aileen20180623 · 2019年01月13日
* 问题详情，请 查看题干
问题如下图：
选项：
A. 
B. 
C. 
解释：
1.这道题不可以用t检验去估计一下吗？ 我记得老师视频里说过，t可以估计单还是需要DF检验，这里面的lag1 和lag2 的t statistic分别是5.。。和3.。。说明b1可能存在1 的情况，但还是需要进一步DF 检验，难道不对吗？
2. DW是不能用在AR里，所以c是错误的，对吧？
3. 为什么B对？怎么解释？
4.这种题目不是应该看数据吗？ 是这道题没有相关数据是吗，这就推翻我的问题1？
5.我不知懂着手点，以后碰见先看哪个点去判断，能否讲一讲？
菲菲_品职助教 · 2019年01月21日
同学你好，其实是你想的太复杂了。
我们先来看题目，问M的结论1对不对。
我们再去case里面找到相关的结论1：
Conclusion 1: The time series for WTI oil prices is covariance stationary.
也就是让我们来判断这个WTI oil prices的时间序列是不是协方差平稳的。
那我们要怎么来判断呢。
其实这道题考的是构成协方差平稳的三个条件：
•Constant and finite expected value of the time series
•Constant and finite variance of the time series
•Constant and finite covariance with leading or lagged values
这时候我们再去看题目，会发现题目里面有一句跟这个有直接联系的话：
After reviewing the time-series data, Martinez determines that the mean and variance of the time series of oil prices are not constant over time.
所以我们根据这句话就可以直接判断M的结论1是错误的了。并且理由是时间序列的均值和方差是会变的。
所以这道题目根本就不需要用数据来进行判断，其实反而是一道概念题。
所以当我们拿到题目时，首先要看清题目问的是什么，想一想，再去case里找找相应的语句。
而不是直接一拿到题就去看数据，形成数据为先的固有思维。
不过也不用太担心，case题做多了自然也就会发现相应的做题规律了。加油~
NO.PZ201709270100000404问题如下 4. Martinez’s Conclusion 1 is: correct. incorrebecause the meanvarianof WTI oil prices are not constant over time. C.incorrebecause the rbin–Watson statistic of the AR(2) mol is greater th1.75. B is correct. There are three requirements for a time series to covarianstationary. First, the expectevalue of the time series must constant anfinite in all perio. Secon the varianof the time series must constant anfinite in all perio. Thir the covarianof the time series with itself for a fixenumber of perio in the past or future must constant anfinite in all perio. Martinez conclus ththe meanvarianof the time series of WTI oil prices are not constant over time. Therefore, the time series is not covarianstationary. 麻烦一下C，不太懂为啥不选它
NO.PZ201709270100000404 问题如下 4. Martinez’s Conclusion 1 is: correct. incorrebecause the meanvarianof WTI oil prices are not constant over time. C.incorrebecause the rbin–Watson statistic of the AR(2) mol is greater th1.75. B is correct. There are three requirements for a time series to covarianstationary. First, the expectevalue of the time series must constant anfinite in all perio. Secon the varianof the time series must constant anfinite in all perio. Thir the covarianof the time series with itself for a fixenumber of perio in the past or future must constant anfinite in all perio. Martinez conclus ththe meanvarianof the time series of WTI oil prices are not constant over time. Therefore, the time series is not covarianstationary. 这题开头确实是说了meancovarianis not constant， 然后他开始做mol来验证。然后一堆验证后得出一个新的结论 “meancovarianis constant ” 但是答案居然说因为他开头说了“meancovarianis not constant” 所以得选b。所以请问这道题有更严密的逻辑吗？
4. Martinez’s Conclusion 1 is: correct. incorrebecause the meanvarianof WTI oil prices are not constant over time. incorrebecause the rbin–Watson statistic of the AR(2) mol is greater th1.75. B is correct. There are three requirements for a time series to covarianstationary. First, the expectevalue of the time series must constant anfinite in all perio. Secon the varianof the time series must constant anfinite in all perio. Thir the covarianof the time series with itself for a fixenumber of perio in the past or future must constant anfinite in all perio. Martinez conclus ththe meanvarianof the time series of WTI oil prices are not constant over time. Therefore, the time series is not covarianstationary. 这题从Exhibit 2看出是有AR现象，是不是有没有AR现象和covariance-stationary 3个条件是否constant & finite没有关系？ 但如果有ARCH现象和单位根，那么则不是 covariance-stationary。还是只有单位根会违背 covariance-stationary ？ 这里学的有点混乱，谢谢
4. Martinez’s Conclusion 1 is: correct. incorrebecause the meanvarianof WTI oil prices are not constant over time. incorrebecause the rbin–Watson statistic of the AR(2) mol is greater th1.75. B is correct. There are three requirements for a time series to covarianstationary. First, the expectevalue of the time series must constant anfinite in all perio. Secon the varianof the time series must constant anfinite in all perio. Thir the covarianof the time series with itself for a fixenumber of perio in the past or future must constant anfinite in all perio. Martinez conclus ththe meanvarianof the time series of WTI oil prices are not constant over time. Therefore, the time series is not covarianstationary. 这个结论是从题目中哪些数据中看出来的？
4. Martinez’s Conclusion 1 is: correct. incorrebecause the meanvarianof WTI oil prices are not constant over time. incorrebecause the rbin–Watson statistic of the AR(2) mol is greater th1.75. B is correct. There are three requirements for a time series to covarianstationary. First, the expectevalue of the time series must constant anfinite in all perio. Secon the varianof the time series must constant anfinite in all perio. Thir the covarianof the time series with itself for a fixenumber of perio in the past or future must constant anfinite in all perio. Martinez conclus ththe meanvarianof the time series of WTI oil prices are not constant over time. Therefore, the time series is not covarianstationary. the meanvarianof the time series of WTI oil prices are not constant over time. ---这句话从哪个指标可以看出来？
