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

qygeorge05 · 2023年04月01日

为何这里不用研究每个变量系数的t值?

NO.PZ2015120204000013

问题如下:

Based on past research, Hansen selects the following independent variables to predict IPO initial returns:

Underwriter rank = 1–10, where 10 is highest rank

Pre-offer price adjustment (Expressed as a decimal) = (Offer price – Initial filing price)/Initial filing price

Offer size ($ millions) = Shares sold × Offer price

Fraction retained (Expressed as a decimal) = Fraction of total company shares retained by insiders

Hansen’s Regression Results Dependent Variable: IPO Initial Return (Expressed in Decimal Form, i.e., 1% = 0.01)

The upcoming IPO has the following characteristics:

l underwriter rank = 6;

l pre-offer price adjustment = 0.04;

l offer size = $40 million;

l fraction retained = 0.70.

Based on Hansen’s regression, the predicted initial return for the upcoming IPO is closest to:

选项:

A.

0.0943.

B.

0.1064.

C.

0.1541.

解释:

C is correct.

The predicted initial return (IR) is:

IR = 0.0477 + (0.0150 × 6) + (0.435 × 0.04) – (0.0009 × 40) + (0.05 × 0.70) = 0.1541

老师好!如题,a=1%对应检验的t值是2.58左右,为什么不用将每个变量系数的t值与它对比以判断每个自变量是否有效/显著?谢谢

1 个答案
已采纳答案

星星_品职助教 · 2023年04月01日

同学你好, 题干要求“Based on Hansen’s regression”,所以直接按照Hansen的原方程进行代数计算就可以,不需要考虑系数的问题。 绝大多数预测Y值的题目都是这种考法,只有少数题目会在题干中明确标出:只根据显著的系数进行计算。 只有在这个前提下,才需要去考虑每个系数的假设检验是否显著。