2017 Supporting Statement B 1-3-18

2018 Supporting Statement -B

Dairy Products Mandatory Sales Reporting

OMB No. 0581-0274

18-B. COLLECTION OF INFORMATION EMPLOYING STATISTICAL METHODS

1. Describe (including a numerical estimate) the potential respondent universe and any sampling or other respondent selection method to be used. Data on the number of entities (e.g., establishments, State and local government units, households, or persons) in the universe covered by the collection and in the corresponding sample are to be provided in tabular form for the universe as a whole and for each of the strata in the proposed sample. Indicate expected response rates for the collection as a whole. If the collection has been conducted previously, include the actual response rate achieved during the last collection.

The information collection universe consists of dairy manufacturers that produce cheddar cheese, butter, dry whey, or nonfat dry milk meeting the precise specifications included in the mandatory reporting requirements. Manufacturers that produce less than 1 million pounds of a specific product are exempt from reporting sales information for that product. In 2017, there were 98 dairy product plants that were subject to mandatory reporting of sales data for one or more products. There were 46 reporting entities that reported data for one or more plants. The weekly surveys are mandatory. In 2017, the response rate was 100 percent. The following table provides an estimate of responses using 2017 information.

Dairy Products Mandatory Sales Reporting, Responses for 2017
Survey	Survey Size	Annual Frequency	Total Responses per Year	Response Rate
Cheddar Cheese - 40 lb. block	16	52	832	100%
Cheddar Cheese - 500 lb. barrel	13	52	676	100%
Butter	22	52	1,144	100%
Dry Whey	18	52	936	100%
Nonfat Dry Milk	29	52	1,508	100%
Annual Validation	114	1	114	100%
Total	212	261	5,210	100%
Survey Follow-Up Verification	7	52	364	100%

2. Describe the procedures for the collection of information including:

•statistical methodology for stratification and sample selection,

•estimation procedure,

•degree of accuracy needed for the purpose described in the justification,

•unusual problems requiring specialized sampling procedures.

Manufactured dairy product sales data is collected weekly via an electronic survey; follow-up telephone interviews will be conducted for non-respondents and for data clarification when needed. Data collection for cheddar cheese, butter, dry whey, or nonfat dry milk sales is limited to plants producing annually 1 million pounds or more of one of the surveyed commodities that meet the precise specifications included in the mandatory reporting requirements (7 CFR, § 1170.7 through § 1170.9).

Manufacturers are required to submit information to AMS by 12:00 noon, local time of the reporting entities, on Tuesday on all applicable products during the 7 days ending 12:00 midnight of the previous Saturday, of the plant or storage facility where the sales are made. AMS personnel review and compile data and publish the information by 3:00 p.m. Eastern Time on Wednesday as required by the Act. If a Federal holiday falls on Monday through Wednesday of a particular week, the due date for report submission may be adjusted. Prior to the beginning of each calendar year, AMS informs reporting entities of the times and dates that reports are due.

Data included in the Dairy Products Mandatory Sales reports are collected through a census of all qualifying manufacturers of the following products:

1) Cheddar cheese in 40 pound blocks, colored between 6 and 8 on the National Cheese Institute color chart, meeting Wisconsin State Brand, USDA Grade A, or better standards.

2) Cheddar cheese in 500 pound barrels, white, meeting Wisconsin State Brand, USDA Extra Grade, or better standards.

3) Salted butter (80% butterfat), fresh or storage, in 25 kilogram and 68 pound boxes meeting USDA Grade AA standards.

4) Non-fortified, nonfat dry milk in 25 kilogram bags, 50 pound bags, totes, and tankers meeting USDA Extra Grade or USPH¹ Grade A standards.

5) Edible non-hygroscopic dry whey in 25 kilogram bags, 50 pound bags, totes, and tankers meeting USDA Extra Grade standards.

Data reported by manufacturers are reviewed for reasonableness and consistency by comparing with data reported in prior weeks and by data reported by other firms in one of three regions and national trends. The three regions to be used for analysis purposes are aggregated as displayed in the table on the following page.

Although data are analyzed internally by region, only summary data aggregated on a national basis is published. No estimated data are included in publications. In the event that a response is not received or received too late to include in a weekly publication, no adjustments are made that week to account for the missing response. Non-compliance with the mandatory reporting requirements could result in enforcement actions by AMS. Confidentiality is ensured as no individual companies are identified in the survey results or through the data published.

During weekly review before publication, AMS contacts manufacturers to verify any unusual data relationships. If a correction needs to be made, the reporting entity is required to submit a corrected report.

Each weekly publication includes data for the week ending 12:00 midnight of the previous Saturday and for four weeks prior to that. Data is subject to revisions for the previous four weeks. If a reporting entity discovers an error that occurred within the previous four weeks, the reporting entity is required to submit a revised report for the week that the error occurred.

