Results of 2007 CES

Download Report

Transcript Results of 2007 CES

Identifying Sources of Error:
the 2007 Classification Error Survey for
the US Census of Agriculture
Jaki McCarthy and Denise Abreu
USDA’s National Agricultural Statistics Service
Presented at the International Total Survey Error Workshop
Tallberg, Sweden
June 2009
Errors in one survey can be measured with
matching information from other sources

Target:
Census of
Agriculture

Alternate Source of
Information:
June Agricultural Survey
Error of Interest:
Scoping Errors, i.e. Census Misclassification

Census farms incorrectly classified
as non-farms

Census non-farms incorrectly
classified as farms
Errors in one survey can be measured with
matching information from other sources
Census of Agriculture




Census of Agriculture
conducted every 5
years
Count of all US Ag
operations ($1000 or
more in sales)
Primarily mail data
collection
Data collected
December - March
June Agricultural Survey




(JAS)
Annual area frame based
sample survey in June
JAS is primarily face to
face interviews
Data collected in first 2
weeks of June
JAS has been used to
measure undercoverage
and misclassification on
census
JAS – Area Frame Based
7
NASS Area Frame - SEGMENT

Theoretically
complete sampling
frame

No overlap or gaps

Segments of land
sampled
8
NASS Area Frame – Segment
Enumeration

Sampled segments
divided into tracts
representing unique
land operating
arrangements

In-person interviewers
screen for whether a
tract is part of an
agricultural operation
and, if so, collect crop
and livestock
information
9
Background:
Previous Classification Error Studies

Measured census classification error – records
incorrectly classified as farms or non-farms and
duplication

Census records matched to JAS

JAS was assumed as truth; differences between the two
sources were designated as census misclassification

Overall census misclassification error was estimated
10
Background:
Previous Classification Error Studies

Net classification error was small and was not
used to adjust census numbers

For these reasons, shift in study’s primary
objective
11
Current Classification Error Survey

To identify REASONS for discrepancies
between the JAS and the Census

Qualitative examination of why errors occur



Classification errors
Reporting errors also examined
To provide information to improve quality of the
data, reduce analyst review and editing
12
2007 CES Objective

Determine whether acreage/scoping differences
are legitimate changes or errors

Determine why people report incorrectly

Determine if the forms were correctly processed
13
Methods

Census records matched to JAS records

Respondents records with scoping or acreage discrepancies
were identified

Respondents re-interviewed and asked to resolve
discrepancies
Census farm
JAS farm
JAS non-farm
Census non-farm
Match
Misclassification undercount
Misclassification
Match
- overcount
14
Identifying Groups with Discrepancies
Group
Description
Action
Total
MATCH:
Classification in
agreement, acres
comparable
Census farm/ JAS farm
OR
Census non-farm / JAS Non-farm
No Action
1,629
MATCH:
Classification in
agreement, acres
not w/in 25%
Census farm / JAS estimated farm
No Action;
JAS Incorrect
240
Census farm / JAS farm
Re-interview
1,122
Census non-farm by NASS / JAS farm
FO Review Only
158
Potential Undercount:
Census non-farm / JAS farm
Re-interview
185
Census non-farm / JAS estimated
farm
No Action;
JAS Incorrect
53
Potential Overcount:
Census farm/JAS Non-farm
Re-interview
279
Total
3,666
Potential Scoping
Errors:
Classification
Conflict
Discrepancies between Census and JAS

Scoping differences: 18.4% of matched records
had discrepancies in classification (~3% net
classification error)

Acreage differences: 37.2% of matched records
had acreage differing by more than 25%
16
Methods

67 respondents were re-interviewed by
enumerators in July 2008

Respondents reviewed questionnaires from
both the 2007 Census and the 2007 JAS

Then asked to identify which was correct and
why they were different
17
Scoping Differences
Which Source is Correct?
JAS 15.0%
Both 13.4%
Census 59.7%
Neither 11.9%
Scoping Differences
Which Source is Correct?
TRUE Census
Misclassification
Scoping Differences – Census is Correct
Number of Responses
(n=39)
20
Scoping Differences – JAS is Correct
Number of Responses
(n=10)
21
Reasons for Discrepancies
Scoping Differences – Both Sources Correct
Land Purchased
1
Land Sold
1
NASS O/S
True Change – reported correctly
True Change – reported incorrectly
2
4
Different Operation
Number of Responses
(n=9)
22
Scoping Differences – Neither Source Correct
Number of Responses
(n=9)
23
Scoping Differences – Overall Summary by Category
True Change – Correct
True Change - Incorrect
Number of Responses
(n=67)
24
Summary – Scoping Differences

Very few of these cases are real changes between
JAS and the Census

Census was correct more often than June

Most discrepancies are actual errors



June tracts screened out incorrectly
Proxy respondents reporting incorrectly in JAS
Specific types of land excluded (government program land,
woods, rented)
25
Source Used to Report Acres
Source Used to Report Acres*
Percent
(n=67)
No Records, I know my acreage
50.8%
Tax records
10.5%
FSA records
6.0%
Operation books
14.9%
Other records (ie., deed, GPS #s)
1.5%
* Multiple answers allowed
26
What did we learn about Census
misclassification?


Classification error remains minimal and is
probably smaller than previous estimates
JAS cannot be used as “truth”



Re-interview with resolution shows both the
Census and the JAS have errors
JAS is not the GOLD STANDARD --personal
interviews not always best way to get
accurate responses
Some errors due to respondents and
won’t be eliminated
27
Our external source had more
errors than our target:
Recommendations to improve the JAS:


Avoid proxy respondents in JAS
Review of screening in JAS


Intensive re-screening of all non-ag tracts
is in progress
Estimation of farms missing
from JAS

Capture/Re-capture
estimates in progress
28
To examine errors,
you need a good measure