OMB Supporting Statement - Part B

Supporting Statement – Part B

Collections 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 had been conducted previously, include the actual response rate achieved during the last collection.

Response

CMS is interested in continuously measuring and improving the quality of its services by collecting information from individuals about the customer service they received in a recent communication with Medicare. This information collection request addresses four contact channels that individuals use to communicate with Medicare:

• Telephone (1-800-MEDICARE)

• Written correspondence

• E-mail

• Web chat

Each contact channel has distinct characteristics that potentially impact the services provided. As such, all individuals who contact Medicare in each of these four communication channels constitute a unique respondent universe. This approach helps ensure the quality of services is consistent for individuals, regardless of the method they choose to contact Medicare.

CMS proposes drawing two samples per month from the telephone channel for use in two existing surveys. The first is an automated survey currently conducted by the 1-800-MEDICARE interactive voice response (IVR) unit. The second survey is an outbound telephone call conducted 1-2 business days after the call to 1-800-MEDICARE. CMS proposes using one survey for each of the remaining contact channels. Table 1 summarizes statistical information for each channel.

Table 1. 1-800-MEDICARE Beneficiary Satisfaction Survey Metrics (Monthly)
Contact Channel	Estimated Potential Respondent Universe	Sample Size	Response Rate
Telephone (IVR survey)	2,160,000	1,225	4% (Actual)
Telephone (Outbound telephone survey)	2,160,000	1,225	27% (Actual)
Written correspondence	41,000	246	28% (Actual)
E-mail	6,500	102	25% (Estimated)
Web chat	20,000	214	25% (Estimated)

Proposed sampling methods for each survey are as follows:

• IVR Survey – The IVR unit conducts systematic sampling by offering the survey to 300 consecutive callers, and then does not offer it to the next 9,700 consecutive callers.

• Outbound survey – The CMS National Data Warehouse (NDW) provides a daily report of all 1-800-MEDICARE call activities. Due to the large volume of calls, current NDW reporting limitations frequently prevent exporting all call activity. As a solution, a systematic sampling plan was adopted. The 1-800-MEDICARE Beneficiary Contact Center (BCC) currently uses six contact center sites to answer beneficiaries’ calls. For each business day of the month, one of the six BCC sites is selected for the Customer Satisfaction Outbound Surveys. From the selected BCC site, a random sample is collected.

• Written Correspondence – The NDW provides a weekly report of all closed written correspondence activities. These closed activities represent letters mailed by the BCC in response to beneficiaries’ written inquiries. A simple random sample of activities is drawn from the NDW report.

• E-mail – A simple random sample will be drawn from a report of all e-mail activities.

• Web chat – A simple random sample will be drawn from a report of all Web chat activities.

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, and

- Any use of periodic (less frequent than annual) data collection cycles to reduce burden.

Response

The outbound telephone and IVR surveys use a systematic sample design, as previously noted. The remaining surveys (written correspondence, e-mail, and Web chat) will use simple random sampling. Table 2 summarizes the sampling methodology for each survey.

Table 2. 1-800-MEDICARE Beneficiary Satisfaction Survey Sampling Methodologies
Contact Channel	Sampling Method	Sampling Error	Population Proportion	Sample Size
Telephone (IVR survey)	Systematic	0.02	0.85	1,225
Telephone (Outbound telephone survey)	Systematic	0.02	0.85	1,225
Written correspondence	Simple random	0.05	0.80	246
E-mail	Simple random	0.07	0.80	102
Web chat	Simple random	0.05	0.80	214

The justifications for the variations in sampling error and population proportion are as follows:

• Sampling error – The most commonly used contact channel is 1-800-MEDICARE, receiving well over one million calls per month. The volume of remaining channels combined constitutes less than five percent of this figure. Actions undertaken to improve 1-800-MEDICARE based on survey data are likely to impact more beneficiaries and require substantially more effort, and therefore a lower level of error is desired.

• Population proportion – The population proportions in Table 2 represent the estimated “success” rates for each contact channel. For the IVR, outbound telephone, and written correspondence surveys these figures are based on results from previous collections. For e-mail and Web chat, these figures are conservative estimates as no baseline data for these populations are known to exist.

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.

Response

Surveys are conducted during standard business hours with consideration given to the time zone of potential respondents to maximize response rates.

4. Describe any tests of procedures or methods to be undertaken. Testing is encouraged as an effective means of refining collections of information to minimize burden and improve utility. Tests must be approved if they call for answers to identical questions from 10 or more respondents. A proposed test or set of tests may be submitted for approval separate­ly or in combination with the main collection of information.

Response

No tests of procedures or methods will be undertaken for this collection.

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), grantee(s), or other person(s) who will actually collect and/or analyze the information for the agency.

Response

Name	Agency/ Contractor Name	Telephone Number
Adrian Terrel	Briljent, LLC	317-735-3496
David Linn	Briljent, LLC	317-735-3522

4