When making inferences from data analysis, sample assumes a primary position. Sample for any research should be selected by following a particular sampling plan. It is a method of selecting a sample of subjects from an entire population targeted for the study.
For example, to study the effect of television advertisement of Baby Food on buying propensity of viewers, a target population will be parents and would-be parents of children aged 5 years or below in the city of Amritsar. However, it is practically difficult to gather data of all the television viewers who are either parents or would-be parents residing in Amritsar.
Hence, the researcher needs to select a sample out of the entire population, based on a particular country and area. Further, it is important to note that, sample and target population should be similar to each other. This helps to provide a generalised observation at the end of the study and also avoid biasness in the results.
Types of sampling plan
The sampling plan is broadly classified into– probability and non-probability sampling.
The probability of getting selected in a sample is equal for all the members of the population in probability sampling method. Furthermore, in case of non-probability the chance of getting selected in a sample is not equal for every member.
Probability sampling plans
Simple random results in an equal probability of selection for all the elements in the population. Random numbers are selected from an ordered list to select the samples.
Stratified requires the population to be divided into sub-populations known as strata and that probability sampling be conducted independently in each stratum.
For example, gender, position occupied, location, etc. In this case researcher divides the population in different groups and then for each group conduct the random sampling .
In Systematic random each element has a specific probability of getting selected. However, when combined, elements have different probabilities. The error rate of selecting a sample is same as simple random sampling if the list is too random or haphazard.
In Random cluster, the population is divided into groups like geographic and organisational, where the groups are selected randomly. Pure cluster sampling takes the whole cluster as a sample. However, in case of multistage cluster, random sampling is done within the cluster. Error in case of cluster sampling increases if clusters selected are different from each other.
Non-probability sampling plans
Convenience sampling plan involves selection of sample which is close to hand and is readily available and convenient. Limitation of this approach is that it is difficult to draw interpretations because the sample would not be representative enough.
Snowball is a type of convenience which uses the existing study subjects to recruit more subjects within the sample for analysis. Also known as chain referral, researcher often use this method to find and recruit “hidden populations,” that is, groups not easily accessible to researchers through other strategies.
For example: Aids patients, Drug addicts, Victims of Human Trafficking
In case of Purposive sampling researcher select a sample on the basis of his/her judgement i.e. who they think is appropriate for the study. This approach is used where there is few people that have expertise in the area which is being researched.
In Quota sampling researcher do not select the sample randomly. Sample collection depends on some quota which can reflect major characteristics of the population.
- Daniel, J. (2011). Sampling Essentials: Practical Guidelines for Making Sampling Choices. SAGE.
- Hilliard, S. (2007). Re: Attribute Vs Variable Sampling.
- Lunsford, T., & Lunsford, B. (1995). The Research Sample, Part I: Sampling. JPO: Journal of Prosthetics and …, 7(3), 17A.
- Schutt, R. K. (2015). Sampling. In Investigating the Social World (8th ed., pp. 148–189). Singapore: Sage Publications. Retrieved from https://us.sagepub.com/en-us/nam/investigating-the-social-world/book242232
- Som, R. K. (1995). Practical Sampling Techniques (2nd ed.). CRC Press.
- Wilumila, M. F. (2002). Sampling In Research. Nairobi. Retrieved from https://www.uonbi.ac.ke/fridah_mugo/files/mugo02sampling.pdf
She is a true Piscean. She loves doing things to perfection with passion. She is very creative and likes to make personalized gifts for her dear ones, this is actually something that keeps her going. Shruti loves adventure sports and likes river rafting and cliff jumping.
Latest posts by Shruti Datt (see all)
- Matrices and arrays in MATLAB - November 15, 2018
- Understanding the process of selecting data entry formats in meta-analysis - October 22, 2017
- Variable returns to scale in DEA and summary of efficiency and slacks - October 10, 2017