楼主: 7113341832
2255 1

[问答] 关于交互项的经济解释的几个问题 [推广有奖]

  • 0关注
  • 0粉丝

博士生

46%

还不是VIP/贵宾

-

威望
0
论坛币
1173 个
通用积分
48.7119
学术水平
0 点
热心指数
0 点
信用等级
0 点
经验
1465 点
帖子
176
精华
0
在线时间
177 小时
注册时间
2019-11-2
最后登录
2025-11-24

楼主
7113341832 发表于 2022-1-27 16:01:15 |AI写论文

+2 论坛币
k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群
赵安豆老师微信:zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

感谢您参与论坛问题回答

经管之家送您两个论坛币!

+2 论坛币
最近读了一篇文章,文章中有几个关于交互项经济解释的记算,是这么说的:
The  mean cumulative number of upgrade experiments among firms with high-end machines is 2.21,
and the average fraction of low-end products in this sample is 0.67. Therefore the coefficient on
the interaction term of 0.087 implies that one additional upgrade experiment, conditional on the
mean fraction of low-end products, was associated with a 5.8 percentage point higher output
growth. This is slightly over 30 percent of the interquartile difference in growth rates across
firms. Similarly, a one-standard-deviation increase in the fraction of low-end products was
associated with a 6.3 percent higher total output growth rate at the mean number of cumulative
upgrade experiments.


楼主实在没明白这些数字是怎么的出来,背后的涵义是什么完全一窍不通,希望有大佬指点迷津,不胜感激!
二维码

扫码加我 拉你入群

请注明:姓名-公司-职位

以便审核进群资格,未注明则拒绝

关键词:经济解释 交互项 Experiments conditional coefficient

沙发
917968079 发表于 2022-1-28 20:40:28
5.8≈0.087×0.67
6.3的算法类似,但最后还要乘the fraction of low-end products的标准差

您需要登录后才可以回帖 登录 | 我要注册

本版微信群
加好友,备注jltj
拉您入交流群
GMT+8, 2026-1-3 19:00