## All Answers (40)

- simple random sampling is just one way of random sampling. There are many other way, for instance stratified random sampling, cluster random sampling, systematic random sampling et cetera. see the book of Cochran, 1977, Sampling Techniques
- Simple random sampling is one case of the random sampling techniques
- There are many forms of "random sampling", one of which is "simple random sampling". "Random sampling" can be conducted by - for example - dividing the larger population in distinct strata, then sampling randomly within each strata -- yielding a so-called "stratified random sample" or "stratified sample". Simple random sampling usually refers to selecting a sample from the population in such a way that every sample of size n has equal opportunity of selection, but does not first - for example - break the population into strata. There are of course other approaches such as "sampling with probability proportional to size", "cluster sampling", etc. I won't claim that sampling is my strength, but there are some decent highly accessible resources out there with one being the classic book "Elementary Survey Sampling", now in its seventh edition by: Scheaffer, Mendenhall, Ott and Gerow published by Brooks/Cole - Cengage Publishing (2012).
- A random sample uses randomization to pick your sample. That can be done in a number of ways. A simple random sample is basically like selecting names from a hat. Every subject in the population has an equally likely chance of being in the sample, and every possible sample has an equally likely chance of being selected. Other possible ways to take a random sample are systematic sampling (where you randomly select a starting point, and then pick every nth subject). In brief, simple random samples are random samples, but random samples are not necessarily simple random samples. Thanks
- It is a debatable question, what is random sampling and what is Simple random sampling. Basically, in all sampling we use random method for selection until. So all sampling are random except purposive sampling. The random sample can be simple in nature, selection process, planning etc. or difficult. The simple form of random sampling is called simple random sampling. this includes SRS WR and WOR. The other methods such as Stratified, two stage systematic etc are not simple in nature. So they are not SRS.
- A simple random sampling is one of the type of random sampling. Simple random samples are also random samples but the random samples are not simple random samples. Also, it will depend on the type of population and the objective of your study.
- See books on survey sampling such as the one by Sharon Lohr or the classic by Cochran.
- Random sample: every element of the population has a (nonzero) probability of being drawn.

Simple random sample (SRS): every element of the population has the same (nonzero) probability of being drawn. SRS is thus a special case of a random sample.

The inverse of the selection probability can be used to weight the sampled data. The weighting is easier with SRS (than with other types of random samples) because all cases have the same weight. - Simple random sampling is only a "kind" of random sampling. Random Sampling have other kinds of sapling.
- I would have thought random sampling is the umbrella terms for ‘probability sampling’. A probability sample has the essential characteristic that every unit/person in a population has a known, non-zero probability of being included in the sample. Simple random sampling is the most straightforward method of probability sampling. Other types of probability sampling include systematic, stratified, cluster and multi-stage (multi-stage might combine more than one method of probability sampling in a step by step sampling process).
- All the answers are easy to understand, I don't know if you need examples or something, but here I can share with you a link: http://www.csulb.edu/~msaintg/ppa696/696sampl.htm, just in case you need all the background and I add an attachment... I hope all of us can give you a clue
- Rick Edgeman has given a nice explanation. Simple random sampling is one the random sampling techniques, namely, simple random sample, systematic random sample, stratified random sample, cluster sampling, etc etc..Simple sample is useful only for homogeneous population...
- Another very synthetic reference for classical sampling methods from finite populations is :

Jill M. Montaquila. "Sampling from Finite Populations" (version 2). StatProb: The Encyclopedia Sponsored by Statistics and Probability Societies.

It is freely available at http://statprob.com/encyclopedia/SamplingFromFinitePopulations.html - Random Sample: Each member of the entire population has an equal chance of being selected.

Simple Random Sample: You can select groups of size n from the entire population, and every possible group has the same chance of being selected. - Simple random sampling is like lottery system such that every subject has equal chance of participation and this is one method of random sampling
- A simple random sampling is an unbiased surveying technique. as difference between random sampling and simple random sampling is that simple random sampling is a type of random sampling.

Each individual is chosen randomly and entirely by chance, such that each individual has the same probability of being chosen at any stage during the sampling process, and each subset of k individuals has the same probability of being chosen for the sample as any other subset of k individuals in simple random sampling. - Simple random sampling is a form of sampling design in which n distinct units are selected from the N units in the population in such a way that every possible combination of n units is equally likely to be the sample selected. With this type of sampling design the probability that the tth population unit is included in the sample is i ¼ n=N, so that the inclusion probability is the same for each unit.

Designs other than this one may also give each unit equal probability of being included, but only here does each possible sample of n units have the same probability. - A simple random sample as already mentioned is a type of random sampling and a random sample typical means one in which either a set of n independent and identically distributed random variables, or a sample of n individuals selected from a population in such a way that each sample of the same size is equally likely.
- Schutt is correct. Thumbs UP!!
- Random sampling is a generally used terminology that applies to all sampling techniques whereby people are involved in the study haphazardly or by chance. In random sampling, every individual in the population must have equal chance of being sampled so that the equality principle shall not be violated, and the selection of an individual shall not be affected by the selection of the previous one so that the independence principle is respected.

