全部版块 我的主页
论坛 数据科学与人工智能 数据分析与数据科学 SAS专版
2894 1
2008-12-07

本人痛苦的自学计量和sas,伍德里奇的书看了挺多但课后计算机习题还没怎么做

最近抓紧解决习题,却现在卡在一道很简单的题上,周围没人学计量和sas,都不知道该怎么弄

于是上论坛请前辈赐教:

计量经济学导论现代观点第三版第四章习题

4.14 Refer to Problem 3.14. Now, use the log of the housing price as the dependent
variable:
log(price) =b0 +b1*sqrft +b2*bdrms+ u.
(i) You are interested in estimating and obtaining a confidence interval for
the percentage change in price when a 150-square-foot bedroom is
added to a house. In decimal form, this is  c1=150*b1+b2

原式有b0,b1,b2,三个参数,现在引入c1这个参数,使得c1=150*b1+b2,然后估计c1的值;我把b2用c1,b1替换,用sas输入

proc model data=homework.hprice2;
parm b0 b1 c1;
lprice=b0+b1*(sqrft-150*bdrms)+c1*bdrms;
fit lprice/ols;
run;

 命令怎么都弄不出结果,请问应该输入什么代码呢(我刚开始自学,还不太会用)

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

全部回复
2008-12-11 04:06:00

C1 is not a new parameter, the problem just wants you to find the change of price when change of sqft=150 and change of bdrms=1. I guess there should be data associated with the problem, if so you can do this.

1. Use linear regression and in the output find estimates for b0,b1,b2

   proc reg data=homework.hprice2;

   lprice=sqft bdms; run;

2. Now you have the estimates of price: log(price) =b0 +b1*sqrft +b2*bdrms

   Those parameter estimates measure the rate of change in lprice corresponding to a one-unit change in input variable. So the change of lprice is just 150*b1+1*b2.

Hope it helps.

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

相关推荐
栏目导航
热门文章
推荐文章

说点什么

分享

扫码加好友,拉您进群
各岗位、行业、专业交流群