Since August 2007, when survey response became mandatory, AMS has had verification responsibilities for the program. AMS verifies the sales information of reporting entities by visiting the reporting entities and examining their records. AMS currently visits larger entities that account for 80 percent of the yearly reported product volume of each specified dairy product at least once annually. AMS visits one-half of entities that account for the remaining 20 percent each year, visiting each such entity at least once every other year. During each visit, AMS reviews applicable sales transactions records for at least the 4 most recent weeks. In some cases, AMS may review sales records for periods of up to 2 years. AMS may visit reporting entities more often if there is reason to believe that information may not have been reported correctly. AMS verifies that sales transactions match the information reported and that there are no applicable sales transactions not reported.

3. Describe methods to maximize response rates and to deal with issues of non-response. The accuracy and reliability of information collected must be shown to be adequate for intended uses. For collections based on sampling a special justification must be provided for any collection that will not yield "reliable" data that can be generalized to the universe studied.

Dairy Product Mandatory Sales surveys are submitted electronically. Non-responders receive follow-up phone calls. When necessary, AMS also conducts follow-up phone calls to clarify data. AMS provides the verification and enforcement of the accuracy of the information collected. Since response is mandatory and enforced, the response rate is expected to continue to be 100 percent of the universe, as it has been since response became mandatory in August 2007.

Noncompliance, appeals, and enforcement procedures are administered by AMS (7 CFR sections 1170.14 through 1170.16). In the event of noncompliance, the Secretary may issue a cease and desist order. If a U.S. district court finds that the manufacturer or person violated the cease and desist order, the manufacturer or person shall be subject to a civil penalty of not more than $10,000 for each offense.

A system employing Market Administrators and State regulatory agencies has been established to identify and verify which plants meet the criteria for reporting.  All plants that AMS estimates are feasibly capable of producing more than 1 million pounds of the products included in the Dairy Products Mandatory Sales surveys are contacted once a year to complete an Annual Validation Survey. The validation survey serves three purposes: it is used as a tool to determine which operations will be required to complete the weekly surveys; it serves as a training tool (to help ensure that the respondent completes the weekly forms in a consistent and accurate manner); and it is used to document that the respondent understood the proper and accurate way to complete the weekly surveys. AMS works closely with respondents to assure that they understand survey requirements and that they will complete each survey in a proper and accurate manner.

No estimated data are included in publications. In the event that a response is not received or received too late to include in a weekly publication, no adjustments are made that week to account for the missing response. Non-compliance with the mandatory reporting requirements could result in enforcement actions by AMS. Since AMS took over the weekly publication in April 2012, there has been only one missing report. Therefore, AMS does not need any imputation methodology for non-response.

4. Describe any tests of procedures or methods to be undertaken.

AMS created an Estimation Manual to aid AMS personnel in carrying out the AMS administered Dairy Products Mandatory Sales Program. This manual provides detailed instructions for all aspects of the statistics program including: plant qualification, survey processing procedures, instruction for data analysis, aggregation, publication, and list management procedures. AMS continually monitors analysis procedures and edits constraints to ensure data analyses are timely, accurate, and relevant to the current situation in the dairy industry. On an ongoing basis, AMS applies three levels of analyses to insure the validity of the data that are reported.

The first level of analysis consists of simple computer edit checks. These checks look for missing data and inconsistencies of reported data items. If a problem is identified, personnel check whether the original submission loaded properly. If the data cannot be reconciled, personnel place a call-back to the respondent to verify that the correct information was used in the report.

The second level of analysis involves more advanced computer edit checks using data relationships and percent changes from current and previous reports to identify possible data discrepancies. The advanced edits are set to flag a greater range of potential inconsistencies for review and follow-up. Again, respondents are contacted to resolve questionable data, and in some cases respondents may be visited by AMS audit staff to verify that information has been accurately reported.

The third level of analysis entails analysis using graphic charts to review reported data along with weekly aggregated data, AMS administrative data, Dairy Market News information, and Chicago Mercantile Exchange (CME) spot price data. AMS personnel review national data and corresponding relationships between the three geographic regions. Respondents are contacted to resolve questionable data, and in some cases respondents may be visited by AMS audit staff to verify that information has been accurately reported.

5. Provide the name and telephone number of individuals consulted on statistical aspects of the design and the name of the agency unit, contractor(s), or other person(s) who will actually collect and/or analyze the information for the agency.

The Survey Administration Branch of USDA’s National Agricultural Statistics Service was consulted on the design of this information collection package.

AMS contacts regarding data collection report publication:

Roger Cryan, Director, Dairy Economics Division: (202) 720-7091

Lorie Warren, Chief, Market Information Branch: (202) 720-4405

1 USPH refers to the US Department of Health and Human Services-Public Health Service/Food and Drug Administration.