CHAPTER 14 NOTES
1. Sampling
Sampling is a statistical technique which is used in almost every field in order to collect information and
on the basis of this information inferences about the characteristics of a population are made.
2. Parameters
The values of the population characteristics are summarized by certain numerical descriptive measures,
called parameters.
3. Statistic
The observations composing a sample are used to calculate a corresponding numerical descriptive
measure, called a statistic.
4. Statistical Population
A statistical population (or universe) is defined as the aggregate or totality of all individual members or
objects, whether: animate or inanimate, concrete or abstract, of some characteristics of interest. The
individual members of the population are called sampling units or simply units.
5. Sample and Sampling
A set of n sampling units selected from a given population is called a sample of size n and the process of
selecting a sample, is known as sampling.
The numerical values assigned to units of interest are related as values of a random variable X, and the
distribution of X is called the population distribution.
Population can be finite or infinite. For example, all the students of a college.
6. Existent Population
A population of concrete units such as trees, households, students, etc. is called an existent population
7. Hypothetical Population
A hypothetical population consists of all conceivable ways in which an event can occur, e.g. all. possible
throws of a die.
8. Sample and Targeted Population
a sampled population is that from which a sample is chosen, whereas a population about which we wish
to draw inferences, is called a target population.
For examples: All colleges of the province are target population while five college scattered throughout
the province is sample population.
9. Purpose of sampling
The two basic purposes of sampling are
1. to provide sufficient information about the characteristics of a population without examining
every unit of the population.
2. to find the reliability of the estimates derived from the sample.
10. Advantages of Sampling
1. Sampling saves money as it is much cheaper to collect the desired information from a small
sample than from the whole population.
2. Sampling saves a lot of time and energy as the needed data are collected and processed much
faster than census information.
3. Sampling provides information that is almost as accurate as that obtained from a complete
census;
4. Sampling makes it possible to obtain more detailed information from each unit of the sample as
collecting data from a few units of the population (i.e. sample) can be more complete and
thorough.
5. Sampling is essential to obtaining the data when the measurement process physically damages
or destroys the sampling unit under investigation.
6. Sampling may be the only means available for obtaining the needed information when the
population appears to be infinite or is inaccessible such as the population of mountainous or
thickly forested areas.
7. The most important advantage of sampling is that it provides a valid measure of -reliability for
the sample estimates and this is one of the two basic purposes of sampling.
11. Probability Sampling.
When each unit in a population has a known non- zero (not necessarily equal) probability of its being
included in the sample, the sampling is said to be probability sampling. A probability sampling is also
called random sampling.
Types of Probability Sampling
1. Simple random sampling
2. Stratified random sampling
3. Systematic sampling
4. Cluster sampling
Advantage: The advantage of probability sampling is that it provides a valid estimate of sampling error.
Usage: Probability sampling is widely used in various areas such as industry, agriculture, business, etc.
12. Non-Probability Sampling
A non-probability sampling, also called non-random sampling, is a process in which the personal
judgement determines which units of the population are selected for a sample.
Types of Non-probability sampling
1. Purposive sampling
2. Quota sampling
Disadvantage: The disadvantage of non-probability sampling is that the reliability of the sample results
cannot be determined in terms of probability.
13. Sampling with and Without Replacement
Sampling is said to be with replacement when from a finite population a sampling unit is drawn,
observed and then returned to the population before another unit is drawn. The population in this case
remains the same.
If, on the other hand, a sampling unit is chosen and not returned to the population after it has been
observed, the sampling is said to be without replacement. Here the sampling units cannot be selected
again for that sample as the units drawn are not replaced.
14. Sampling and Non-Sampling Errors
The difference between the value of sample statistic and the true value of the corresponding population
parameter. Such a difference is called sampling error for that sample.
Sampling Error = x̄ - ū
Errors which occur at the stages of gathering and processing of data, 1 less of whether a sample or a
complete census is taken. These errors are called non- sampling errors. Non sampling errors include all
kinds of human errors.
These errors can be avoided through the proper selection of questionnaires, following up the non-
response, proper training of the investigators, correct manipulation of the collected information, etc.
15. Types of Probability Sampling
15.1 Simple Random Sampling Used for homogenous Population
A sample is defined to be a simple random sample (SRS) if it is selected in such a manner that
1. each unit in the population has an equal probability of being included in the sample
2. each possible sample of the same size has an equal probability of being the sample selected.
