Sampling

Download as pdf or txt
Download as pdf or txt
You are on page 1of 4

Sampling

Population and Sample


Population 1
- the set of all elements of interest in a particular study
- collection of all individuals or items included in the scope of the study
- refers to the totality of objects, individuals, or reactions that can be described as having a
unique combination of qualities, with which we are concerned
- can either be finite or infinite; finite population can be counted with relative ease and the
number obtained is limited whereas infinite population cannot be counted easily because of the
large number involved
Examples of finite population:
1. the population consisting of all bolts produced in a factory on a given day
2. number of students enrolled in Saint Louis University for the second semester AY 2014-2015
3. number of cards in a deck
Examples of infinite population:
1. number of stars in the sky
2. the exact number of people in the Philippines (because people are born and die every now and
then)
3. the population consisting of all possible outcomes (heads, tails) in successive tosses of a coin

Sample
- part or subset of the population from where the data is actually taken
- collection of some elements in a population
- representative of the entire population
- refers to a finite number of objects selected from the population

Parameter
- numerical value used as a summary measure for a population (e.g., the population mean 𝜇, the
population variance 𝜎 2 , and the population standard deviation 𝜎)
- quantitative value or attribute that characterizes the population

Statistic
- numerical value used as a summary measure for a sample (e.g., the sample mean 𝑥̅ , the sample
variance 𝑠2 , and the sample standard deviation 𝑠)
- quantitative value or attribute that characterizes the sample
- used to estimate the corresponding population parameter

In collecting data concerning characteristics of a group of individuals or objects, such as heights and
weights of students in a university or numbers of defective and non-defective bolts produced in a
factory on a given day, it is often impossible or impractical to observe the entire group, especially if it is
large. Instead of examining the entire group, called the population or universe, one examines a small
part of the group called a sample.
Sampling

Sampling
Sampling is the act, process, or technique of selecting suitable sample, or a representative part of a 2
population, to study and fairly generalize the results back to the population of interest.
Advantages of Sampling:
1. Reduced cost; cost entailed in studying only a part of the population is much lower with
investigations involving the whole population.
2. Greater speed; a smaller group under study requires shorter time spent for data collection and
processing.
3. Greater scope; more comprehensive data may be gathered.
4. Better quality of information; a smaller study group allows proper execution of technical
procedures.
Qualities of Statistical Data:
 Accuracy – reflects how close the measurement or the data collected to the true value
 Precision – refers to the repeatability or consistency of the information collected
 Timeliness – time interval between the date of occurrence of the event and the time the
information is collected or disseminated
 Adequate – reflects that the data collected contains the needed information to meet
the requirements or the interest of the collection process
 Relevance – reflects the applicability of the data collected to the needs of the users
 Completeness – refers to comprehensiveness on coverage as well as all items being
asked for in the study
Good Sampling Design:
 Representative – sample to be collected should reflect the characteristics as well as the
variability of the population
 Feasible – sampling procedure should be simple enough to be implemented and can be carried
out and sustained according to plan
 Adequate – the sample size should be sufficiently large to provide reliable generalization
 Economic – sampling design should be efficient enough to produce the most information at a
least cost

Practical guidelines in designing questions for data collection in a statistical study:


1. State the questions clearly.
2. Avoid asking leading questions.
3. Construct questions that will give objective rather than subjective replies.
4. Follow a logical flow of questioning.
5. Ask for essential information only.
6. Ensure that questions are well-understood.
7. Avoid incorporating too many ideas in a question.
8. Construct questions which the respondents can answer confidently.
9. If negative items cannot be avoided, be sure to mark (capitalize, underscore) the negation so as
to guide the respondents.
Sampling

