Insurance Survey Justification B

B. COLLECTIONS OF INFORMATION EMPLOYING STATISTICAL METHODS

1. Provide a numerical estimate of the potential respondent universe and describe any sampling or other respondent selection method to be used. Data on the number of entities (e.g. households or persons) in the universe and the corresponding sample are to be provided in tabular format for the universe as a whole and for each strata. Indicate expected response rates. If this has been conducted previously include actual response rates achieved.

The information below was determined by using averages over the course of the last three full fiscal years (FY 2014 – FY 2016).

During a 12-month period, 480 Beneficiary surveys will be released to insured/beneficiaries.

End Product	Surveys To Be Released	Actual Response (Number)	Expected Response (Percent)
Mail Survey	480	299	62%

During a 12-month period, 480 Cash Surrender surveys will be released to insured.

End Product	Surveys To Be Released	Actual Response (Number)	Expected Response (Percent)
Mail Survey	480	270	56%

During a 12-month period, 480 Correspondence surveys will be released to insured.

End Product	Surveys To Be Released	Actual Response (Number)	Expected Response (Percent)
Mail Survey	480	191	40%

During a 12-month period, 480 Insurance Claims surveys will be released to insured/beneficiaries.

End Product	Surveys To Be Released	Actual Response (Number)	Expected Response (Percent)
Mail Survey	480	253	53%

During a 12-month period, 480 Policy Loan surveys will be released to insured.

End Product	Surveys To Be Released	Actual Response (Number)	Expected Response (Percent)
Mail Survey	480	181	38%

During a 12-month period, 480 Insurance (S-DVI) Application surveys will be released to insured.

End Product	Surveys To Be Released	Actual Response (Number)	Expected Response (Percent)
Mail Survey	476*	184	39%

During a 12-month period, 480 Waiver of Premiums surveys will be released to insured.

End Product	Surveys To Be Released	Actual Response (Number)	Expected Response (Percent)
Mail Survey	480	202	42%

During a 12-month period, 480 VMLI surveys will be released to insured.

End Product	Surveys To Be Released	Actual Response (Number)	Expected Response (Percent)
Mail Survey	449*	166	37%

During a 12-month period, 600 Telephone Service (120 ICD and 480 PSD) surveys will be released to insured/beneficiaries.

End Product	Surveys To Be Released	Actual Response (Number)	Expected Response (Percent)
Mail Survey	600	281	47%

*Any surveys with less than 40 sent per month are due to not enough end products available to acquire the proper amount of surveys from.

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

• Statistical methodology for stratification and sample selection

Type of Survey	Selection Process	Mailing Method
Policyholder Services Division
Telephone Service Surveyed Monthly: 50 (40 Policy Service and 10 Death Claims)	Manual – selected from the Telephone Interview Evaluation sheet.	Manually printed, stuffed and mailed
Loans Surveyed Monthly: 40	Automated – VICTARS SQC Reports	Manually printed, stuffed and mailed
Cash Surrenders Surveyed Monthly: 40	Automated – VICTARS SQC Reports	Manually printed, stuffed and mailed
Correspondence Surveyed Monthly: 40	Automated – VICTARS SQC Reports	Manually printed, stuffed and mailed
Type of Survey	Selection Process	Mailing Method
Insurance Claims Division
Waiver of Premiums Surveyed Monthly: 40	Automatic – VICTARS	Manually printed, stuffed and mailed
Insurance Claims Surveyed Monthly: 40	Automatic - VICTARS	Manually printed, stuffed and mailed
Insurance (S-DVI) Application Surveyed Monthly: 40	Automatic – VICTARS	Manually printed, stuffed and mailed
Beneficiary Surveyed Monthly: 40	Automatic – VICTARS	Manually printed, stuffed and mailed
VMLI Surveyed Monthly: 40	Automatic – VICTARS	Manually printed, stuffed and mailed

• Estimation procedure

The sample size of 40 surveys per category was determined for all survey categories. The sample size was established and approved in the mid-nineteen nineties by the VBA Office of Surveys and Research and validated by the Chief, Insurance Actuarial Staff.

We will survey 40 randomly selected Veterans/ beneficiaries per month for each of the Insurance end products. The sample size is 95% confidence level with a 3% error tolerance rate.

The sample size formula that we utilize assumes a standard normal distribution, which is appropriate since we process a sufficiently large number of cases, correspondence, calls, etc. to assume a normally distributed population.

 

The parameters required for the formula are:

    Population size  =  N

    Sampling error tolerance  =  e

    Confidence level expressed in number of standard deviations (i.e., 1.96 for 95% confidence level, 1.64 for 90% confidence level)   =  z

    True proportion of the characteristic being sampled for in the population  =  p  (This can be estimated from a pilot sample or prior experience.)

 

The formula that we use to calculate the sample size (n) is:

 

    n  =  [N*z^2*p*(1-p)]/[N*e^2+z^2*p*(1-p)]

• Degree of accuracy needed

The above formula will yield a 95% confidence level with a 3% error tolerance rate.

The final high ratings of returned responses are a weighted calculation based on the number of responses and end products in each category of service sampled.

• Unusual problems requiring specialized sampling procedures

No unusual problems requiring specialized sampling procedures.

• Any use of less frequent than annual data collection to reduce burden

N/A

3. Describe methods to maximize response rate 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.

To maximize response rates, a cover letter is released with the survey explaining how the response will help improve service to all our insured Veterans. The response rate for FY09 was 53% for eleven surveys mailed. The 53% overall response rate was calculated by the average of the four Policyholder Services Division surveys (55%) and the seven Insurance Claims Division surveys (50%).

According to Custom Insight and NCS Pearson, leading survey research companies, the private industry rate of response for surveys ranges between 10- 20%. Therefore, the Insurance response rate is well above the average. In light of this, and due to the fact the Insurance expenses are borne by the Policyholders, it would be counterproductive to send a follow-up letter with each survey. An additional follow-up letter would also delay our ability to provide timely information to management (e.g. trends and problems), which is derived from the returned surveys.

4. Describe any tests of procedures or methods to be undertaken. Testing is encouraged as an effective means of refining collections to minimize burden and improve utility. Tests must be approved if they call for answers to identical questions of 10 or more individuals.

No testing of procedures or methods is required for the surveys.

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.

Donna Wagner

Budget Analyst, Strategic Planning and Budget Staff

Insurance Center

Department of Veterans Affairs

Philadelphia, PA 19144

(215) 842-2000, ext. 4313

4