开发者:上海品职教育科技有限公司 隐私政策详情

应用版本:4.2.11(IOS)｜3.2.5(安卓)APP下载

返回

大老王 · 2023年04月12日

T 的数额

  1. CFA II
  2. Quantitative

* 问题详情，请 查看题干

NO.PZ201709270100000406

问题如下：

6. Based on the data for the AR(1) model in Exhibits 1 and 2, Martinez can conclude that the:

选项：

A.

residuals are not serially correlated.

B.

autocorrelations do not differ significantly from zero.

C.

standard error for each of the autocorrelations is 0.0745.

解释：

C is correct. The standard error of the autocorrelations is calculated as 1T\frac{1}{\sqrt{T}}, where T represents the number of observations used in the regression. Therefore, the standard error for each of the autocorrelations is 1180\frac{1}{\sqrt{180}} = 0.0745. Martinez can conclude that the residuals are serially correlated and are significantly different from zero because two of the four autocorrelations in Exhibit 2 have a t-statistic in absolute value that is greater than the critical value of 1.97.

Choices A and B are incorrect because two of the four autocorrelations have a t-statistic in absolute value that is greater than the critical value of the t-statistic of 1.97.

请问本题中求 standard error中为什么T 或者说N 是180而不是181呢，我是拿1/ √181 这么算的

添加评论
1 个答案

星星_品职助教 · 2023年04月12日

同学你好，

1）理解角度：可以从AR模型的形式来理解这个数字。AR是自己和自己做回归，即Xt=b0+b1Xt-1。可以看出，如果一共有t个值，那么有一个值就要分给等式左侧的因变量（即Xt会占用一个值），用于等式右侧回归的自变量的值就只有t-1个；

2）解题角度：实际做题中并不用自己去数数字。常规情况下，题干中会给出一个表格，从表格中直接找到“observations”这一行的数字就可以用。因为无论用字母T还是N，公式的本质都是1/ √observations。

例如下面这种情况，直接代入1/ √65即可。

  • 1

    回答

  • 1

    关注

  • 365

    浏览
相关问题

NO.PZ201709270100000406 问题如下 6. Baseon the ta for the AR(1) mol in Exhibits 1 an2, Martinez cconclu ththe: resials are not serially correlate autocorrelations not ffer significantly from zero. stanrerror for eaof the autocorrelations is 0.0745. C is correct. The stanrerror of the autocorrelations is calculate 1T\frac{1}{\sqrt{T}}T​1​, where T represents the number of observations usein the regression. Therefore, the stanrerror for eaof the autocorrelations is 1180\frac{1}{\sqrt{180}}180​1​ = 0.0745. Martinez cconclu ththe resials are serially correlateanare significantly fferent from zero because two of the four autocorrelations in Exhibit 2 have a t-statistic in absolute value this greater ththe criticvalue of 1.97.Choices A anB are incorrebecause two of the four autocorrelations have a t-statistic in absolute value this greater ththe criticvalue of the t-statistic of 1.97. RT

2024-07-11 23:54 1 · 回答

NO.PZ201709270100000406 问题如下 6. Baseon the ta for the AR(1) mol in Exhibits 1 an2, Martinez cconclu ththe: resials are not serially correlate autocorrelations not ffer significantly from zero. stanrerror for eaof the autocorrelations is 0.0745. C is correct. The stanrerror of the autocorrelations is calculate 1T\frac{1}{\sqrt{T}}T​1​, where T represents the number of observations usein the regression. Therefore, the stanrerror for eaof the autocorrelations is 1180\frac{1}{\sqrt{180}}180​1​ = 0.0745. Martinez cconclu ththe resials are serially correlateanare significantly fferent from zero because two of the four autocorrelations in Exhibit 2 have a t-statistic in absolute value this greater ththe criticvalue of 1.97.Choices A anB are incorrebecause two of the four autocorrelations have a t-statistic in absolute value this greater ththe criticvalue of the t-statistic of 1.97. 但是对于表2，我有点疑问，比如AR1和AR2存在序列相关，但是AR3和AR4不存在的话？可以得出一个什么结论？比如我们可以用AR3或者AR4模型吗？

2022-11-15 09:01 1 · 回答

NO.PZ201709270100000406 6. Baseon the ta for the AR(1) mol in Exhibits 1 an2, Martinez cconclu ththe: resials are not serially correlate autocorrelations not ffer significantly from zero. stanrerror for eaof the autocorrelations is 0.0745. C is correct. The stanrerror of the autocorrelations is calculate1T\frac{1}{\sqrt{T}}T ​1​, where T represents the number of observations usein the regression. Therefore, the stanrerror for eaof the autocorrelations is 1180\frac{1}{\sqrt{180}}180 ​1​ = 0.0745. Martinez cconclu ththe resials are serially correlateanare significantly fferent from zero because two of the four autocorrelations in Exhibit 2 have a t-statistic in absolute value this greater ththe criticvalue of 1.97. Choices A anB are incorrebecause two of the four autocorrelations have a t-statistic in absolute value this greater ththe criticvalue of the t-statistic of 1.97. t检验有些lag拒绝 有些没有拒绝不是肯定有不等于0的么？ regectHo 大概有哪几种表示方法可以总结下么

2021-12-03 15:03 1 · 回答

NO.PZ201709270100000406 6. Baseon the ta for the AR(1) mol in Exhibits 1 an2, Martinez cconclu ththe: resials are not serially correlate autocorrelations not ffer significantly from zero. stanrerror for eaof the autocorrelations is 0.0745. C is correct. The stanrerror of the autocorrelations is calculate1T\frac{1}{\sqrt{T}}T ​1​, where T represents the number of observations usein the regression. Therefore, the stanrerror for eaof the autocorrelations is 1180\frac{1}{\sqrt{180}}180 ​1​ = 0.0745. Martinez cconclu ththe resials are serially correlateanare significantly fferent from zero because two of the four autocorrelations in Exhibit 2 have a t-statistic in absolute value this greater ththe criticvalue of 1.97. Choices A anB are incorrebecause two of the four autocorrelations have a t-statistic in absolute value this greater ththe criticvalue of the t-statistic of 1.97. 如题，请问老师检验是否有autocorrelation为何不用方法？

2021-08-11 17:52 1 · 回答