survey data summary

[Xaheer Ahmed]

hi,
I have the below data; I am new in Stata so struggling to produce the right summary.

hid		fid	cluster	line1	sex1	age1	line2	sex2	age2	....	line10	sex10	age10
1		1	1	1	m	5	2	m	12	.....	10	f	65
1		2	1	1	f	20	2	m	14		10	m	80
2		1	2	1	m	8	2	m	12
3		1	3	1	f	54	2	f	3	.....	15		60
4		1	2	1	m	22

how I calculate the below summary: (There are 10 variables for each household and in some survey just 5 members' data are available while few all 10)

- Counting all line # for individual households: *For household 1 there is 20 member (10 in the first family + 10 in the second family) while for household 4 is just 1;
- counting all line# for individual households cluster vise: CLUSTER 3 only 10 people while in Cluster 4 there is just one person living
- Counting all males/females living in individual households as well as cluster vise.
- total populations in survey cluster vise and # of male & female row and column total.

[Ken Chui]

Welcome to Statalist,

Very hard to help without seeing the data and its format. Please follow the advice in the FAQ by providing some sample data. Try this code:

dataex hid fid cluster line1 sex1 age1 line2 sex2 age2 line3 sex3 age3 line10 sex10 age10, count(100)

And then paste the sample data here. Users here can then input those into Stata and suggest working codes for you.

[Xaheer Ahmed]

hid	cluster	fid	line#1	Sex1	age1	line#2	Sex2	age2	line#3	Sex3	age3	line#4	Sex4	age4
88-88001-001-01	88	1	1	1	60	2	2	56	3	1	24	4	2	22
88-88001-001-02	88	2	1	1	37	2	2	28	3	2	2
89-8902-4002-01	89	1	1	1	31	2	2	30	3	2	5	4	2	1
88-88001-001-04	88	4	1	1	28	2	2	21	3	2	1
89-89024-004-01	89	1	1	1	27	2	2	28	3	2	7	4	2	5
89-89-89024-003	89	1	1	1	52	2	2	49	3	1	28	4	2	26
89-89024-003-01	89	1	1	1	52	2	2	49	3	1	28	4	1	26
90-90001-001-0	90	3	1	1	50	2	2	48	3	2	24	4	2	22

[Xaheer Ahmed]

sex: 1, male 2, female
Line # is the serial number of the family
cluster is 88, 89, 90
fid: if more than one family lives in the household they will assign family like 1, 2, 3....

[Ken Chui]

Not this form. Currently, the data example in #3 will not even work because it'd trigger missing period in those cases with missing. Also "#" is not allowed in variable name. If anyone would like to help they they will have to spend extra time to make the data usable.

After you've run the dataex code, you should receive an output wrapped with "CODE" and "\CODE" in Stata, please paste that whole chunk from "CODE" to "\CODE".

[Xaheer Ahmed]

input str10 hid byte fid str3 cluster byte(line1 sex1 age1 line2 sex2 age2 line3 sex3 age3)
"c13-001-01" 1 "c13" 1 1 60 2 2 56 3 1 24
"c13-001-02" 2 "c13" 1 1 37 2 2 28 3 2 2
"c16-002-01" 1 "c16" 1 1 31 2 2 30 3 2 5
"c13-001-03" 4 "c13" 1 1 28 2 2 21 3 2 1
"c16-004-01" 1 "c16" 1 1 27 2 2 28 3 2 7
"c16-003-01" 1 "c16" 1 1 52 2 2 49 3 1 28
"c16-003-01" 1 "c16" 1 1 52 2 2 49 3 1 28
"c13-001-03" 3 "c13" 1 1 50 2 2 48 3 2 24
"c16-007-01" 1 "c16" 1 1 23 2 2 20 3 2 1
"c16-006-01" 1 "c16" 1 1 60 2 2 54 3 1 16
"c16-008-01" 1 "c16" 1 1 55 2 2 23 3 2 6
"c16-004-01" 1 "c16" 1 1 23 2 2 40 3 1 25
"c16-009-01" 1 "c16" 1 1 37 2 2 34 . . .
"c16-001-01" 1 "c16" 1 1 40 2 2 30 . . .
"c16-010-01" 1 "c16" 1 1 29 2 2 25 3 2 4
"c16-007-01" 2 "c16" 1 1 33 2 2 28 3 2 12
"c16-009-02" 1 "c16" 1 1 20 2 2 25 3 2 3
"c16-005-01" 1 "c16" 1 1 37 2 2 34 . . .
"c16-001-01" 1 "c16" 1 1 50 2 2 45 3 1 7
"c21-002-01" 2 "c21" 1 1 52 2 2 48 3 2 20
end
here is the output after pasting it to dataex as advised
please keep in mind that, i am a NEW/beginner Stata user. Thanks in advance.