Looping a regression command sequentially by observation and storing each model.

[Rob Winter]

Hi all,

Apologies if this is very simple or has been asked before. I have searched through many topics and have struggled to find an answer. Any help is greatly appreciated.

I am trying to run a regression command for each observation in a dataset, increasing by one observation each time. It may be more useful if I post the code I have that works so far:

foreach x in 1/11 1/12 1/13 1/14 1/15 1/16 1/17 1/18 1/19 1/20 1/21 1/22 1/23 1/24 1/25 1/26 1/27 1/28 1/29 1/30 1/31 1/32 1/33 1/34 1/35 {

reg DV IV1 IV2 IV3 in `x'
}

This works (although I am sure there must be a more efficient way of doing this) but I believe it is creating errors down the line when I try to add the following:

 foreach x in 1/11 1/12 1/13 1/14 1/15 1/16 1/17 1/18 1/19 1/20 1/21 1/22 1/23 1/24 1/25 1/26 1/27 1/28 1/29 1/30 1/31 1/32 1/33 1/34 1/35 {

reg DV IV1 IV2 IV3 in `x'

est store model_`x'
}

When attempting this code, it returns the error of:

/ invalid name
11 invalid name

I interpret this as: it's trying to store my estimate, but having / in the estimate name is causing the error?

Although, I know I could be completely wrong here. I am very much a Stata beginner and I am making a lot of errors along the way!

Any help is greatly appreciated!

Thanks

[Fei Wang]

Rob, an example code as follows.

sysuse auto, clear

forvalues obs = 11/35 {
    reg price mpg if _n <= `obs'
    est store model_`obs' 
}

[Carlo Lazzaro]

Rob:
you may also want to take a look at -statsby-.

[Rob Winter]

You guys are brilliant! Thank you.

[Nick Cox]

The error in #1 is that the slash may not be part of a name.

Even so, this is going to be a bit (or in other circumstances a lot) faster:

sysuse auto, clear  

forvalues obs = 11/35 {    
     reg price mpg in 1/`obs'    
     est store model_`obs'  
}

[Carlo Lazzaro]

Rob:
just applying a very minor surgery on a very interesting Nick Cox 's post (thanks Nick!) on another forum he contributes to (https://stackoverflow.com/questions/...coefficients):

. sysuse auto.dta, clear
(1978 Automobile Data)

. tempname myresults

. postfile `myresults' num_obs intercept mpg_coeff mpg_se using myresults.dta

.
. quietly forval x = 2(1)74 {
.
. regress price mpg length gear_ratio i.foreign in 1/`x'
.
. post `myresults' (`x') (`=_b[_cons]') (`=_b[mpg]') (`=_se[mpg]')
.
. }

.
. postclose `myresults'

.
. use myresults

.
. list

+-------------------------------------------+
| num_obs interc~t mpg_coeff mpg_se|
|-------------------------------------------|
1. | 2 6959 -130 0 |
2. | 3 4812.333 -173.3333 0 |
3. | 4 3370.359 -130.31 0 |
4. | 5 1161.01 -185.7874 310.1894 |
5. | 6 4342.634 -321.1453 306.7237 |
|-------------------------------------------|
6. | 7 1729.177 -.4641546 116.8822 |
7. | 8 1979.505 -3.478176 102.0471 |
8. | 9 3922.224 -299.1741 289.8163 |
9. | 10 5575.879 -270.3074 290.458 |
10. | 11 8045.566 -299.5507 311.4781 |
|-------------------------------------------|
11. | 12 21283.88 -462.3358 382.374 |
12. | 13 13031.65 110.2493 376.0489 |
13. | 14 13687.06 17.89214 303.7362 |
14. | 15 14237.47 37.40229 309.9285 |
15. | 16 15862.72 -20.57691 298.0098 |
|-------------------------------------------|
16. | 17 18497.53 -78.16478 277.9452 |
17. | 18 17663.69 -113.0256 269.2007 |
18. | 19 15694.79 -107.9036 276.4348 |
19. | 20 10888.18 -15.41563 271.5362 |
20. | 21 11114.55 -35.95477 279.8067 |
|-------------------------------------------|
21. | 22 9707.108 -10.38597 273.8028 |
22. | 23 10054.53 -11.01054 266.3543 |
23. | 24 12848.46 -22.28206 261.4966 |
24. | 25 12749 -19.8053 249.3439 |
25. | 26 11741.51 -40.52274 246.4133 |
|-------------------------------------------|
26. | 27 11277.44 -84.12788 250.2435 |
27. | 28 18861.74 -212.315 244.9058 |
28. | 29 16204.84 -192.1921 239.9254 |
29. | 30 17197.74 -162.5354 238.1236 |
30. | 31 15372.99 -159.089 240.3489 |
|-------------------------------------------|
31. | 32 13584.69 -160.6033 241.8861 |
32. | 33 13656.96 -140.6935 235.7217 |
33. | 34 14236.24 -134.7314 232.8587 |
34. | 35 13316.22 -113.5074 203.3133 |
35. | 36 13403.14 -111.648 200.0028 |
|-------------------------------------------|
36. | 37 13548.01 -108.5492 197.0977 |
37. | 38 15606.05 -131.2431 194.191 |
38. | 39 15901.91 -127.9984 191.3153 |
39. | 40 15804.45 -139.3503 187.0644 |
40. | 41 16824.46 -148.5528 185.4286 |
|-------------------------------------------|
41. | 42 16194.86 -124.7119 178.6325 |
42. | 43 15147.52 -78.84817 160.0226 |
43. | 44 15567.19 -93.93787 158.3768 |
44. | 45 11405.17 -68.06149 160.3926 |
45. | 46 11650.25 -61.63638 157.4141 |
|-------------------------------------------|
46. | 47 12379.09 -68.92999 155.3936 |
47. | 48 12375 -66.1585 152.3788 |
48. | 49 12499.16 -65.63114 150.7698 |
49. | 50 12590.24 -63.47343 149.3211 |
50. | 51 12928.23 -62.88809 147.8992 |
|-------------------------------------------|
51. | 52 12592.28 -69.14545 146.4715 |
52. | 53 12592.28 -69.14545 146.4715 |
53. | 54 12777.39 -71.34354 144.4498 |
54. | 55 11348.56 -46.87218 142.1075 |
55. | 56 11344.62 -45.21507 140.4135 |
|-------------------------------------------|
56. | 57 13295.98 -88.66376 122.9301 |
57. | 58 12558.13 -81.63242 122.5333 |
58. | 59 12581.88 -82.92133 121.1154 |
59. | 60 9252.308 -45.91871 118.5079 |
60. | 61 8607.44 -59.23783 117.826 |
|-------------------------------------------|
61. | 62 7754.326 -60.0155 117.1789 |
62. | 63 7848.948 -62.71835 115.6931 |
63. | 64 9341.412 -131.3444 113.446 |
64. | 65 8713.549 -124.0916 110.9693 |
65. | 66 9109.488 -130.7823 101.7588 |
|-------------------------------------------|
66. | 67 7188.92 -110.3453 100.3528 |
67. | 68 7676.8 -135.2735 96.7711 |
68. | 69 6146.195 -118.3158 95.47392 |
69. | 70 5978.788 -121.315 94.76587 |
70. | 71 4076.07 -83.25227 84.51991 |
|-------------------------------------------|
71. | 72 4041.676 -82.50186 83.24106 |
72. | 73 4341.403 -89.66816 82.50635 |
73. | 74 4715.698 -94.406 82.50603 |
+-------------------------------------------+

.