Population is defined as including all items with the characteristic one wishes to understand. Because there is seldom enough time or money to gather information from everyone or everything in a population, the goal is to find a representative sample (or subset) of that population. For example, a researcher might study the success rate of a new ‘quit smoking’ program on a sample group of 50 patients, in order to predict the effects of the program if it were made available nationwide. Here the superpopulation is “everybody in the country, given access to this treatment” – a group which does not exist, since the program isn’t yet available to all.

Sampling Frame:

Sampling Frame refers to the selection of a subset of individuals/items from a population to form the sample for our survey. There are two types of sampling methods: Probability Sampling and Non-Probability Sampling. Definition and Difference between Probability Sampling and Non-Probability Sampling Probability methods require a sample frame.

Probability methods rely on random selection in a variety of ways from the sample frame of the population. They permit the use of higher level statistical techniques and allow you to calculate the difference between your sample results and the population equivalent values so that you can confidently state that you know the population values. Non-probability methods does not have this allowance. However non-probability samples are available even when you have no sample frame. They are generally less complicated to undertake. They minimise the preparation costs of a survey, and are used when you are actually unsure of the population of interest. Types of Probability Sampling:

1.Simple random sampling:

In a simple random sampling of a particular size, all subsets of the frame are given an equal probability. Each element of the frame has an equal probability of selection: the frame is not subdivided. Furthermore, any given pair of elements has the same probability of selection as other such pairs. This reduces bias and simplifies the analysis of results.

The problem with SRS is that it can produce sampling error because the randomness of the selection may result in a sample that doesn’t reflect the picture of the whole population. For example, a simple random sample of ten people from a country will on average produce 5 men and 5 women, but any given trial will result in over representation of 1sex and under representation of other sex. Systematic and stratified probability sampling methodology attempt to overcome this problem by using information about the population to select a more representative sample.

SRS may also be tedious when sampling from an very large target population.Sometimes, investigators are interested in research questions specific to particular subgroup of the population. For example they might be interested in examining if cognitive ability as a predictor of job performance is equally applicable across racial groups. SRS cannot satisfy the needs of researchers in this case because it does not provide subsamples of the population. Stratified sampling, addresses this weakness of SRS.Simple random sampling is always qualified as an EPS design (equal probability of selection), but not all EPS design qualify as simple random sampling.

2. Systematic sampling

In Systematic sampling, have to arrange the study population according to some ordering scheme and then select elements at regular intervals through that ordered list. It involves a random start and then proceeds with the selection of every kth element from then onwards. In this case, k is the population size or sample size. It is important that the starting point is not automatically the first in the list, but is instead randomly chosen from within the first to the kth element in the list For example, if we wish to sample people from a long street that starts in a poor area (house No. 1) and ends in an expensive area (house No. 1000).

A simple random selection of houses from this street could easily end up with too many from the expensive end and too few from the poor end (or vice versa), leading to an unrepresentative sample.Selecting (e.g.) every 10th street number along the street ensures that the sample is spread evenly along the length of the street.

3.Stratified sampling

Where the population encloses a number of distinct categories, the frame can be organized by these categories into separate strata. Each stratum is then considered as an independent sub-population, out of which individual elements can be randomly selected. Advantages:

1. Dividing the population into distinct strata can help researchers to form inferences about specific category of that population that is not possible in random sampling. 2. This approach results in a more efficient statistical estimates provided the selected strata is in relevance to the criterian in question.It would definitely not reduce the statistical efficiency. Finally, since each stratum is considered as an independent population, different sampling methodologies can be applied to different strata.One of the disadvantage of this sampling method is that it increases the cost and complexity of the population estimates.

4.Cluster sampling

Sampling is often clustered by geography or by time periods. For example,if we are surveying households within a city, we might choose to select hundred city blocks and then interview every household within the selected blocks.The advantage of Cluster sampling is that it reduces travelling and administrative cost to a large extent. In the instance stated above, an interviewer can make a single trip to visit several households in one block, rather than driving to a different block for each household. Cluster sampling is generally implemented as multistage sampling.

This complex form of clustering consists of two or more levels of units embedded one in the other. The first stage will be used to construct cluster which we will use to make samples.The second stage consists of randomly selecting samples from each cluster (rather than using all units contained in all selected clusters). In the next stage, from each of those selected clusters, additional samples of units are selected, and so on. The ultimate units selected at the last step of this procedure are then surveyed

5.Quota sampling

In quota sampling probability method, the population is first divided into mutually exclusive sub-groups, similar to stratified sampling. Then judgement is used to select the subjects or units from each segment based on a specified proportion. For example, an interviewer may be told to sample 200 females and 300 males between the age of 45yrs and 60yrs. In this sampling method, sample selection is non-random. For example interviewers might be tempted to interview those who look most helpful. The disadvantage is that these samples may be biased because not everyone gets a chance of selection

Types of Non-Probability Sampling:

1. Convenience or haphazard sampling:

Also known as haphazard or accidental sampling.This methodology is not considered as representative of target population because sample units are selected only if they can be easily accessed and are available.Example of when the average person uses convenience sampling. A food critic may try several appetizers or several entrees to judge the quality and variety of a menu.

Television reporters often seek so-called â€˜people-on-the-street interviews’ to find out how people view an issue. In both these examples, the sample is chosen randomly, without use of a specific survey method.The advantage is that this method is easy to use, but that advantage is greatly offset by the presence of bias. For example, a scientist could use this method to determine whether a lake is polluted. Assuming that the lake water is well-mixed, any sample would yield similar information. A scientist could safely draw water anywhere on the lake without fretting about whether or not the sample is representative. 2. Volunteer sampling

This type of sampling occurs when people volunteer their services for the study. In psychological experiments or pharmaceutical trials (drug testing) it would be difficult and unethical to enlist random participants from the general public. In cases like these, the sample is taken from a group of volunteers. Sometimes, the researchers also pays the volunteers for their contribution The disadvantage of volunteer sampling is that it introduces string biases in thesurvey because only the people who care strongly enough about the subject one way or another tend to respond. The silent majority does not typically respond, resulting in large selection bias. 3.Judgement sampling

Judgement sampling is used when a sample is taken based on certain judgements about the overall population. Objectivity is the main issue iin this sampling method i.e how much can judgment be relied upon to arrive at a typical sample? Judgement sampling is depends on the researcher’s biases and is perhaps even more biased than haphazard sampling. Large biases can be introduced if preconceptions made by researchers are inaccurate. One advantage of judgement sampling is the reduced cost and time involved in acquiring the sample. Statisticians often use this method in exploratory studies like pre-testing of questionnaires and focus groups. They methodis used in laboratory settings where the choice of experimental subjects (i.e., animal, human, vegetable) and the observation reflects the investigator’s pre-existing beliefs about the population.