Supporting Statement - Customer Satisfaction Surveys (Part B)

Supporting Statement

Internal Revenue Service

Request for Approval of New Information Collection

B. Collections of Information Employing Statistical Methods.

1. Universe and Respondent Selection

The surveys covered under this clearance vary greatly with regard to universe and respondent selection. Some surveys represent respondents selected from a comprehensive range of IRS functions and activities or customer characteristics related to many products or services. Others represent respondents selected from an extremely limited range of IRS functions and activities or customer characteristics related to narrowly defined products or services.

In most cases, the contractor develops the sampling plan that includes the target population and sampling frame, sampling specifications, expected reliability of the sample estimates, preliminary sampling weights, and the strategy of achieving target quotas within key strata. The contractor is responsible for running standard checks to ensure complete mailing addresses and administers the survey on a monthly basis.

The contractor releases responses as summaries in a de-identifiable format to the IRS. Data will not include any identifying information such as name, address, and taxpayer identification number.

Generally, the contractor or administrator, using software such as SPSS, will summarize the quantitative ratings and produce national and or area reports showing customer satisfaction scores. The contractor will include any relevant database variables in the analysis and will weight the survey responses as necessary to accurately reflect the entire customer base.

For the analysis reports, the contractor will use basic and advanced statistical techniques including:

• Survey counts and overall response rates

• The overall level of customer satisfaction with services provided

• The frequencies and mean for all survey items

• The difference in satisfaction ratings and attitudes across customer segments

• Analysis of the relationship between survey responses

• Analysis of the open-ended questions for improvement suggestions

Response rates to these voluntary customer surveys are also expected to vary greatly. For example, during the current three-year approval period for 1545-1432 under which these surveys were approved, response rates have varied from as low as 35% for an internet survey up to 67% and as low as 25% up to 54% for mail and phone surveys. These response rates are similar to the response rates we received in the prior three years. This level of response is typical for IRS customer surveys and is considered adequate for making product and service improvement decisions. Non-response follow-up efforts are usually, but not always, employed. No follow-up is attempted if a customer fails to return a questionnaire following an in-office contact where the customer agreed to participate. However, non-response follow-up efforts, when employed, help ensure that a sufficient number of respondents are represented and that non-response bias is minimized.

2. Procedures for Collecting Information

Limited information from IRS customers, as well as users and potential users of new IRS technology will be collected. Respondents will be advised of the purpose of the survey and its voluntary nature via a cover letter or advance letter in the case of a telephone survey or in an email or as part of the survey introduction in the case of electronic surveys.

Survey data may be collected via mail, phone (IVR, toll-free, CATI), in-person, or web instrument (questionnaires, comment card, etc.) and all are established and tested survey instruments. If changes are made to the instruments, they are expected to be minor. Revising the coding scheme for open-ended questions is one example. The surveys may include several demographic items. In addition to the Office of Management and Budget (OMB) control number and Privacy Statement, all respondents will be provided with an address to offer comments concerning the data collection process.

Modes of Collection

Mail-Participants are randomly selected from a database provided by IRS and offered the survey through mail by contractor. Established fielding methods and structure will mirror the Dillman approach (Dillman “The Tailored Design Method,” 1999). These include 1) a pre-notification letter, 2) cover letter and questionnaire, 3) a postcard reminder, and 4) a copy of cover letter and questionnaire to non-respondents.

Phone-The survey data is collected via an Interactive Voice Response (IVR) phone questionnaire. Generally at the completion of a service call, callers are randomly selected to participate in the survey. If the caller agrees, they are then transferred to complete the survey. This data is then transferred to the contractor to conduct analysis and prepare reports if this optional task is exercised. If not, the analysis and reporting will be conducted by the IRS Business Unit.

Web-The sources of the sample are the database maintained by the contractor. The contractor shall use a web panel for survey administration that will accurately represent the U.S. adult taxpayer population and also accommodate skip patterns that allow for drill down analysis based on taxpayers who have used IRS services.

In-person- The respondent population consists of taxpayers who visit the Taxpayer Assistance Centers (TACs) nationwide. The survey or comment card is available to all TACs customers. TAC managers mail in the completed survey or comment cards to the contractor who then scans in the results.

3. Methods to Maximize Response

In an effort to enhance response rates, questionnaires have been tested or reviewed to ensure that the questions and instructions are clear, relevant, and unambiguous. Surveys employing non-response follow-up will require multiple contacts by telephone and/or by additional mailings of the questionnaire to ensure an adequate response. Also, weighting procedures may be applied to adjust aggregated data from those who do respond

4. Testing Procedures

IRS employees and/or their contractors who are familiar with the product or service under investigation review the questionnaires used in the surveys. In some cases, questionnaires may be pre-tested on up to nine external customers.

5. Contact for Statistical Aspects and Data Collection

SOI may be consulted with questions regarding any statistical aspects employed or data procedures used, or for administrative questions regarding the IRS use of this clearance should be directed to:

Laura R. Rasmussen

Internal Revenue Service

Statistics of Income Division

500 N. Capitol Street

Washington, DC 20001

Phone: (202) 874-1269

Michelle Sloan

Internal Revenue Service

Statistics of Income Division

500 N. Capitol Street

Washington, DC 20001

Phone: (202) 874-0683