Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Dropping/Keeping observations

From   "Gauri Khanna" <>
Subject   st: Dropping/Keeping observations
Date   Sat, 22 Apr 2006 12:29:57 +0000

It works... thanks Nick.

This leads to one more question.

I am subsampling my data out. I would like to KEEP those plots/observations where farmerID appears more than once. Hence, I would like to DROP those observations which have only one farmerID. Any tips?

I looked on the drop /keep command in Stata help and the examples given are rather simple.

Thanks again.



From: "Nick Cox" <>
To: <>
Subject: st: RE: Producing averages for cross sectional data by ID
Date: Fri, 21 Apr 2006 18:56:55 +0100

Sorting by farmer ID is not necessary. You can
get the averages with a suitable -egen, mean()-
and -by()- or -by:-.


Gauri Khanna

> I would like to produces averages in my cross sectional data and was
> wondering how to do it.
> I have cross sectional data on 300 plots for 100 farmers.
> Each plot is
> associated with a farmer's identification. Hence the same
> farmer can have
> multiple plots.
> I would like to estimate the following production function for my 100
> farmers:
> (Yi-Yibar)=(X1i-X1ibar)+(X2i-X2ibar)+(X3i-X3ibar)+....
> where i= ith farmer, Y = output, and X1i,X2i...'s= various
> inputs of the ith
> farmer,
> Yibar=average output of ith farmer calculated over his multiple plots,
> X1ibar=average of input1 of ith farmer calculated over his
> multiple plots
> etc.
> How can I select the ith farmer from my data and calculate
> averages? Note
> that each farmer has a farmerID
> I know that I must sort the data by "farmerID" but what comes after?

*   For searches and help try:
Express yourself instantly with MSN Messenger! Download today it's FREE!

* For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index