0990-EvaluationWomensHealthPublication

B. Collections of Information Employing Statistical Methods

1. Respondent Universe and Sampling Methods

The respondent universe will be the population who receive the materials and therefore surveys. It is expected that 1% of women receiving the materials will return the survey. Thus, 666,160 women will make up the respondent universe. The table below illustrates the stratified sample. The universe and sample size for each strata are based on probable distributions of each material.

OWH Material	N Universe	N Sample
Easy Guide to Breastfeeding	499,910	5,000
Lifetime of Good Health Guide	116,250	1,163
Teen Survival Guide	50,000	500
Total	666,160	6,663

2. Procedures for the Collection of Information

All of the women receiving the materials and therefore in the respondent universe, (666,160) will be invited to participate in a survey. A 1% response rate is expected. Thus, 6,663 completed surveys are expected. The universe will be stratified into the following categories based on material: Easy Guide to Breastfeeding, Lifetime of Good Health Guide, and Teen Survival Guide. Stratification will mirror the distribution of OWH materials.

As described above, for the purposes of this investigation a statistical power of 80% is needed. The needed sample size, assuming a small to medium effect size and an alpha of .05, is well below the anticipated response. No special problems requiring specialized sampling procedures exist. As this is a one time data collection, it is not possible to collect data any less frequently.

3. Methods to Maximize Response Rates and Deal with Nonresponse

Efforts to maximize response rates will include the use of an incentive Respondents will be informed in each material distributed of the incentive for participating in the survey.

4. Tests of Procedures or Methods to be Undertaken

Cognitive testing with nine or fewer women was conducted on each data collection instrument. Feedback from women was incorporated into the survey instruments.

5. Individuals Consulted on Statistical Aspects and Individuals Collecting and/or Analyzing Data.

Data will be collected and analyzed by Shattuck and Associates, 800-829-1777.Works Cited

Schonlau, M., Asch, B. J., & Du, C. (2003). Web survey as part of a mixed-mode strategy for populations that cannot be contacted by e-mail. Social Science Computer Review, 21(2), 218-222.

Shettle, C. and Mooney, G. (1996). Evaluation of Uinsg Monetary Incentives in a Government Survey. Paper presented at the Joint Statistical Meetings, Chicago, IL.

Witmer, D. F., Colman, R. W. and Katzman, S. L. (1999) From paper-and-pencil to screen-and-keyboard: Toward a methodology for survey research on the internet. Doing internet research: Critical issues and methods for examining the net, Jones, S. ed., pp. 145–161. Sage, Thousand Oaks, CA.