计量经济学第三章.ppt

因此： 虽然我们并没有解释为什么卡方随机变量V在统计上独立于最小二乘估计量b1和b2，但这确实是成立的。 因此，V和标准正态分布随机变量Z是独立的。 Eq. 3A.4 3A Derivation of the t-Distribution 通过将标准正态分布随机变量Z~N(0, 1)除以独立的卡方随机变量V ~ χ2(m) 除以自由度m后的平方根，得到服从t分布的随机变量： 3A Derivation of the t-Distribution 利用Z和V的公式（分别来自于Eq. 3A.1 和 Eq. 3A.4），我们得到: Eq. 3A.5 3A Derivation of the t-Distribution 3B Distribution of the t-Statistic under H1 To examine the distribution of the t-statistic in Eq. 3.7 when the null hypothesis is not true, suppose that the true β2 = 1 We can show that: If β2 = 1 and we incorrectly hypothesize that β2 = c, then the numerator in Eq. 3A.5 that is used in forming Eq. 3.7 has the distribution: Since its mean is not zero, the distribution of the variable in Eq. 3B.1 is not standard normal, as required in the formation of a t-random variable Eq. 3B.1 3B Distribution of the t-Statistic under H1 3C Monte Carlo Simulation When studying the performance of hypothesis tests and interval estimators it is necessary to use enough Monte Carlo samples so that the percentages involved are estimated precisely enough to be useful For tests with probability of Type I error α = 0.05 we should observe true null hypotheses being rejected 5% of the time For 95% interval estimators we should observe that 95% of the interval estimates contain the true parameter values We use M = 10,000 Monte Carlo samples so that the experimental error is very small 3C.1 Repeated Sampling Properties of Interval Estimators Table 3C.1 Results of 10000 Monte Carlo Simulations 3C Monte Carlo Simulation The lesson is, that in many repeated samples from the data generation process, and if assumptions SR1–SR6 hold, the procedure for constructing 95% interval estimates ‘‘works’’ 95% of the time 3C.1 Repeated Sampling Properties of Interval Estimators 3C Monte Carlo Simulation The lesson is that in many repeated samples from the data generation process, and if assumptions SR1–SR6 hold, the procedure for testing a true null hypot