Quarterly Hogs and Pigs Quality Measures

Quarterly Hogs and Pigs Methodology
and Quality Measures
ISSN: 2166-9813

Released December 23, 2019, by the National Agricultural Statistics Service (NASS), Agricultural Statistics Board, United States
Department of Agriculture (USDA).

Quarterly Hogs and Pigs Survey Methodology
Scope and Purpose: The Hogs and Pigs Survey is conducted quarterly in December, March, June, and September. The
survey targets hog and pig producers in the United States. The survey collects data for total hog inventory and other
components including breeding herd, market hog inventory, market hogs by weight group, farrowings, pig crop, and litter
rate. Additional data is collected for death loss, on-farm and custom slaughter, inventory values, and hogs raised under
contract. Data is published for 16 major states every quarter except December when every state is published.
Survey Timeline: The reference date for the Hogs and Pigs Survey is the first day of the quarterly month with a data
collection period of 15 days. Regional Field Offices (RFO) may begin data collection one day prior to the reference date.
Data collection continues until a scheduled ending date and RFO have about four or five business days to complete editing
and analysis, execute the summary, and interpret the survey results. The Agricultural Statistics Board (ASB) must perform
the national review, reconcile state estimates to the national estimates, and prepare the official estimates for release in five
or six business days. The estimates are usually released to the public by the last week in the quarterly month. The
publication date may change due to the timing of federal holidays.
Sampling: The target population for the Hogs and Pigs Survey is all agricultural establishments with one or more hogs or
pigs owned by the operation. NASS uses a dual frame approach, consisting of list frame and area frame components, to
provide complete coverage of this target population. The Hog Survey is conducted for every state.
The list frame includes all known agricultural establishments. A profile, known as control data, of each establishment is
maintained on the list frame to allow NASS to define list frame sampling populations for specific surveys and to employ
efficient sampling designs. Only list frame records with recent positive hog control data are included in the list frame
population. In December, a base sample is selected for all states in the survey. During the follow-on quarters, the list
sample is split into five replicates and only a partial number of replicates are contacted. This is done to reduce the burden
of multiple survey contacts on the respondents in one calendar year. The list frame hog population covers approximately
97 percent of hog inventory in the United States.
The area frame contains all land in the state and, as such, is complete. The land is stratified according to intensity of
agriculture using satellite imagery. The land in each stratum is divided into segments of roughly one square mile.
Segments are optimally allocated and sampled to effectively measure crops and livestock. The sampled segments are fully
enumerated in June. All farms and ranches found operating tracts in these segments are checked to see if they are included
in the list frame hog population. The farms and ranches that are not included in the list frame hog population, called
nonoverlap tracts, are sampled for the December Hogs and Pigs Survey so that the target population is completely
represented. The area frame component of the December Hogs and Pigs Survey covers approximately one percent of the
December hog inventory in the United States. The area frame component is modeled for the other three quarters to reduce
respondent burden.
The Hogs and Pigs Survey list frame sample is selected using a hierarchical stratified sampling design with strata defined
by total hogs and pigs. The sample is a panel sample and is designed to achieve a standard error of one percent of the
point estimate for total hogs and pigs at a national level. The United States list frame sample size for the Hogs and Pigs
Survey in recent years is approximately 6,500 in December and 5,500 in March, June, and September. The Hogs and Pigs
Survey nonoverlap sample uses a stratified sample design based on data collected in the June Area Frame Survey. The

