Draft Version: Do Not Distribute
B. COLLECTION OF INFORMATION EMPLOYING STATISTICAL METHODS
B.1 Respondent universe and sample
CMS is requiring all Medicare MA, MA-PD and free-standing PDP plans that have had a contract effective for at least one year (defined in this start-up year as effective on or before Jan 1, 2006 to participate in an independent third party administration of this survey (hereinafter referred to as Medicare CAHPS). For the 2007 national Medicare CAHPS survey, the names and addresses of sampled beneficiaries shall be obtained from the Medicare Beneficiary Database (MBD) files on or shortly after November each year. Beneficiaries who have been continuously enrolled for 6 months and who are not institutionalized are included in the sampling frame. A random sample of 600 eligible beneficiaries per reporting unit is selected. If there are less than 600 eligible beneficiaries in an organization, all of the beneficiaries are selected
The survey will be conducted through use of a randomized sample of Medicare enrollees in all 50 states, the District of Columbia, the US Virgin Islands, and Puerto Rico. Because the sample design is dependent on the most recent information available from CMS enrollment databases, sampling experts from RAND, Harvard, and Westat are currently in the process of preparing the sample design for the 2006 survey. Current plans are for 600 enrollees to be drawn from each of the MA, MA-PD, and Stand-alone PDPs, as well as sufficient numbers of additional enrollees in Original Medicare to produce state-level estimates. The sampling plan will be finalized by November 2006. A data collection plan has also been developed and tested to assure sufficient survey response to provide for statistically significant CAHPS measurements in all Medicare health and prescription drug plans and in all states.
The response universe for this survey has grown considerably. The MMA legislation has increased the size and scope of the Medicare CAHPS surveys. For 2007, the number of plans to be included in the survey has grown from 208 in the 2005 MA survey, to now include 509 MA-PD plans and 81 freestanding PDPs. For plans that cover large geographic areas or have national coverage (ie Private Fee For Service), we will be splitting the organizations into multiple sampling units. We estimate that we have up to 1,000 sampling units.
B.2 Information collection procedures
The administration of the survey consists of a pre-notification letter signed by the CMS Privacy Officer sent out prior to the first questionnaire mailing, the first questionnaire mailing, a postcard reminder, and a second mailing. We conduct telephone follow-up of non-respondents.
B.3 Methods to maximize response rates
For the first round of Medicare CAHPS, we achieved a 74 percent response rate. From the first round of the survey, we learned that it would be helpful to lengthen the data collection period to get the most out of the first two mailings and to increase the period of time for telephone follow-up. For the fifth and sixth rounds of the survey, we achieved an 82 percent and 83 percent response rate, respectively.
A variety of efforts have been made to maximize our response rate. First, extensive testing of the individualized questions and their order within the survey, ensures that beneficiaries easily comprehend the questions and can answer with minimum effort. Second, the method of administration chosen pre-notification letter, two mailouts and a reminder postcard, and telephone followup of non-respondents – is a multi-pronged, comprehensive strategy that avoids the weaknesses of reliance upon mail or telephone contact alone.
B.4 Tests of procedures or methods
Not applicable. No tests of new procedures or methods are performed.
B.5 Statistical and questionnaire design consultants
We are receiving ongoing input from statisticians to develop, design, conduct, and analyze the information collected from this survey. This statistical expertise will be available from RAND and Harvard Medical School.
Marc N. Elliot, Ph.D.
RAND
1776 Main Street
Santa Monica, CA 90401-3208
Tel: 310-393-0411
Alan Zaslavsky, Ph.D.
Associate Professor of Statistics
Harvard University, Department of Health Care Policy, Harvard Medical School
| File Type | application/msword |
| Author | CMS |
| Last Modified By | CMS |
| File Modified | 2006-11-09 |
| File Created | 2006-11-09 |