All,
I've obtained some extremely large datasets that contain the following
structure:
. list id year cty dist turn const vote in 26640/26660
+-------------------------------------------------------------+
| id year cty dist turn const vote |
|-------------------------------------------------------------|
26640. | 87.51051 87 tyne and sunderla 29.4 555 311 |
26641. | 87.51051 87 tyne and sunderla 29.4 555 170 |
26642. | 87.51051 87 tyne and sunderla 31.6 322 2119 |
26643. | 87.51051 87 tyne and sunderla 31.6 322 738 |
26644. | 87.51051 87 tyne and sunderla 31.6 322 570 |
|-------------------------------------------------------------|
26645. | 87.51051 87 tyne and sunderla 32.5 322 2243 |
26646. | 87.51051 87 tyne and sunderla 32.5 322 433 |
26647. | 87.51051 87 tyne and sunderla 32.5 322 252 |
26648. | 87.51051 87 tyne and sunderla 33.5 322 2092 |
26649. | 87.51051 87 tyne and sunderla 33.5 322 1150 |
|-------------------------------------------------------------|
26650. | 87.51051 87 tyne and sunderla 33.5 322 1057 |
26651. | 87.51051 87 tyne and sunderla 32.8 322 1864 |
26652. | 87.51051 87 tyne and sunderla 32.8 322 797 |
26653. | 87.51051 87 tyne and sunderla 32.8 322 543 |
26654. | 87.5201 87 west mid birmingh 44.5 60 3644 |
|-------------------------------------------------------------|
26655. | 87.5201 87 west mid birmingh 44.5 60 3352 |
26656. | 87.5201 87 west mid birmingh 44.5 60 2374 |
26657. | 87.5201 87 west mid birmingh 34.3 58 4517 |
26658. | 87.5201 87 west mid birmingh 34.3 58 871 |
26659. | 87.5201 87 west mid birmingh 34.3 58 774 |
|-------------------------------------------------------------|
26660. | 87.5201 87 west mid birmingh 34.3 58 219 |
+-------------------------------------------------------------+
Naturally, this is a snapshot not just of cases, but also of variables.
Each case represents the voting record of a candidate standing in a
council ward ("ward" is not shown here).
What I want to do is 'collapse' this ward-level data into constituencies
("const"). As you can see, each constituency has its own number. Trouble
is, how can I achieve this whilst summing the votes, averaging the turnout
("turn"), keeping the same "year", "city" and "dist" and so forth?
I suspect this might be too tricky even for the list.
CLIVE NICHOLAS |t: 0(44)191 222 5969
Politics Building |e: [email protected]
School of Geography, |f: 0(44)870 126 2421
Politics & Sociology |
University of |
Newcastle-upon-Tyne |
Newcastle-upon-Tyne |
NE1 7RU |
United Kingdom |http://www.ncl.ac.uk/geps
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
