From Survey to Data to Analysis

1
From Survey to Data to Analysis
Providing Social Science Data Services Jim
Jacobs, 2008
2
The Survey Instument
Survey instrument Q1. enter zip code Q2.
enter Rs first name Q3. enter sex of R Q4.
What was your major in College? Q5. What was your
income last year? Q6. Did you go to church last
week?
3
Answers to Questions
Zip Name Sex Major income church 29002 Wilma
F lit 0 y 99005 Barney M engin
10 n 99005 Betty F . 0 n 92005
Ethel F theater 1000 y 12534 Fred M. M PE
10000 y 12534 Lucy F lit 700
y 25000 Ricky M music 11000 y 20000 Fred A.
M dance 10500 n 15000 Ginger F math 9500
y
4
Must anonymize the data!
Zip Name Sex Major income church 29002 Wilma
F lit 0 y 99005 Barney M engin
10 n 99005 Betty F . 0 n 92005
Ethel F theater 1000 y 12534 Fred M. M PE
10000 y 12534 Lucy F lit 700
y 25000 Ricky M music 11000 y 20000 Fred A.
M dance 10500 n 15000 Ginger F math 9500
y
5
Must anonymize the data!
Zip Name Sex Major income church 29002 001
F lit 0 y 99005 002 M engin
10 n 99005 003 F . 0 n 92005
004 F theater 1000 y 12534 005 M PE
10000 y 12534 006 F lit 700
y 25000 007 M music 11000 y 20000 008
M dance 10500 n 15000 009 F math 9500
y
6
Change Text to Numeric Codes
Zip Name Sex Major income church 29002 001
F lit 0 y 99005 002 M engin
10 n 99005 003 F . 0 n 92005
004 F theater 1000 y 12534 005 M PE
10000 y 12534 006 F lit 700
y 25000 007 M music 11000 y 20000 008
M dance 10500 n 15000 009 F math 9500
y
7
Change Text to Numeric Codes
Zip Name Sex Major income church 29002 001
1 lit 0 y 99005 002 2 engin
10 n 99005 003 1 . 0 n 92005
004 1 theater 1000 y 12534 005 2 PE
10000 y 12534 006 1 lit 700
y 25000 007 2 music 11000 y 20000 008
2 dance 10500 n 15000 009 1 math 9500
y
8
Change Text to Numeric Codes
The codebook mustdocument the numeric codes
used!For example Variable sex 1
female 2 male
Zip Name Sex Major income church 29002 001
1 lit 0 y 99005 002 2 engin
10 n 99005 003 1 . 0 n 92005
004 1 theater 1000 y 12534 005 2 PE
10000 y 12534 006 1 lit 700
y 25000 007 2 music 11000 y 20000 008
2 dance 10500 n 15000 009 1 math 9500
y
9
Change Text to Numeric Codes
Zip Name Sex Major income church 29002 001
1 lit 0 y 99005 002 2 engin
10 n 99005 003 1 . 0 n 92005
004 1 theater 1000 y 12534 005 2 PE
10000 y 12534 006 1 lit 700
y 25000 007 2 music 11000 y 20000 008
2 dance 10500 n 15000 009 1 math 9500
y
10
Change Text to Numeric Codes
Zip Name Sex Major income church 29002 001
1 0075 0 y 99005 002 2 engin
10 n 99005 003 1 . 0 n 92005
004 1 theater 1000 y 12534 005 2 PE
10000 y 12534 006 1 0075 700
y 25000 007 2 music 11000 y 20000 008
2 dance 10500 n 15000 009 1 math 9500
y
11
Change Text to Numeric Codes
Zip Name Sex Major income church 29002 001
1 0075 0 y 99005 002 2 0070
10 n 99005 003 1 . 0 n 92005
004 1 0076 1000 y 12534 005 2 0001
10000 y 12534 006 1 0075 700
y 25000 007 2 0077 11000 y 20000 008
2 0078 10500 n 15000 009 1 0050 9500
y
12
Change Text to Numeric Codes
Zip Name Sex Major income church 29002 001
1 0075 0 y 99005 002 2 0070
10 n 99005 003 1 . 0 n 92005
004 1 0076 1000 y 12534 005 2 0001
10000 y 12534 006 1 0075 700
y 25000 007 2 0077 11000 y 20000 008
2 0078 10500 n 15000 009 1 0050 9500
y
13
Change Text to Numeric Codes
Zip Name Sex Major income church 29002 001
1 0075 0 1 99005 002 2 0070
10 2 99005 003 1 . 0 2 92005
004 1 0076 1000 1 12534 005 2 0001
10000 1 12534 006 1 0075 700
1 25000 007 2 0077 11000 1 20000 008
2 0078 10500 2 15000 009 1 0050 9500
1
14
Change Text to Numeric Codes
Sometimes, evennumeric variablesare encoded in
ranges. For example Variable income 1
less than 1000 2 1000 - 4999 3 5000 -
10000 4 more than 10000 9 not reported
Zip Name Sex Major income church 29002 001
1 0075 0 1 99005 002 2 0070
10 2 99005 003 1 . 0 2 92005
004 1 0076 1000 1 12534 005 2 0001
10000 1 12534 006 1 0075 700
1 25000 007 2 0077 11000 1 20000 008
2 0078 10500 2 15000 009 1 0050 9500
1
15
Change Text to Numeric Codes
Sometimes, evennumeric variablesare encoded in
ranges. For example Variable income 1
less than 1000 2 1000 - 4999 3 5000 -
10000 4 more than 10000 9 not reported
Zip Name Sex Major income church 29002 001
1 0075 1 1 99005 002 2 0070
1 2 99005 003 1 . 1 2 92005 004
1 0076 2 1 12534 005 2 0001
3 1 12534 006 1 0075 1 1 25000
007 2 0077 4 1 20000 008 2 0078
4 2 15000 009 1 0050 3 1
16
Data Files do not need headers
Zip Name Sex Major income church 29002 001
1 0075 1 1 99005 002 2 0070
1 2 99005 003 1 . 1 2 92005 004
1 0076 2 1 12534 005 2 0001
3 1 12534 006 1 0075 1 1 25000
007 2 0077 4 1 20000 008 2 0078
4 2 15000 009 1 0050 3 1
17
Data Files do not need headers
29002 001 1 0075 1 1 99005 002
2 0070 1 2 99005 003 1 .
