Importance of Sampling design & Sample size
Download as PPT, PDF41 likes31,329 views
The document discusses the importance and benefits of sampling over a census for research purposes. It notes that sampling saves time and money compared to a census. Additionally, a sample may be more accurate than a census due to limitations in resources and risks of introducing unpopular actions to an entire market. The document also emphasizes that both sampling design and sample size are important considerations, as an inappropriate design will not allow findings to be generalized even with a large sample, and an inadequate sample size cannot meet study objectives. It provides some general guidelines for appropriate sample sizes.
Importance of Sampling design & Sample size
- 1. IMPORTANCE OF SAMPLING A sample saves money and time. Compare a sample versus a census: Far greater speed in completing a 5% randomly selected sample, as opposed to increasingly larger surveys (10%, 20%, etc.) Few census designs would satisfy the value of information constraint in marketing research. Sample size is directly related to the cost of a study, the more representative the sample, the lower the sample size needed.
- 2. IMPORTANCE OF SAMPLING A sample may be more accurate than a census. A census requires enormous numbers of interviewers, supervisors of interviewers, and people for data entry. There is limited supply of qualified labor available for any research purpose, which minimize sampling error. A sample is better in the event that the study results in the destruction or contamination of the element sampled. You don't want to risk the potential disadvantages of introducing a unpopular marketing action (advertisement, product, or price) to an entire market.
- 3. IMPORTANCE OF SAMPLING DESIGN AND SAMPLE SIZE Sampling decisions should consider both sampling design and sample size, because If the sampling design is inappropriate, a large sample size will not allow the findings to be generalized. If the sample size is inadequate, no sampling design, can be useful in meeting the objectives of the study
- 4. IMPORTANCE OF SAMPLING DESIGN AND SAMPLE SIZE There are some general rules regarding sample size Sample sizes larger than 30 and less than 500 are appropriate for most research. Where samples consists of subsets like male/ female, rural/ urban etc, it is appropriate to ensure a minimum sample size of 30 for each subset In multivariate research, the sample size should be several times as large as the number of variables in the study For simple experimental research with tight controls, a sample size of 10 to 20 is adequate.
- 5. Sample Size Determination for a Mean: Interval or Ratio Questionnaire Items Where… n = the sample size z = standard error associated with the chosen level of confidence s = variability indicated by an estimated standard deviation e = acceptable error 2 22 e zs n =
- 6. Sample Size Determination for a Mean: Interval or Ratio Questionnaire Items Where… n = the sample size z = standard error associated with the chosen level of confidence s = variability indicated by an estimated standard deviation e = acceptable error 2 22 e zs n =