Under random sampling we can name simple random sampling, convenience sampling, incidental sampling, systematic sampling, and accidental sampling. But only two of them, that is simple random sampling and systematic sampling are unbiased. The application of simple random sampling and systematic sampling is generally limited to context where all subjects in the population are identified. That is the reason why in most countries where the database is poor or not updated, it is at time difficult to apply such sampling techniques and we then resort to close substitute such as convenience sampling. Below is explained the various random sampling techniques.

Simple random sampling

Simple random samples are selected using chance random numbers. Practically, numbers are distributed to the subjects of a population that are all identified in a data base. These numbered cards will be collected and thoroughly mixed in a bowl, and the quantity of needed cards will be selected. The subjects whose numbers have been picked from the bowl will be part of the sample. Instead of mixing, random number can be generated with a computer, table of random numbers or slate lottery. Statistical software can assist us in selecting the desired number of cases at random from a given data base. In SPSS, you can access the command ‘New query’ through the ‘File’ main menu and the ‘Open Database’ sub-menu. The inconvenience of simple random sampling lies on the fact that if the population is large and an initial listing (data base) not done, a lot of time may be wasted doing that. To solve this problem, convenient sampling is used as the closest alternative.

Systematic sampling

Systematic sampling is obtained by selecting any Kth number of the population. Let us consider a situation where we have a population of 4000 students in the Highlands University of Bangangte and FASTDAM needs only 100 subjects for malaria test. K = 4000/100 = 40. Every 40th student will be selected. The first subject (which number is between 1 and 100) will be selected at random. If subject 15 is the first subject to be selected, then subjects 55, 95, 135, 175…..will be selected subsequently. As for simple random sampling, the students shall be numbered or if appropriate, their matriculation numbers can be used. This technique of sampling is also conducive in selecting households where houses are numbered and can apply to many similar situations where targeted subjects or individuals are numbered. Here also we absolutely need a data base.

Simple random sampling and systematic sampling are typical examples of probabilistic sampling because every individual is given equal chance of being selected. But the sample size shall be properly estimated for the criteria of probabilistic sampling to really stand. The opposite of probabilistic sampling is non-probabilistic sampling, and in this line we can name as typical examples, convenience, incidental, snowball and accidental samplings.

Let us consider a situation whereby a researcher would like to sample people’s opinions in Fako division. If every member of the population of Fako is listed, and the researcher proceeds by simple random sampling, he would have to struggle to meet those sampled even if this may entail time, financial and effort constraints. But in convenience or incidental sampling, the researcher may avoid this potential burden and deal only with readily available participants, therefore reducing the chance of some people to be involved in the study. In convenience sampling, the sampling bias is somehow reduced if the sample is representative in characteristic and size. This bias is corrected by increasing the DEFF to 2 or 3, which improves the variability.

Lack of reliable and updated population data base, financial and time constraints often push researcher to shift from simple random sampling to convenience sampling.

Convenience sampling

Convenient sampling is a form of random sampling whereby participants are not known, are not initially identified and are met and involved at random when they are available in the course of the study till the initial targeted sample size is met. To make a clear cut difference between random sampling whereby the subjects were identified, numbered or listed drawn at random and a situation whereby they were not identified or numbered, the former is often termed simple random sampling whilst the latter is termed convenience sampling.

The concept of convenience sampling is advised to be used in order to make a clear cut difference with simple random sampling.

Incidental sampling

When an initial number of individuals to meet is not set and where the sample size will depend on how available the targeted participants will be as well as on the chance of meeting them during the period covered by the study, we are then faced with incidental sampling. Here the researcher has no set objective in relation to the number of people he may sample and the sample size will depend essentially on opportunistic circumstances.

Convenient sampling is different from incidental sampling in the sense that in convenient sampling, the number of people to sample for the study is initially set.

Accidental sampling

This sampling technique applies if the identity of the subject of interest is not known in advance and the chance of meeting them assumed slim; e.g., looking for people who are aged 100 years and above in an area. Such key informant is rare and can be met only accidentally.

Accidental sampling is different from incidental sampling in the sense that in incidental sampling, the participants are not rare and the chance of meeting them not all that slim. The similarity is that in both cases, the number of people to meet is not initially set and will be determined by research’s circumstances. - Schutt has simplest and accurate explanation. I wrote a textbook more than twenty years ago on this topic after I was a student of Deming in graduate school
- Yes Jeff, the explanation of Schutt might be simplest and accurate but operationally it may not really help a lot of those who may like to apply to field work. On this forum, what we tend to forget is that we are faced with people with different intellectual levels and needs and our explanation shall go beyond mere intellectual exhibitionism to serve this diversity.
- Please note that selecting sampling units by convenience does not result in a random or simple random sample.
- Random sampling is the general term used for probability sampling in which every unit in a population has some chances of selection in a sample. Thus if these chances of every unit to be selected in a sample are equal, simple random sampling is being used to deal with the issue, and if these chances of every unit to be selected in a sample are not equal, stratified or cluster are rather used.