area frame sample size is approximately 1,000. Each list frame and area frame sampling unit is assigned a sampling
weight which is used to create the survey estimates.
Data Collection and Editing: For consistency across modes, the paper version is considered the master questionnaire and
the web and Computer Assisted Telephone Interview (CATI) instruments are built to model the paper instrument.
Questionnaire content and format are evaluated annually through a specifications process where requests for changes are
evaluated and approved or disapproved. Input may vary from question wording or formatting to a program change
involving the deletion or modification of current questions or addition of new ones. If there are significant changes to
either the content or format proposed, a NASS survey methodologist will pre-test the changes for usability. Prior to the
start of data collection, all modes of instruments are reviewed and web and CATI instruments are thoroughly tested.
All federal data collections require approval by the Office of Management and Budget (OMB). NASS must document the
public need for the data, apply sound statistical practice, prove the data does not already exist elsewhere, and ensure the
public is not excessively burdened. The Hogs and Pigs Report questionnaire must display an active OMB number that
gives NASS the authority to conduct the survey, a statement of the purpose of the survey and the use of the data being
collected, a response burden statement that gives an estimate of the time required to complete the form, a confidentiality
statement that the respondent’s information will only be used for statistical purposes in combination with other producers,
and a statement saying that response to the survey is voluntary and not required by law.
In addition to asking the specific hog inventory items, all instruments collect information to verify the sampled unit,
determine any changes in the name or address, identify any partners to detect possible duplication, verify the farm still
qualifies for the target population, and identify any additional operations operated by the sampled operator.
Sampled farms and ranches receive a pre-survey letter explaining the survey and informing them that they will be
contacted for survey purposes only. The letter provides the questions to be asked to allow respondents to prepare in
advance and also provides a pass code they can use to complete the survey on the internet. All modes of data collection
are utilized for hog surveys. RFO are given the option of conducting a mail out/mail back phase. While mail is the least
costly mode of collection, the short data collection period and the uncertainty of postal delivery times limit its
effectiveness. Most of the data are collected by computer-assisted telephone interviews (CATI) by RFO and Data
Collection Centers. Limited personal interviewing is done, generally for large operations or those with special handling
arrangements. A program is run to determine if any sampled farms are in multiple on-going surveys, so data collection can
be coordinated.
Survey Edit: As survey data are collected and captured, they are edited for consistency and reasonableness using
automated systems. The edit logic ensures the coding of administrative data follows the methodological rules associated
with the survey design. Relationships between data items on the current survey are verified and in certain situations those
items may be compared to data from earlier surveys to make sure certain relationships are logical. The edit will determine
the status of each record to be either “dirty” or “clean”. Dirty records must be updated and reedited or certified by an
analyst to be clean. If updates are needed, they are reedited interactively. Only clean records are eligible for analysis and
summary.
Analysis Tools: Edited hog data are processed through an interactive analysis tool which displays data for all reports by
item. The tool provides scatter plots, tables, charts, and special tabulations that allow the analyst to compare an individual
record to other similar records within their state. Outliers and unusual data relationships become evident and RFO staff
will review them to determine if they are correct. The tool also allows comparison to an operation’s previously reported
data to detect large changes. Suspect data found to be in error are corrected, while data found to be correct are kept.
Nonsampling Errors: Nonsampling errors are present in any survey process. These errors include reporting, recording,
editing, and imputation errors. Steps are taken to minimize the impact of these errors, such as questionnaire testing,
comprehensive interviewer training, validation and verification of processing systems, detailed computer edits, and the
analysis tool.
Estimators: Each farm and ranch in the sample has an initial sampling weight. This is the inverse of the sampling
fraction. For example, if a stratum has 1,000 farms in the population and 200 are sampled for this survey, each sampled
2

Quarterly Hogs and Pigs Methodology and Quality Measures (December 2019)
USDA, National Agricultural Statistics Service

