题目是英语的,教育和婚姻变量没labels,请根据下边副本里的价值标签给教育和婚姻贴上标签
The variables –education– and –married– are numeric but do not have value
labels, yet. Label the values of the two variables according to those given below
in the Appendix.
Value labels
–married–:
1 - married
2 - not married
–education–: 1 - tertiary
2 - unfinished tertiary
3 - special secondary
4 - secondary
5 - 7 years of schooling 6 - primary
7 - can read and write 8 - can read
9 - illiterate
10 - child aged 0-8 99 - missing value
cd /Victor/stata
//二
//1.a
sysuse "auto.dta",clear
foreach num of numlist 1/74{
export excel using "auto`num'.xlsx" in `num'
}
//1.b
foreach num of numlist 1/74{
import excel "auto`num'", clear
save "auto`num'.dta", replace
}
//将excel转换成dta格式
use "auto1.dta",clear
foreach num of numlist 2/70{
append using "auto`num'.dta"
}
save "auto_new.dta", replace
//1.c
foreach num of numlist 1/74{
erase "auto`num'.xlsx"
}
//2(因为我的stata软件无法识别跨行命令,只能一长串写在一行)
use "auto_new.dta",clear
twoway(scatter weight mpg if foreign == 0, mcolor(navy blue) msymbol(x)) (scatter weight mpg if foreign == 1, mcolor(red)) , legend(on order(1 "foreign" 2 "domestic") ring(0)) title("The Relatonship between Car Weight and MPG") ylabel(1000 2000 3000(2000)5000) xlabel(10(5)35)
//3
sysuse "nlsw88.dta",clear
tabstat wage hours ttl_exp tenure ,by(union) stat(n mean sd min median) c(s)
//4
sysuse "nlsw88.dta",clear
order wage hours ttl_exp tenure collgrad
foreach v of varlist wage-collgrad{
ttest `v',by(union)
}
//5
sysuse "nlsw88.dta",clear
reg wage age race industry occupation ttl_exp hours
ssc install logout
logout, save(result_2017302330037.xlsx) excel dec(3) replace:reg wage age race industry occupation ttl_exp hours
//三
sysuse "firm.dta",clear
sort ID date ipc patent_ID
//2
replace firm_name = subinstr(firm_name, "有限责任公司"," ",.)
replace firm_name = subinstr(firm_name, "集团股份有限公司"," ",.)
replace firm_name = subinstr(firm_name, "股份有限公司"," ",.)
//3
//计算每个企业每年专利数量总和
use "firm.dta",clear
encode patent_ID ,gen(patent_ID1)
bys ID date : egen num_patent=count(patent_ID1)
//计算不重复的领域数
duplicates drop ID date ipc,force
bys ID date: egen ipc_sum=count(ipc)