Obviously, the sample is drawn from some population and if population is homogenous then no matter what unit is selected, in such case simple random sampling implied. - Simple random sampling is defined as a result of selection process where each sampling unit has the same (or equal) chance of selection.
- I've built a Bootstrapping program for free download that gives these options...easy to use ...

http://correctcharts.com/returnfinder/etfs - As has been mentioned earlier by some other contributors, in random sampling in general the probability of selection of an element is not necessarily the same as the probability of selection of another element. In simple random sampling, every element of the population concerned will have an equal probability of being selected.
- Nan is wrong!! There is nothing haphazard about random sampling. Read a book by Deming on Sampling.
- There is no distinction between random sampling and simple random sampling. There is a distinction between simple random sampling and systematic or stratified random sampling. Systematic means that there is a reason for selecting a subset of the population because of a characteristic of that subset. The posing of the sampling makes that distinction. Within the subset, simple random is expected. More important, the sample must be representative of the posed argument that requires sampling. The imposition of randomness must not compromise representation.

Random means selected by chance. The reason for random sampling is because one is sampling a stochastic process. Note that any definition of random, chance, or stochastic is circular and any of the three can be used to define the other two. The word random does not confer any blessing on sampling. The words simple, stratified and systematic do not confer any blessing on sampling. They are all a part of statistical language and indicate effort made in the sampling process. The most important effort is ensuring representative sampling for the posed argument. One should explain the process of the representative sampling without relying on stock phrases.

Random, chance, and stochastic all mean unknown. The previous statement, "Random means selected by chance," is not only circular, but it conveys that chance performed selection. Neither chance, stochastic, nor random are active participants in the process. Representative sampling is an active process and language and quibbles about language should not detract from that process. - Many have pointed out that in simple random sampling every unit of the population has an equal chance of being selected. Equal probability systematic sampling also has this property. What characterizes simple random sampling is that every subset of the population has the same probability of being in the sample as every other subset of the same size.
- Simple Random Sampling is a particular case of Random Sampling. According to the theory on random sampling it depends upon the variability of your variable. You may have, to use Estratified Random Sampling or Cluster Samplig depending bassically on the variability of your poulation. The SRS, can be used if the population is homogeneus, and it could be sistematic or you may use some criteria, for numbering the subjects and taking your observations by using a random number table or any other convenient strategy, that asures you, that every experimental unit have the same chance of being selected.
- Good answer Rafael. I believe this discussion should end.
- Sample is a small group, which is being selected either by random sampling technique or non random sampling technique from a target population.. Random sampling is a process for selecting a sample from the population by giving equal chance to each unit of the population. Random sampling is classified as simple and restricted random sample according to the size and homogeneity of target population. If target population size is small and homogeneous, we are using simple random sample method such as lottery and random table methods by strictly adopting probability. If our target population is large and heterogeneous we are using restricted random sampling such as Stratified, systematic, multistage, multi phase etc. All are random sampling methods. Hence there will not be any question of difference between RS & SRS. For example, 1000 years ago, the Chola King of Uthiramerur, Tamil Nadu, India had conducted the election by lottery method called "Kuda volai" system for unbiased selection of people representatives. SRS is a random sampling method as told by Atif Akbar and others.
- Another sampling scheme to consider is whether or not it is sampling with replacement. With replacement, you draw a random sample from the population (e.g. one person) and then replace them back into the population, then draw another random sample. Thus it is possible that someone could be selected twice.
- Simple random sampling is a draw without return and is a type of random sampling. SRS and systematic sampling are the only sampling techniques free from bias but the constrain is that these two sampling techniques demand the existence of a good and reliable data base that provide sufficient information that can help to meet the sampled participants. Generally when the database is not available or to reduce time and financial constrains related to SRS, the closest alternative notably convenience sampling is used.
- From your different anwers I can only conclude that random sampling is not a simple task (I learned this from Nana's explanations). The fact that some particular sampling technique is called "Simple" Random Sample only contributes to increase my confusion. I would appreciate if someone may explain what are the requirements to guarantee that a N sample size is representative of the population of interest, according to the "random variable" we intend to measure. Thanks, emilio

## Popular Answers

Johannes Schult· Universität des SaarlandesSimple random sample (SRS): every element of the population has the same (nonzero) probability of being drawn. SRS is thus a special case of a random sample.

The inverse of the selection probability can be used to weight the sampled data. The weighting is easier with SRS (than with other types of random samples) because all cases have the same weight.

Rick Edgeman· Aarhus University