farm has a weight of 5. In other words, each sampled farm represents 5 farms. The nonoverlap tracts sampled to measure
the hogs and pigs not accounted for by the list have a weight determined by adjusting their original area frame weight by
any second stage sampling weight.
Response to the Hogs and Pigs Survey is voluntary. Some producers refuse to participate in the survey. Others cannot be
located during the data collection period and some submit incomplete reports. These nonrespondents must be accounted
for if accurate estimates of hogs are to be made. For the Hogs and Pigs Survey, nonrespondents are accounted for by
adjusting the weights of the respondents. The adjustment occurs by stratum as the bounded strata represent homogeneous
groupings of similar sized farms. The largest stratum is unbounded and is made up of large and, often unique, farms.
Nonrespondents in this stratum and the nonoverlap tracts must be manually imputed by RFO statisticians and their
weights are not adjusted. The adjustment is performed by individual item on the questionnaire (total hogs, market hogs,
pig crop) so adjustments for item nonresponse (partial reports) and unit nonresponse (refusals and inaccessibles) are done
in a single calculation.
Two estimators are used to compute direct measures of the hog inventory items. The “reweighted” estimator and the
“adjusted” estimator are computationally identical except in how the nonresponse adjustments are made. The reweighted
estimator uses a global weight adjustment across all usable reports. Using the previous example, if 180 of the original 200
respond, the weights of the 180 will be adjusted to 1,000 divided by 180, or 5.56. The nonresponse weight adjustment for
the adjusted estimator uses an additional piece of information. When a sampled farm refuses to cooperate, interviewers
will probe to determine the presence of hogs even though the number is not known. This presence/absence indicator is
used in the weight adjustment.
Point estimates, also called direct expansions, for both estimators are calculated by multiplying the reported value by the
nonresponse weight and summing to a stratum total. A variance estimate is also computed at the stratum level. The
nonoverlap tracts are treated as an additional stratum. Totals and variances are additive across strata to form a state
estimate and states are additive to a national estimate.
Ratio estimates are also computed for many items. For example, market hogs can be estimated as a percent of total
inventory. A matched record ratio of current quarter data to previous quarter data is used to indicate change. Ratio
indications use the reweighted estimator described above for the numerator and denominator direct expansions. Both the
numerator and denominator must be complete in order for that record to be used in the ratio estimator.
Estimation: When all samples are accounted for, all responses fully edited, and the analysis material is reviewed, each
RFO executes summaries for their states. When all states have been summarized, Headquarters executes the national
summary. Since all states conduct identical surveys, the samples can be pooled and national survey results computed. The
summary results provide multiple point estimates and their standard errors for each data series being estimated. It also
provides information used to assess the performance of the current survey and evaluate the quality of the survey estimates,
such as strata level expansions, response rates, and percent of the expansion from usable reports.
RFO are responsible for performing a detailed review of their survey results. Any irregularities revealed by the summary
must be investigated and, if necessary, resolved. Using the historical relationship of the survey estimates to the official
estimate, RFO must interpret the survey results and submit a recommended estimate to Headquarters for all data series for
which they are in the NASS program. The data are viewed in tabular and graphical form and a consensus estimate is
established. RFO see their survey results only and do not have access to other Regions’ results. For some data series,
information from other sources is also utilized in the process of establishing estimates. This includes commercial slaughter
data, imports, and exports.
For the national estimates, NASS assembles a panel of statisticians to serve as the ASB which reviews the national results
and establishes the national estimates. Since larger sample sizes yield more precise results, NASS employs the “topdown” approach by determining the national estimates first and reconciling the state estimates to the national number for
hog inventory, pig crop, and farrowings. The ASB has the advantage of being able to examine results across states,
compare the state recommendations, and utilize administrative data available only at the United States level. The same
estimators used in the state summaries are produced by the national summary. The Board follows the same approach the
states do in determining the national estimate. The historical relationship of the survey estimates to the official estimate is
Quarterly Hogs and Pigs Methodology and Quality Measures (December 2019)
USDA, National Agricultural Statistics Service