Sample Size
Slovin’s formula: 3
𝑁
𝑛=
1 + 𝑁𝑒 2
where 𝑛 is the sample size, 𝑁 the population size, and 𝑒 the margin of error. Marginal error is the
probability of committing an error. On the other hand, confidence level (100% − 𝑒) is the probability of
getting the correct result.
Example:
A researcher would want to make a survey of the employees from the different departments of a
company. The distributions of the population are as follows:
Department No. of Employees
Administrative 250
Manufacturing 120
Finance 85
Warehousing 20
Research and Development 15
Total 490
Use the Slovin’s formula to identify the sample size of the survey with the following margin of error:
a. 5%
b. 2.5%
c. 1%

Sampling Techniques
Sampling technique is the procedure of gathering sampling units or observations from the population.
 Probability Sampling is a method of sampling that utilizes some form of random selection.
Random selection is performed by selecting a group of subjects (sample) for study from a larger
group (population). Each sample point is chosen entirely by chance.
1. Simple Random Sampling is a method of selecting a sample size 𝑛 from a population 𝑁
such that each member of the population has an equal chance of being selected.
2. Systematic Random Sampling selects every 𝑘 𝑡ℎ element in the population for the
sample, with the starting point determined at random from the first 𝑘 elements.
3. Stratified Random Sampling is a sampling method which involves dividing the
population into non-overlapping homogeneous subgroups and then taking a simple
random sample from each subgroup.
4. Cluster Random Sampling is a sampling method which involves dividing the population
into clusters, usually along geographic boundaries, then randomly taking samples of
clusters and measuring all units of the sample within the sampled clusters.
5. Multi-stage Sampling is a sampling method which uses several stages of phases in
getting the sample from the general population but selections are done by random. This
type of sampling is useful in conducting nationwide surveys or any survey involving a
very large population.
Sampling

 Non-probability Sampling is a sampling technique that does not involve random selection of
samples as it is difficult to determine the probability of a unit to be chosen as sample. 4
1. Accidental or Haphazard Sampling is one of the most common methods of sampling
where samples that are most available and conveniently accessible are chosen.
2. Purposive or Judgment Sampling is a sampling method based on the knowledge of the
population and certain criteria laid down by the researcher.
a. Snowball Sampling is a sampling method wherein the investigator begins by
identifying someone who meets the criteria for inclusion in the study then asks
the respondent to recommend others who also meet the criteria.
b. Heterogeneity or Maximum Variation Sampling is a purposive sampling
technique used to capture a wide range of perspectives relating to the thing
that you are interested in studying; it is a search for variation in perspectives,
ranging from those conditions that are view to be typical through to those that
are more extreme in nature.
c. Expert Sampling involves the assembling of a sample of persons with known or
demonstrable experience and expertise in some area.
d. Quota Sampling is a sampling method in which you select the sample according
to some fixed quota and can either be proportional or non-proportional.
e. Modal Instance Sampling is a sampling method done with the most frequent or
the typical case.
f. Extreme Case Sampling is a type of purposive sampling that is used to focus on
cases that are special or unusual, in the sense that these cases highlight notable
outcomes, failures, or successes.
g. Critical Case Sampling is a type of purposive sampling technique that is
particularly useful in exploratory qualitative research, research with limited
resources, as well as research where a single case (or small number of cases)
can be decisive in explaining the phenomenon of interest.
h. Total Population Sampling is a type of purposive sampling technique where you
choose to examine the entire population that have a particular set of
characteristics (e.g., specific experience, knowledge, skills, exposure to an event,
etc.). In such cases, the entire population is often chosen because the size of the
population that has the particular set of characteristics that you are interested
in is very small. Therefore, if a small number of units (i.e., people,
cases/organizations, etc.) were not included in the sample that is investigated, it
may be felt that a significant piece of the puzzle was missing.
3. Sequential Sampling is a non-probability sampling technique wherein the researcher
picks a single or a group of subjects in a given interval, conducts his study, analyzes the
results then picks another group of subjects if needed and so on. The researcher can
accept the null hypothesis, accept his alternative hypothesis, or select another pool of
subjects and conduct the experiment once again. This entails that the researcher can
obtain limitless number of subjects before finally making a decision whether to accept
the null hypothesis or alternative hypothesis.

You might also like