1 2 92005 004 1 0076 2 1 12534
005 2 0001 3 1 12534 006 1
0075 1 1 25000 007 2 0077 4
1 20000 008 2 0078 4 2 15000 009
1 0050 3 1
18
Data Files do not need extra space
29002 001 1 0075 1 1 99005 002
2 0070 1 2 99005 003 1 .
1 2 92005 004 1 0076 2 1 12534
005 2 0001 3 1 12534 006 1
0075 1 1 25000 007 2 0077 4
1 20000 008 2 0078 4 2 15000 009
1 0050 3 1
19
Data Files do not need extra space
290020011 0075 1 1 990050022
0070 1 2 990050031 . 1 2
920050041 0076 2 1 125340052 0001
3 1 125340061 0075 1 1 250000072
0077 4 1 200000082 0078 4
2 150000091 0050 3 1
20
Data Files do not need extra space
2900200110075 1 1
9900500220070 1 2 990050031. 1
2 9200500410076 2 1 1253400520001
3 1 1253400610075 1 1 2500000720077
4 1 2000000820078 4 2 1500000910050
3 1
21
Data Files do not need extra space
29002001100751 1
99005002200701 2 990050031. 1 2
92005004100762 1 12534005200013 1
12534006100751 1 25000007200774
1 20000008200784 2 15000009100503 1
22
Data Files do not need extra space
290020011007511
990050022007012 990050031. 12
920050041007621 125340052000131
125340061007511 250000072007741 200000082007842 1
50000091005031
23
Codebook must document locations
290020011007511
990050022007012 990050031. 12
920050041007621 125340052000131
125340061007511 250000072007741 200000082007842 1
50000091005031
For example Variable sex location column
9 width 1
24
Codebook must document locations
123456789
290020011007511
990050022007012 990050031. 12
920050041007621 125340052000131
125340061007511 250000072007741 200000082007842 1
50000091005031
For example Variable sex location column
9 width 1
25
Codebook documents question, location, codes.
290020011007511
990050022007012 990050031. 12
920050041007621 125340052000131
125340061007511 250000072007741 200000082007842 1
50000091005031
For example Q3. enter sex of R Variable
sex location column 9 width
1 Variable sex 1 female 2 male
26
(No Transcript)
27
Aggregating Microdata
Zip Name Sex Major income church 29002 Wilma
F lit 0 y 99005 Barney M engin
10 n 99005 Betty F . 0 n 92005
Ethel F theater 1000 y 12534 Fred M. M PE
10000 y 12534 Lucy F lit 700
y 25000 Ricky M music 11000 y 20000 Fred A.
M dance 10500 n 15000 Ginger F math 9500
y
28
Aggregating Microdata
Zip Name Sex Major income church 2 Wilma
F lit 0 y 9 Barney M engin
10 n 9 Betty F . 0 n 9
Ethel F theater 1000 y 1 Fred M. M PE
10000 y 1 Lucy F lit 700 y 2
Ricky M music 11000 y 2 Fred A. M
dance 10500 n 1 Ginger F math 9500
y
29
Aggregating Microdata
Zip Name Sex Major income church 1 Fred
M. M PE 10000 y 1 Ginger F math
9500 y 1 Lucy F lit 700 y 2
Fred A. M dance 10500 n 2 Ricky M
music 11000 y 2 Wilma F lit 0
y 9 Barney M engin 10 n 9 Betty
F . 0 n 9 Ethel F theater 1000
y
30
Aggregating Microdata
Zip Sex 1
M 1 F 1 F 2
M 2 M 2 F 9
M 9 F 9 F
31
Aggregating Microdata
Zip Sex Male Female 1
M 1 2 1 F 1 F 2
M 2 1 2 M 2
F 9 M 1 2 9 F 9
F
32
Aggregating Microdata
Geo Sex Male Female 1
1 2 2
2 1 9 1
2
33
Aggregating Microdata
Geo Sex Male Female 1
1 2 2 2
1 9 1 2
34
Aggregate Data
35
(No Transcript)