How to download data and set up a new data set in Stata

Part B: How to download data and set up a new data set in Stata

ADD NEW VARIABLE

1. Go at: http://data.worldbank.org/
2. Have a look at the window and choose: Indicators
3. Go to the set of indicators with title: Economy & growth and choose:GDP (current US$)
4. Choose: download data\EXCEL
5. Save the new file at your desktop as gdp_original
6. Mark and delete the rows 1-3 and do the same for the columns B up to AR. So, you have to remain with the years 2000-2017 (i.e. 18 years)
7. Save the file as: gdp
8. Mark the cells from B1-P1 with the years
9. Ctrl+f to open the find and replace window
10. Find: 20; Replace with: newvarname20 let say: gdp20 and choose: replace all
11. Save the file as: gdp
12. Open a stata file and open the menu: FileàimportàExcel spreadsheet: import first row as variable names-browse-ok (or select all the table copy and paste it into the data editor of a new stata file).
13. Choose that the first line contains variables names.
14. Open the data editor in stata. Open the menu: DataàVariables manager.
15. Choose all the variables of this list on your left except the first.Choose on your right (format) createàtotal digits: 15, to increase the numbers that STATA shows to you. Alternatively you can type the command: format %15.0g gdp2000-gdp2017 at the command line.
16. Create an index variable: generate cnameid=_n
17. Rename the variable CountryName typing the command: rename CountryNamecname
18. Place the variable cnameid before the variable cname: order cnameid, before(cname)
19. Add label for the variable cnameid: label variable cnameid “Country id”
20. Save the stata file as gdp
21. Open the data editor and have look of your dataset.
22. Reshape your data from wide to long giving the order: reshape long  gdp, i( cnamecnameid) j(year)
23. Open the data editor and have a look again.
24. Sort your data set by cnameid: sort cnameid year
25. Save the stata file as gdp_final
26. Open the data editor and have a look again.

ADD NEW VARIABLE

27. Go at: http://data.worldbank.org/
28. Go to the set of indicators with title: Economy & growth and choose: Foreign direct investment, net inflows (BoP, current US$)
29. Choose: download data\EXCEL
30. Save the new file at your desktop as fdi_original
31. Mark and delete the rows 1-3 and do the same for the columns B up to AR. So, you have to remain with the years 2000-2017 (i.e. 18 years)
32. Save the file as: fdi
33. Mark the cells from B1-P1 with the years
34. Ctrl+f to open the find and replace window
35. Find: 20; Replace with: newvarname20 let say: fdi20 and choose: replace all
36. Save the file as: fdi
37. Open a stata file and open the menu: FileàimportàExcel spreadsheet: import first row as variable names-browse-ok (or select all the table copy and paste it into the data editor of a new stata file).
38. Choose that the first line contains variables names
39. Open the data editor in stata. Open the menu: DataàVariables manager.
40. Choose all the variables of this list on your left except the first.Choose on your right (format) createàtotal digits: 15, to increase the numbers that STATA shows to you. Alternatively, you can type the command: format %15.0g fdi2000-fdi2017 at the command line.
41. Create an index variable: generate cnameid=_n
42. Rename the variables CountryNamewith:rename CountryNamecname
43. Place the variable cnameid before the variable cname: order cnameid, before(cname)
44. Add label for the variable cnameid: label variable cnameid “Country id”
45. Save the stata file as fdi
46. Open the data editor and have look of your dataset.
47. Reshape your data from wide to long giving the order: reshape long  fdi, i(cnamecnameid) j(year)
48. Open the data editor and have a look again.
49. Sort your data set by cnameid: sort cnameid year
50. Save the stata file as fdi_final(pay attention: you must save the file in the same folder you saved the gdp_final.dta).
51. Open the data editor and have a look again.
52. Close the fdi_final.dta
53. Open the stata file gdp_final
54. To merge data from the fdi.dta into the dataset of gdp.dta give the order: merge 1:1 cname year using fdi_final
55. Put the year variable at the beginning: order year cnameid, before(cname)
56. Sort your dataset by cnameid year: sort cnameid year
57. Delete an unnecessary variable: drop _merge
58. label variable gdp “Gross domestic product”
59. label variable fdi “Foreign direct investment”
60. Save the new file as:merged_data

Before running panel data analysis (please leave these steps for the end of the semester and after the completion of our lecture about panel data analysis)

61. Denote to the program that you use panel data by giving the order: xtsetcnameid year
62. Run: xtreggdpfdi,fe r

Find out more useful information at:http://dss.princeton.edu/training/