Meaning of different code

[Kendal zhang]

1. Create the dummies and estimate
levelsof year, local(time)
foreach t of local time {
local y_rr = `t' - 1975
gen intra_nafta`t' = yr`y_rr' * intra_nafta
gen imp_nafta_rest`t' = yr`y_rr' * imp_nafta_rest
}

xtreg lnV lncGDP lnpGDP lnD yr* intra_nafta* imp_nafta_rest*, fe vce(robust)

Who can help me explain how y_rr is defined in the above code? What meaning of yr`y_rr' * intra_nafta ? Thank you!

[Nick Cox]

The question omits the context, namely the data structure you're using. The code implies that your data include variables like

yr5  yr10 yr15

for something or other in years 1980 1985 1990 and so on. That is, data for 1980 are stored in a variable yr5 (5 = 1980 - 1975), and so on. You may have many more years. At the same time, it seems odd that there is evidently a variable year too, so I can't follow whether your layout is long or wide.

The code is calculating interaction terms in a loop before calling up xtreg

On the other hand, if you're reading someone else's code somewhere, they should describe their data structure -- if they did a good job.

There are many introductions to loops and local macros in Stata. One familiar to me is https://journals.sagepub.com/doi/pdf...36867X20976340 (note the correction at https://journals.sagepub.com/doi/pdf...6867X211025839)

[Kendal zhang]

My time period is 1985-2004. I'm still a little confused about y_rr = `t' - 1975, and can we write in other forms,for example, y_rr = `t' - 1970 or other forms? ( This paper want to study the impact of Free Trade Zone on trade）

The question omits the context, namely the data structure you're using. The code implies that your data include variables like

yr5 yr10 yr15

for something or other in years 1980 1985 1990 and so on. That is, data for 1980 are stored in a variable yr5 (5 = 1980 - 1975), and so on. You may have many more years. At the same time, it seems odd that there is evidently a variable year too, so I can't follow whether your layout is long or wide.

The code is calculating interaction terms in a loop before calling up xtreg

On the other hand, if you're reading someone else's code somewhere, they should describe their data structure -- if they did a good job.

There are many introductions to loops and local macros in Stata. One familiar to me is https://journals.sagepub.com/doi/pdf...36867X20976340 (note the correction at https://journals.sagepub.com/doi/pdf...6867X211025839)

[Nick Cox]

To get another answer, please tell us what variables you have by showing the results of

ds yr* 

[Kendal zhang]

label var ccode "Country code"
label var pcode "Partner code"
label var year "Year"
label var exp_tv "value of exported goods"
label var exp_q "physical aount of exported goods ( in kg)"
label var exp_uv "average Unit value of exported goods"
label var imp_tv "value of imported goods"
label var imp_q "physical aount of imported goods ( in kg)"
label var imp_uv "average Unit value of imported goods"
label var km "bilateral distance"
label var name "country name"
label var lang1 "first official language"
label var lang2 "second official language"
label var cgdp_c2000 "home's real GDP, year base = 2000"
label var cgdp_current "home's current GDP"
label var cgdp_pcppp_c2000 "home's real GDP per capita in PPP, year base = 2000"
label var cgdp_pcppp_current "home's current GDP per capita in PPP"


label var com_lang "1 if common language"
label var border "1 if common border"
label var ldlock "1 if landlocked"
label var island "1 if island"label var exp_tv "value of exported goods"

gen nafta = (ccode=="CAN" | ccode=="MEX" | ccode=="USA")
label var nafta "1 if home is nafta member"
gen pnafta = (pcode=="CAN" | pcode=="MEX" | pcode=="USA")
label var pnafta "1 if partner is nafta member"
gen intra_nafta = (ccode=="CAN" | ccode=="MEX" | ccode=="USA") & (pcode=="CAN" | pcode=="MEX" | pcode=="USA")
replace intra_nafta = 0 if year < 1994
label var intra_nafta "1 if trade bewteen nafta members"
gen imp_nafta_rest = (ccode=="CAN" | ccode=="MEX" | ccode=="USA") & (pcode!="CAN" & pcode!="MEX" & pcode!="USA")
replace imp_nafta_rest = 0 if year < 1994
label var imp_nafta_rest "1 if nafta's imports from the rest of the world"


These are the related variables.

[Nick Cox]

Sorry, but #5 does not answer #4.

ds yr*

is a Stata command. If the code in #1 applies to your data then its results should include variables whose names begin with yr.

Detail: It is just possible that the references are to scalars. in which case

scalar list

should list them.

[Kendal zhang]

ccode imp_tv cgdp_c2000 pgdp_pc~2000 island
pcode imp_q cgdp_current pgdp_pcppp~t nafta
year imp_uv cgdp_pc~2000 km pnafta
name exp_tv cgdp_pcppp~t com_lang intra_nafta
lang1 exp_q pgdp_c2000 border imp_nafta_~t
lang2 exp_uv pgdp_current ldlock

Here are the variables.

[Nick Cox]

Thanks for #7. My only guess now, as in #2.is that the code in #1 is someone else's code referring to a different data structure.

[Kendal zhang]

OK， thank you very much！