Definition

Probability Sampling involves the use of a random selection process to select a sample from elements of a population.

Characteristics It gives all the individuals in the population equal chances of being selected. The goal is to examine representative elements of populations. There are five types of probability sampling 1. Simple random sampling 2. Stratified random sampling 3. Systematic random sampling 4. Cluster/multistage sampling 1- Simple random sampling Definition It is a type of probability sampling that ensures each element of the population has an equal and independent chance of being chosen. Prerequisites Population must be homogeneous. Researcher must have list of the elements. Methods The lottery method The use of table of random numbers The use of computer The lottery methods Each member of the population is assigned a unique number. Each number is placed in a bowl or a hat and mixed thoroughly . The blind folded researcher then picks numbered tags from the hat.

 All the individuals bearing the numbers picked by the researcher are the subjects for the study. The use of table of random numbers Example selecting a sample of 15 from a population of 80 Assign a number to each element of the accessible population Enter the table of random numbers at an arbitrary or random starting point. You might close your eyes and blindly point to a number in the table. Suppose you choose number 58. Continue in a systematic way either up, down, to the left, right, or diagonally. The direction is not important, but make the decision before You start the process, and continue this direction until the total samples is selected. Continue to select numbers until you select 15 numbers. The number are circle in table. If you encounter a number more than once, skip it. The use of computer Nowadays random tables may be generated from the computer and subjects may be selected as described in the used of random table.

Simple random sampling Advantages Most reliable and unbiased method. Require minimum knowledge of study population. Free from sampling errors/bias.

Disadvantage Needs up to date complete list of all the members of the population. Expensive and time consuming. 2- Stratified random sampling A probability sampling procedure that is a variation of simple random sampling. This method is used for heterogeneous population. The populations divided into homogenous subgroups or strata according to some variable or variables of importance to the research study. Variables commonly used for stratification include age, gender, ethnicity, socioeconomic status, diagnosis, geographic region, type of care etc. After dividing the population into subgroup the researcher decides how large a sample is required from each subgroup. Two types of approaches may be used. Proportional stratified sampling or disproportional sampling . 1- Proportionate stratified random sampling In this the sample chosen from each stratum is in, proportion to the size of the total population. This means that the each stratum has the same sampling fraction. Stratum Population size Sampling fraction Final sample size A 100 1/2 50 B 200 1/2 100 C 300 1/2 150 stratified

2- Disproportionate stratified random sampling In this subtype the sample chosen from each stratum are not in proportion to size of total population in that stratum. With disproportionate sampling, the different strata have different sampling fraction. Stratum Population size Sampling fraction Final sample size Advantages Ensures representative sample in heterogeneous population. Comparison is possible in two groups. Disadvantages Requires complete information of population. Large population is required. Chances of faulty classification of strata. 3- Cluster sampling: multistage sampling Definition A form of sampling in which large groupings[ clusters] are selected first [e,g, nursing schools], with successive sub sampling of smaller units [e.g nursing students]. A 100 1/2 50 B 200 1/4 50 C 300 1/6 50

Prerequisite A sampling frame is developed that includes the list of states, cities, institutions or organizations with which the elements of the identified population would be linked. The cluster can be selected by simple or stratified methods. Because the sample is selected from cluster in two or more separate stages, the approach is sometimes called multistage sampling. Advantages Cheap, quick, and easy for a large population Saves time and money. Arrangements made with small no. of sampling units. Characteristics of clusters as well as those of population can be estimated. Disadvantages Larger sampling errors than other probability samples. Requires assignment of each member of population uniquely to a cluster. Statistics are more complicated. 4- Systematic random sampling Systematic Random sampling is done when an ordered list of all population is available. The process involves selecting every kth element of the population, such as every fifth, tenth etc. First decide the no of Population(N), then sample size(n). Sampling interval width (k) is determined by N/n. E g . In a population of 500 for a sample of 50,the sampling interval would be k= 500/ 50= 10.

Criteria a) The sampling frame must be random with respect to the variable of interest and , b) The first element or member of the sample must be selected randomly. [ table of random number] . If not the sample becomes a non-probability sample. Later every Kth subject is selected from sampling frame. Advantages Easy to draw sample Economical Time saving technique Disadvantages Samples may be biased if ordering of population is not random. After the 1st sampling element chosen, population members no longer have equal chances of being chosen . Non probability sampling technique Definition Non probability sampling is a technique wherein the samples are gathered in a process that does not give all the individuals in the population equal chances of being selected in the sample. In non-probability sampling the sample elements are chosen from the population by nonrandom methods. Not every element in the population has an opportunity for selection in sample. Types of non-probability sampling techniques 1234Convenience Sampling [ accidental or incidental] Snowball sampling [Network sampling] Quota sampling Purposive sampling [ judgmental /authoritative ]

1- Convenience sampling Definition Convenience sampling is a non-probability sampling technique wherein subjects are selected because of their convenient accessibility and proximity to the researcher. It involves choosing readily available subjects for a study. These elements may or may not be typical of the population.

May be unreliable. Advantages Inexpensive, accessible- saves time and money. Disadvantages Sampling bias. The sample is not representative of the entire population. Findings generated from these samples cannot be generated on the populations. 2- Snowball sampling Definition This term is used to describe a method of sampling that involves the assistance of study subjects to help obtain other potential subjects. Eg. Drug user, HIV/AIDS among commercial sex workers. It is also called chain referral sampling. Linear snowball sampling:- In this each selected sample is asked to provide reference of only one similar subject; where a linear chain is created by the completion of desired sample.

Exponential non discriminative snowball sampling In this each sample member is asked to provide reference of at least two similar subjects because of which the size of the sample size grows exponentially and a large sample size can be achieved.

Exponential discriminative snowball sampling In this initially one sample is selected and asked for two references of similar subjects, out of which at least one subjects must be active to provide further references and another could be non active In providing references. 3- Quota sampling Definition Quota sampling is a non probability sampling technique wherein the researcher ensures equal or proportionate representation of subjects, depending on which trait is considered as the basis of the quota . The basis of quota are usually age, gender, education, race, religion, and socioeconomic status. Quota sampling is similar to stratified sampling except nonrandom sampling method is used here. Divide the population into homogenous strata and selecting sample elements from each of these strata.

This is to include subject types that are underrepresented in the convenience sample. over convenient

Quota sampling represent an improvement sampling and tends to decrease potential biases. Advantage Economically cheap. Disadvantages Not possible to estimate errors

Bias is possible, as investigator/ interviewer can select persons known to him. 4- Purposive sampling Definition It is a non probability sampling technique wherein, subjects are chosen to be part of the sample with a specific purpose in mind. Involves handpicking of subjects. Subjects are chosen that the researcher believes are typical or representative , of the accessible population this is based on the assumption that the researcher has enough knowledge about the population. Advantages Simple to draw a sample. Saves resources as it requires less field work. Disadvantages Require considerable knowledge about the population. Conscious biases may occur.