Nov 2016 data error?

I am trying to analyze the 2016 November Supplement and am using Stata. I’ve followed the download directions as described by your website. However, there appears to be a problem with the data. When I look at the variable “voted” I get the following output (see below). There seems to be extra values (those coded as 3 or higher) included since the two main categories should be “Did not vote” and “vote” Is this a data error or do you think I have done something incorrectly during the downloading process?


. tab voted

Voted for the |
most recent |
November |
election | Freq. Percent Cum.
----------------±----------------------------------
-9 | 1 0.15 0.15
-8 | 2 0.30 0.45
-7 | 9 1.35 1.79
-6 | 1 0.15 1.94
-4 | 2 0.30 2.24
-1 | 2 0.30 2.54
0 | 128 19.13 21.67
Did not vote | 37 5.53 27.20
Voted | 44 6.58 33.78
3 | 29 4.33 38.12
4 | 22 3.29 41.41
5 | 25 3.74 45.14
6 | 26 3.89 49.03
7 | 28 4.19 53.21
8 | 29 4.33 57.55
9 | 35 5.23 62.78
11 | 7 1.05 63.83
12 | 11 1.64 65.47
14 | 6 0.90 66.37
15 | 2 0.30 66.67
17 | 1 0.15 66.82
18 | 1 0.15 66.97
19 | 2 0.30 67.26
21 | 4 0.60 67.86
22 | 4 0.60 68.46
23 | 2 0.30 68.76
24 | 6 0.90 69.66
25 | 16 2.39 72.05
26 | 1 0.15 72.20
27 | 3 0.45 72.65
28 | 4 0.60 73.24
29 | 2 0.30 73.54
32 | 8 1.20 74.74
33 | 1 0.15 74.89
34 | 3 0.45 75.34
35 | 5 0.75 76.08
37 | 1 0.15 76.23
38 | 2 0.30 76.53
39 | 2 0.30 76.83
40 | 1 0.15 76.98
41 | 1 0.15 77.13
42 | 1 0.15 77.28
44 | 2 0.30 77.58
45 | 1 0.15 77.73
46 | 1 0.15 77.88
47 | 2 0.30 78.18
48 | 5 0.75 78.92
50 | 2 0.30 79.22
53 | 5 0.75 79.97
54 | 1 0.15 80.12
55 | 3 0.45 80.57
56 | 1 0.15 80.72
58 | 3 0.45 81.17
60 | 3 0.45 81.61
61 | 1 0.15 81.76
62 | 2 0.30 82.06
63 | 1 0.15 82.21
64 | 6 0.90 83.11
66 | 4 0.60 83.71
67 | 3 0.45 84.16
68 | 2 0.30 84.45
69 | 5 0.75 85.20
70 | 2 0.30 85.50
72 | 2 0.30 85.80
74 | 9 1.35 87.14
75 | 2 0.30 87.44
78 | 7 1.05 88.49
79 | 2 0.30 88.79
80 | 4 0.60 89.39
81 | 2 0.30 89.69
82 | 4 0.60 90.28
83 | 3 0.45 90.73
84 | 7 1.05 91.78
85 | 3 0.45 92.23
86 | 6 0.90 93.12
87 | 2 0.30 93.42
88 | 17 2.54 95.96
90 | 3 0.45 96.41
91 | 2 0.30 96.71
93 | 1 0.15 96.86
94 | 2 0.30 97.16
95 | 6 0.90 98.06
Refused | 6 0.90 98.95
Don’t know | 2 0.30 99.25
No Response | 1 0.15 99.40
Not in universe | 4 0.60 100.00
----------------±----------------------------------
Total | 669 100.00

I downloaded your 2016 November Supplement extract, summarized the data, and the values I’m seeing for VOTED look good to me. Can you provide the code you used in Stata to get your output? You might also find these Data Training Exercises on how to use IPUMS data using various statistical packages useful.

Hi Grace,
Thanks so much, looks like I was missing the decompression step when reading the file into Stata. Thank you for the quick response.
Natalie