3

evaluated over time to determine accuracy and bias using tables and graphs. Every 5 years NASS conducts the Census of
Agriculture, which is an exhaustive data collection effort for all known farm operations across the United States. The
information gathered from the Census of Agriculture is used to establish “bench mark” levels by which the survey
estimators can be compared and bias determined. Survey based estimators can also be impacted by outliers – individual
reports that have excessive influence on the results due to either improper classification or extremely unusual data for a
given operation (i.e. the operation is not representative of other operations). NASS thoroughly reviews the survey data to
identify these situations and considers their impact on the survey results when establishing the official estimates.
External information (administrative data) is also utilized in the process of setting estimates. In order to be considered fit
for use, these data must be deemed to be reliable and come from unbiased sources. The most common administrative data
is commercial slaughter. NASS employs a balance sheet approach whenever possible to ensure that estimates are as
accurate as possible. This approach typically is limited to national-level estimates. A balance sheet and its components are
reviewed when the inventory numbers are established. Commercial slaughter is an important element of the balance sheet
at the national level since its high degree of reliability is based on a near-actual count of animals slaughtered. Live United
States imports and exports to other countries are also considered.
Subtracting the disposition components of the balance sheet from supply components should, theoretically, give the
current inventory. However, each component of the balance sheet has varying degrees of possible estimation error. To be
most useful as an indication of inventory, therefore, each component should be estimated on the basis of all available
information. The supply components of the United States balance sheet are the beginning inventory, births, and imports
(inshipments for State balance sheets). From this supply, the disposition components – commercial slaughter (marketings
at State level), farm slaughter, deaths, and exports – are subtracted. The result is the indicated number on hand at the end
of the period or year.

4

Quarterly Hogs and Pigs Methodology and Quality Measures (December 2019)
USDA, National Agricultural Statistics Service

Quality Metrics for Hogs and Pigs
Purpose and Definitions: Under the guidance of the Statistical Policy Office of the Office of Management and Budget
(OMB), the United States Department of Agriculture’s National Agricultural Statistics Service (NASS) provides data
users with quality metrics for its published data series. The metrics tables below describe the performance data for all
surveys contributing to the publication. The accuracy of data products may be evaluated through sampling and nonsampling error. The measurement of error due to sampling in the current period is irrelevant for a fully enumerated data
series. Non-sampling error is evaluated by response rates and the percent of the estimate from usable reports.
Sample size is the number of observations selected from the population to represent a characteristic of the
population. Operations that did not have the item of interest or were out of business at the time of data collection
have been excluded.
Response rate is the proportion of the above sample size that completed the survey.
Percent of expansion from usable reports is a ratio of survey data expanded by the original sampling weight
compared to survey data expanded by the nonresponse adjusted weight .
Coefficient of variation provides a measure of the size for the standard error relative to the point estimate and is
used to measure the precision of the results of a survey estimator.
Hogs and Pigs Survey Sample Size and Response Rates: To assist in evaluating the performance of the estimates in the
hogs and pigs report, the sample size and response rates are displayed. Response rates overall for 2018 and 2019 are
displayed.

Hogs and Pigs Survey Sample Size and Response Rates - United States: December 1, 2018-2019
Sample size

Response rates

2018

2019

2018

2019

(number)

(number)

(percent)

(percent)

United States ..........................................................

6,892

5,808

58.8

58.5

Quality Metrics for December 1 Hogs and Pigs – United States: 2018 and 2019
Percent of expansion
from usable reports

All hogs and pigs ....................................................
Kept for breeding ................................................
Market ................................................................
Sows farrowed ........................................................
Litter rate ................................................................
Pig crop ..................................................................

Coefficient
of variation

2018

2019

2018

2019

(percent)

(percent)

(percent)

(percent)

92.0
92.1
92.0
92.5
92.5
92.8

Quarterly Hogs and Pigs Methodology and Quality Measures (December 2019)
USDA, National Agricultural Statistics Service

92.4
92.9
92.3
93.4
93.4
93.9

1.0
0.7
1.1
0.8
0.1
0.7

0.4
0.6
0.5
0.8
0.1
0.7

5

Hogs and Pigs Survey Sample Size and Response Rates – United States: 2018 and 2019
Sample size

Percent Expansion
from Usable Reports

Response rate

Coefficient
of Variation

2018

2019

2018

2019

2018

2019

2018

2019

(number)

(number)

(percent)

(percent)

(percent)

(percent)

(percent)

(percent)

Alabama ..............................
Alaska ..................................
Arizona ................................
Arkansas ..............................
California .............................
Colorado ..............................
Connecticut ..........................
Delaware .............................
Florida ..................................
Georgia ................................

