=3
NO.PZ2015120204000019 老师 虽然F-statistic is greater ththe criticvalue ，但是不知道拒绝域在左边还是右边啊？
