Sampling Design
Download as PPT, PDF1 like112 views
This document discusses sampling design for research. It explains that sampling design refers to the method used to collect data from a subset of a population. A proper sampling design starts with a sample that is representative of the population. There are two main types of sampling: census, which investigates all individuals in a population, and sampling, which uses a small number from the larger population due to constraints. The document outlines key concepts in sampling design including the target population, study population, sampling frame, probability and non-probability sampling methods, and factors to consider for an appropriate sample size and design.
Sampling Design
- 1. Sampling Design R.VASANTHAGOPAL PhD University of Kerala
- 2. 26 April 2020 R.Vasanthagopal PhD 2 Research Research- organized set of activities to find practical solution for a realistic problem supported by data
- 3. Research Process Formulating the research problem Survey and review of literature Asking research questions and developing hypothesis Deciding on the research design Sampling design Collecting data Analysis and interpretation of data Testing the hypotheses Findings, conclusion and suggestions Report writing 26 April 2020 R.Vasanthagopal PhD 3
- 4. Sampling Design….. 26 April 2020 R.Vasanthagopal PhD 4 Design of a sample refers to the method used to collect the data A proper sampling design must start with a sample which is representative of the population
- 5. Census Vs. Sampling 26 April 2020 R.Vasanthagopal PhD 5 Investigation of all individual elements Using a small number of items of larger population Impracticable to survey the entire population Budget constraints Time constraints Immediate need of results
- 6. Target Population, Study Population and Sample 26 April 2020 R.Vasanthagopal PhD 6 Sampling frame: The list from which the potential respondents are drawn viz. list of employees
- 7. Sampling Scheme/Methods/Techniques 26 April 2020 R.Vasanthagopal PhD 7 All units in the population have an equal probability of being chosen Sample selection not based on the rationale of probability theory
- 8. Probability Vs. Non-probability Sampling 26 April 2020 R.Vasanthagopal PhD 8
- 9. What is Appropriate Sample Design? Degree of accuracy Resources Time Need for statistical analysis Representative of the population Appropriately sized (the larger the better) Random (selections occur by chance) 26 April 2020 R.Vasanthagopal PhD 9
- 10. Determination of Sample Size A survey estimated that 20% of all Indians aged 21 to 35 drove under the influence of alcohol. A similar survey is planned for Kerala. They want a 95% confidence interval to have a margin of error of 0.04. 26 April 2020 R.Vasanthagopal PhD 10 n=.20(1-.20)1.96x1.96/.04x.04 =384.2 Note: z is the z-score, e.g. 1.645 for a 90% confidence interval,1.96 for a 95% confidence interval, 2.58 for a 99% confidence interval Note: Typical surveys have margins of error ranging from less than 1% to something of the order of 4% - we can choose any margin of error we like but need to specify it. Sample size formula n=N/1+Ne2 Solvin’s(1960) Formula(When population is known. Where e=Margin of error