Page 167 - Data Science class 11
P. 167

Advantages
            Following are the advantages of quota sampling:
               • Meets specific needs: Quota sampling is useful when the time frame to conduct a survey is limited, the research
              budget is very tight, or survey accuracy is not the priority. For example, job interviewers with a limited time frame to
              hire specific types of individuals can use quota sampling.
               • Simple: It is an easy process to carry out and decipher information once the sampling is done. It also enhances the
              representation of any particular group within the population thereby preventing over-representation of groups. This
              sampling technique saves time and resources, making it easier to implement. Moreover, interpreting the responses is
              more straightforward and takes fewer resources.

               • Accurately represents the whole population: Quota sampling is all about taking into consideration taking population
              samples. Since researchers use particular quotas, they can prevent over or underrepresentation of population.

            Disadvantages
            Following are the disadvantages of quota sampling:
               • Random selection not allowed: Since quota sampling doesn’t use random selection, detection of sampling error by
              researcher becomes difficult.
               • Not all traits taken into consideration: In quota sampling, only the pre-determined traits of the population are
              taken into consideration by researchers. For example, in a research that involves creating samples based on gender
              and income, it might not represent other traits like age, race, or religion.
               • Biased: In quota sampling, it is usually up to the researchers to decide who is sampled. Unknowingly or knowingly,
              researchers may sample a population on the basis of convenience, cost, etc., leading to bias.
            Cluster Sampling
            Cluster sampling is a method of probability sampling in which researchers divide a population into smaller groups.
            These smaller groups are called clusters. Examples of clusters can be schools or cities. They do random selection
            among these clusters to form a sample. This sampling method is usually used to study large populations, particularly
            those that are widely geographically distributed. This method is generally conducted when groups that are identical
            yet internally different form a statistical population. Instead of selecting the entire population, the researchers can
            collect data by dividing the data into small and more productive groups.

            Example
            Consider a case in which a researcher wants to conduct a study to assess the performance of second year students in
            Data Science subject of different Universities across India. Conducting a research study that involves a student in every
            university is quite impossible. By using cluster sampling, the researcher can club the universities from each city into one
            cluster. These clusters represent the second year student population across the country. Next, randomly pick clusters
            for the research study by either using simple random sampling or systematic random sampling. By using simple or
            systematic sampling, the sophomore from each of these selected clusters can be selected to conduct the research.
            Using this sampling method, researchers analyse a sample that comprises of multiple sample parameters like
            demographics, preferences, background, etc. which may be the highlight of the research.

            Advantages
            Following are the advantages of cluster sampling:
               • Convenient: By choosing large samples, researchers can increase accessibility to various clusters.
               • Data accuracy: Since there can be large samples in each cluster, loss of precision in information per person can be
              compensated.
               • Economical: This method of sampling requires fewer resources since only certain groups from the entire population
              are selected for the sampling process. It is economical as compared to other sampling techniques as it requires fewer
              administrative and travel expenses.


                                                                                              Randomisation    165
   162   163   164   165   166   167   168   169   170   171   172