56
25
27
62
82
63
51
28
117
76

45
21
26
45
77
43
41
28
59
42

51.8
64.0
55.6
66.1
63.4
44.4
35.3
42.9
52.1
51.3

53.3
57.1
69.2
73.3
48.1
53.5
46.3
35.7
39.0
50.0

96.8
86.0
98.0
99.1
89.9
99.6
49.1
97.7
67.9
92.3

91.1
81.0
99.9
98.8
90.4
99.4
45.9
97.2
68.5
92.2

5.0
7.6
1.6
5.2
8.2
0.3
20.6
2.4
13.0
3.6

4.9
6.8
0.4
1.8
10.6
0.6
24.2
1.6
10.6
5.4

Hawaii ..................................
Idaho ....................................
Illinois ...................................
Indiana .................................
Iowa .....................................
Kansas .................................
Kentucky ..............................
Louisiana .............................
Maine ...................................
Maryland ..............................

42
55
608
505
924
155
62
61
62
39

41
43
497
425
885
131
70
51
52
40

47.6
65.5
60.2
68.1
53.0
45.2
54.8
62.3
69.4
66.7

48.8
48.8
60.2
67.3
54.0
42.0
67.1
78.4
57.7
50.0

65.8
97.5
89.8
93.1
87.6
96.0
93.5
66.3
75.6
94.4

46.9
95.3
90.9
92.8
89.7
94.5
96.7
62.1
46.6
87.1

21.1
8.2
1.0
0.7
1.2
0.6
3.8
20.6
14.6
4.4

25.6
7.9
0.9
1.1
0.9
1.7
1.0
22.3
25.3
6.8

Massachusetts .....................
Michigan ..............................
Minnesota ............................
Mississippi ...........................
Missouri ...............................
Montana ...............................
Nebraska .............................
Nevada ................................
New Hampshire ...................
New Jersey ..........................

57
149
590
51
262
81
478
26
61
39

59
103
565
41
226
75
389
18
53
24

28.1
74.5
59.0
66.7
58.8
79.0
58.4
65.4
50.8
69.2

57.6
71.8
57.0
75.6
55.3
82.7
59.4
55.6
52.8
62.5

82.5
97.6
84.7
99.9
97.0
99.1
92.9
90.4
85.7
91.2

81.6
97.0
85.4
99.7
94.8
99.0
94.0
93.8
75.9
76.0

4.4
1.2
7.9
0.2
0.6
0.7
0.8
4.3
12.8
39.0

17.5
1.7
2.1
0.3
1.0
0.8
0.6
5.9
11.2
19.4

New Mexico .........................
New York .............................
North Carolina ......................
North Dakota ........................
Ohio .....................................
Oklahoma ............................
Oregon .................................
Pennsylvania .......................
Rhode Island ........................
South Carolina .....................

44
89
68
87
347
74
73
200
25
65

34
63
64
55
279
52
65
164
20
42

36.4
53.9
61.8
62.1
53.9
54.1
52.1
69.5
24.0
56.9

61.8
55.6
62.5
63.6
58.1
61.5
44.6
49.4
60.0
50.0

40.6
83.6
99.8
92.4
96.0
99.9
74.9
95.2
87.5
98.1

67.1
84.0
99.4
99.2
92.7
99.7
78.5
92.1
85.0
99.2

18.0
10.1
0.1
7.0
0.9
0.1
12.6
1.0
5.7
0.9

17.9
7.9
0.2
0.8
3.9
0.1
36.0
3.4
11.7
1.7

South Dakota .......................
Tennessee ...........................
Texas ...................................
Utah .....................................
Vermont ...............................
Virginia .................................
Washington ..........................
West Virginia ........................
Wisconsin ............................
Wyoming ..............................

