RESEARCH METHODS-2 (SEMESTER-6) SAMPLING

Sampling is the statistical process of selecting a subset (called a “sample”) of a population of interest for purpose of making observations and statistical inferences about that population. Social science research is generally about inferring patterns of behaviors within specific populations. And since we cannot study entire populations because of feasibility and cost constraints, and hence, we must select a representative sample from the population of interest for observation and analysis.

Sampling has various benefits to us. Some of the advantages are listed below-

Ø  By reducing the amount of data, sampling saves a lot of time.

Ø  Taking a sample ensures the job is not monotonous. Researcher doesn’t have to run the question over and over for each piece of data.

Ø  It enables us to obtain near-accurate results in a much shorter period.

Ø  When using correct methods, sampling is more likely to obtain a higher degree of accuracy than not sampling in certain cases due to reduced monotony, data handling problems, and so on

Ø  Even with a limited number of tools, one can get accurate information on the data by using sampling.

But sampling has certain disadvantages too-

Ø  Since selecting a sampling method is a judgmental process, there is a risk of bias based on the mindset of the individual making the decision.

Ø  If the sampling techniques are chosen incorrectly, the entire process can fail.

Ø  Selection of proper size of samples is a difficult job.

Ø  Sampling may exclude some data that might not be homogenous to the data that are taken. This affects the level of accuracy in the results.

Sociologists typically use two sampling techniques: those based on probability and those that are not.

Probability Sampling Techniques:-

The probability model is a technique wherein samples are gathered in a way that gives all the individuals in the population an equal chance of being selected. Many consider this to be the more methodologically rigorous approach to sampling because it eliminates social biases that could shape the research sample. There are four kinds of probability sampling techniques.

1. Random Sampling-

Random Sampling is the basic sampling method assumed in statistical methods and computations. To collect a random sample, each unit of the target population is assigned a number. A set of random numbers is then generated and the units of those numbers are included in the sample. For example- A researcher studying a population of 1,000 might wish to choose a random sample of 50 people. First, each person is numbered 1 through 1,000. Then, generate a list of 50 random number, and the individuals assigned those numbers are the ones included in the sample.

When studying people, this technique is best used with a homogenous population, or one that does not differ much by age, race, education level, or class. This is because when dealing with a more heterogeneous population, a researcher runs the risk of creating a biased sample if demographic differences are not taken into account.

2. Systematic Sampling-

In a systematic sample, the elements of the population are put into a list and then every ‘n’th element in the list is chosen systematically for inclusion in the sample. For example, if the population of study contained 2,000 students at a high school and the researcher wanted a sample of 100 students, the students would be put into list form and then every 20th student would be selected for inclusion in the sample. To ensure against any possible human bias in this method, the researcher should select the first individual at random. This is technically called a systematic sample with a random start.

3. Stratified Random Sampling-

A stratified sample is a sampling technique in which the researcher divides the entire target population into different sub-groups or strata, and then randomly selects the final subjects proportionally from the different strata. This type of sampling is used when the researcher wants to highlight specific subgroups within the population.

For example, to obtain a stratified sample of university students, the researcher would first organize the population by college class and then select appropriate numbers of freshmen, juniors, and seniors. This would ensure that the researcher has adequate amounts of subjects from each class in the final sample.

4. Cluster Sampling-

Cluster sampling may be used when it is either impossible or impractical to compile an exhaustive list of the elements that make up the target population. Usually, however, the population elements are already grouped into sub-populations and lists of those sub-populations already exist or can be created. For instance- Perhaps a study's target population is church members in the United States. There is no list of all church members in the country. The researcher could, however, create a list of churches in the United States, choose a sample of churches, and then obtain lists of members from those churches.

Non-Probability Sampling Techniques:- 

Non-probability sampling can be described as a sampling technique in which samples are chosen based on the researcher's subjective judgement rather than random selection. It's a more lenient approach. The researchers' expertise is highly reliant on this sampling process. It is carried out by evaluation, and it is commonly used in qualitative research. In contrast to probability sampling, non-probability sampling is a sampling process in which not all members of the population have an equal chance of participating in the sample. Every individual in the population has an equal chance of being chosen. For exploratory experiments, such as a pilot survey, non-probability sampling is ideal (deploying a survey to a smaller sample compared to pre-determined sample size). Researchers use this approach in studies where random probability sampling is difficult due to time or cost constraints. There are five kinds of non-probability sampling.

1. Convenience sampling-

Convenience sampling is a non-probability sampling method in which samples are chosen from the population solely based on their accessibility to the researcher. The researchers choose these samples solely because they are easy to hire, and they did not consider choosing a sample that is representative of the entire population.
In testing, it is ideal to analyze a sample that is representative of the population. However, the population of some studies is too broad to analyze and consider the whole population. Because of its speed, cost-effectiveness, and ease of availability, convenience sampling, the most popular non-probability sampling process, is one of the reasons why researchers rely on it.

2. Quota sampling-

Assume that a researcher wants to investigate the career aspirations of male and female workers in a business. The company has 500 workers, also known as the workforce. The researcher would only need a subset of the population, not the whole population, to get a better understanding of it. Furthermore, the researcher is interested in specific population strata.

3. Purposive sampling-

The judgmental sampling method selects samples solely based on the researcher's knowledge and credibility. In other words, researchers choose only those individuals that they believe are suitable for participation in the study. Judgmental or purposive sampling is not a scientific method of sampling, and the disadvantage is that it exposes a researcher's preconceived ideas. Thus, this research technique involves a high amount of ambiguity.

4. Snowball sampling-

Snowball sampling aids researchers in locating samples that are difficult to identify. When the sample size is limited and not readily accessible, researchers use this method. This sampling scheme functions similarly to a referral program. Once the researchers have found suitable subjects, he asks for their help in finding similar subjects so that a sufficiently large sample can be created.

5. Dimensional sampling-

Quota sampling is supplemented by dimensional sampling. Sex, age, salary, home, and education are all factors considered by the researcher. The researcher must ensure that each of the chosen characteristics is represented by at least one individual in the sample. For example, out of 10 people the researcher ensures they have interviewed 2 people that are a certain gender, 2 a certain age group and 2 who have an income between any certain intervals.