MGMT 8920M Week 8 Sampling Plan Example

Who, From Where and How Many: A Sampling Plan for a Survey of Controllers at Mid-Sized Manufacturers About Rolling Forecasts, Defining the Population From the Review, Naming Who the Frame Will Miss and Sizing the Sample From the Smallest Reviewed Effect

Student Name

Walden University

MGMT 8920M: Developing the Content Literature Review and Research Method and Design

Instructor Name

Month Day, Year

Who, From Where and How Many: A Sampling Plan for a Survey of Controllers at Mid-Sized Manufacturers About Rolling Forecasts, Defining the Population From the Review, Naming Who the Frame Will Miss and Sizing the Sample From the Smallest Reviewed Effect

Population

The target population is financial controllers at US manufacturers with between 100 and 1,000 employees whose firms have used rolling forecasts, forecasts updated at regular intervals to look a fixed period ahead, for at least one year. The review chapter found that most studies of rolling forecasts and alternatives to traditional budgeting sampled firms far larger than this, many of them multinational groups, so the experience of mid-sized manufacturers is largely undescribed. The study asks whether controllers' reported involvement of operations managers in forecast updates is associated with how useful they judge rolling forecasts to be for decisions.

Sampling Frame

The frame is the member directory of a national association of management accountants, filtered by job title and by employer industry and size. Libby and Lindsay (2010) surveyed members of professional management accounting bodies in the United States and Canada about budgeting practice, which provides a precedent for reaching this population through an association. The frame will miss controllers who do not belong to the association, and it may overrepresent controllers at firms that pay for professional memberships, which could tilt the sample toward firms with more developed finance functions. That limit will be stated in chapter three and in the limitations section.

Inclusion Criteria

1. The respondent holds the title of controller or the equivalent role responsible for planning and reporting, because the review found controllers to be the people who design and run forecasting processes in firms of this size.

2. The employer is a manufacturer, because the review's gap concerns manufacturing, where production planning makes forecast accuracy especially consequential.

3. The employer has between 100 and 1,000 employees, the range the review found underrepresented.

4. The firm has used rolling forecasts for at least one year, so that respondents can judge usefulness from experience rather than intention.

Sample Size

The study's main analysis tests the correlation between two measures: operations managers' involvement in forecast updates and the perceived usefulness of rolling forecasts. The power analysis follows the approach Cohen (1988) set out and uses G∗Power, described by Faul et al. (2007). Rather than assume a conventional medium effect, the expected effect is taken from the smallest correlation between a participation measure and a usefulness measure reported among the survey studies in the review chapter's table, r = .20. Setting a two-tailed alpha at .05 and power at .80 gives a required sample of 193 usable responses. Using the smallest reviewed effect protects the study against an optimistic estimate; if the true relationship is larger, the study will be able to detect it with more certainty.

Recruitment

Invitations will be sent by email from the association to members meeting the filters, followed by two reminders at one-week intervals. Baruch and Holtom (2008), analyzing hundreds of surveys in organizational research, reported an average response rate of about 36 percent for surveys of organizations and lower rates in some later years. Surveys of senior finance staff by email tend to fall below that average, so the plan assumes a response rate of 20 percent. Reaching 193 usable responses therefore requires about 965 invitations; the plan sets a target of 1,000, with screening questions at the start of the survey to confirm that each respondent meets all four criteria.

References

Baruch, Y., & Holtom, B. C. (2008). Survey response rate levels and trends in organizational research. Human Relations, 61(8), 1139-1160. https://doi.org/10.1177/0018726708094863

Cohen, J. (1988). Statistical power analysis for the behavioral sciences (2nd ed.). Lawrence Erlbaum Associates.

Faul, F., Erdfelder, E., Lang, A.-G., & Buchner, A. (2007). G∗Power 3: A flexible statistical power analysis program for the social, behavioral, and biomedical sciences. Behavior Research Methods, 39(2), 175-191. https://doi.org/10.3758/BF03193146

Libby, T., & Lindsay, R. M. (2010). Beyond budgeting or budgeting reconsidered? A survey of North-American budgeting practice. Management Accounting Research, 21(1), 56-75. https://doi.org/10.1016/j.mar.2009.10.003