209
65
104
27
67
40
69
69
248
28

184
66
91
23
54
29
45
50
195
18

70.8
66.2
58.7
77.8
74.6
70.0
59.4
78.3
50.4
53.6

66.8
69.7
62.6
87.0
57.4
62.1
46.7
74.0
59.5
72.2

91.5
98.9
99.1
100.0
94.9
98.8
75.6
80.6
78.2
98.2

89.9
99.1
99.3
99.9
93.7
97.8
87.0
62.8
78.1
99.3

1.5
1.3
0.9
0.2
36.6
2.3
15.1
26.7
13.2
4.4

2.2
0.9
0.5
0.3
44.5
2.1
48.6
14.3
9.8
1.1

United States .......................

6,892

5,808

58.8

58.5

92.0

92.4

1.0

0.4

6

Quarterly Hogs and Pigs Methodology and Quality Measures (December 2019)
USDA, National Agricultural Statistics Service

Information Contacts
Process
Estimation ....................................
Data Collection ............................
Questionnaires ............................
Sampling and Editing ...................
Summary and Estimators .............
Dissemination ..............................
Media Contact and Webmaster ....

Unit
Livestock Branch
Survey Administration Branch
Data Collection Branch
Sampling Editing and Imputation Methodology Branch
Summary Estimation and Disclosure Methodology Branch
Data Dissemination Office
Public Affairs Office

Telephone
(202) 720-3570
(202) 720-3895
(202) 720-6201
(202) 720-5805
(202) 720-4008
(202) 720-3869
(202) 720-2639

Email
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]

Access to NASS Reports
For your convenience, you may access NASS reports and products the following ways:
 All reports are available electronically, at no cost, on the NASS web site: www.nass.usda.gov
 Both national and state specific reports are available via a free e-mail subscription. To set-up this free
subscription, visit www.nass.usda.gov and click on “National” or “State” in upper right corner above “search”
box to create an account and select the reports you would like to receive.
 Cornell’s Mann Library has launched a new website housing NASS’s and other agency’s archived reports. The
new website, https://usda.library.cornell.edu. All email subscriptions containing reports will be sent from the new
website, https://usda.library.cornell.edu. To continue receiving the reports via e-mail, you will have to go to the
new website, create a new account and re-subscribe to the reports. If you need instructions to set up an account or
subscribe, they are located at: https://usda.library.cornell.edu/help. You should whitelist [email protected] in your email client to avoid the emails going into spam/junk folders.
For more information on NASS surveys and reports, call the NASS Agricultural Statistics Hotline at (800) 727-9540,
7:30 a.m. to 4:00 p.m. ET, or e-mail: [email protected].
The U.S. Department of Agriculture (USDA) prohibits discrimination against its customers, employees, and applicants for
employment on the basis of race, color, national origin, age, disability, sex, gender identity, religion, reprisal, and where
applicable, political beliefs, marital status, familial or parental status, sexual orientation, or all or part of an individual's
income is derived from any public assistance program, or protected genetic information in employment or in any program
or activity conducted or funded by the Department. (Not all prohibited bases will apply to all programs and/or
employment activities.)
If you wish to file a Civil Rights program complaint of discrimination, complete the USDA Program Discrimination
Complaint Form (PDF), found online at www.ascr.usda.gov/filing-program-discrimination-complaint-usda-customer, or
at any USDA office, or call (866) 632-9992 to request the form. You may also write a letter containing all of the
information requested in the form. Send your completed complaint form or letter to us by mail at U.S. Department of
Agriculture, Director, Office of Adjudication, 1400 Independence Avenue, S.W., Washington, D.C. 20250-9410, by fax
(202) 690-7442 or email at [email protected].