Selection method of simple random sampling:
1. Gold fish Bowl method
2. Using a Random number table
3. Using a computer
15.2 Stratified Random Sample. For Heterogenous Population
A sample of size n is defined to be a stratified random sample if it is selected from a population which
has been divided into a number of non-overlapping groups or sub populations, called strata, such that
part of the sample is drawn at random from each stratum.
The advantages of stratified random
Low Cost
Greater accuracy
Better coverage
Usage
Stratified random sampling is used when
1. The variations among strata are greater than the variations within strata.
2. Information about some parts of the population is desired.
15.3 Systematic Random Sample
A sample of size n is defined to be a systematic random sample if it is obtained by choosing one unit at
random from the first k units and thereafter selecting every kth unit after the N units in the population
have been serially numbered from 1 to N or arranged in a systematic fashion.
For example: ¡=7 and k = 20, then a systematic sample consisting of every 20th unit, will be composed
of the units numbered 7, 27, 47, 67 and so on. Thus, in systematic sampling, sampling units are selected
at uniform interval after a random start.
Advantages
1. Saves much time and effort.
2. It is economical.
3. A systematic random sample is more representative of the population
4. Sample is more evenly distributed.
15.4 Cluster Sample:
A random sample is said to be a cluster sample if it consists of first selecting at random groups of
individual units, called clusters (treated as sampling units) into which a population can be divider and
then including in the sample either all the units from each of the chosen clusters, or selecting a random
sample of the units which the cluster comprises.
The procedure is called one-stage cluster sampling when all the units which each of the sampled clusters
comprises, are included. If each of the sampled clusters is subsampled, then the sampling plan is called
two-stage cluster sampling or subsampling.
Advantages
The advantage of cluster sampling is savings in cost and time, i.e. The cost of sample selection and travel
expenses of interviewers are considerably low.
Usage:
Cluster sampling is used when
1. The sampling frames of adequate coverage are not available,
2. The variations among clusters are smaller than the variations within clusters.
3. It is to be noted that cluster sampling is mostly used in statistical quality control.
15.5 Multistage Sample
A sample is called a multistage sample when it is selected in stages, the sampling units at each stage
being subsampled from the larger units selected at the previous stage.
15.6 Multi-phase Sample
A sample is said to be a two-phase sample when certain items of information are collected from all the
units in sample and other items of usually more detailed information are collected from a subsample of
the units composing the original sample. It is important to note that in multi-phase sampling, the same
units are used at each phase, whereas in multi-stage sampling, the units are different at different stages
of sampling.
Advantages:
1. It is proved to be cheaper.
2. Less burden on respondents.
15.7 Sequential Sampling
This is another method of sampling where the sample size is not fixed in advance but sampling units are
drawn on by one or in lots, and the decision is based on a definite rule relating to the sampling units
themselves. That is, we draw one unit at a time and after each drawing, we make a decision whether to
accept the lot or group, whether to reject it or whether to continue sampling.
16. Types of Non-Probability Samples
16.1 Purposive Sample
A purposive sample is a non-random sample in which the selection of the sampling units is based on a
person's expertise about the population. A purposive sample is liable to bias to be introduced by the
deliberate subjective choice of the person who selects the sample.
it is to be noted that the information gathered from such a sample cannot be made a basis for statistical
inference.
Example:
For instance, when taking a sample of melons from truck-load, the sampler inspects the whole load and
then selects according to his expert subjective judgement.
16.2 Quota Sample
Quota sampling is the sampling in which the information is collected purposively from the segments of a
population (the quotas), e.g., the quotas of men and women; urban and rural; upper, middle- and lower-
income groups; etc. These factors are termed quota controls.
Quota sampling may be considered as stratified sampling in which the selection of units within strata is
non-random.
Advantages:
The advantages of quota sampling are that it is cheaper, it is easy administratively and it is a very quick
form of investigation. Quota sampling is widely used in public opinion polls and market research surveys.
Sampling Distribution
A sampling distribution is defined as a probability distribution of the values of a statistic such as a mean,
a standard deviation, a proportion, etc. Computed from all possible samples of the same size, which
might be selected with or without replacement from a population.
Types of Sampling distribution:
binomial, the normal, the t-distribution, the chi-square distribution, and the F distribution.
Sample Distribution:
The sample is a subset of the population, and is the set of values you actually use in your estimation.
Let’s think 1000 individual you have selected for your study to know about average height of the
residents of India. This sample has some quantity computed from values e.g. mean (x ), Standard
deviation (s) , sample proportion etc. This is called sample distribution.
