INTRODUCTION
When research is conducted, the researchers generally interested in drawing some conclusion
about a population of individuals or elements that have some characteristics. A population
consist of all individuals or elements with a particular characteristic that is of interest to the
researcher. However population are typically too large to allow observation on all
individuals, and researchers resort to selecting a sample, hence sampling. Mohsin, (2016,
p.11) defines sampling as the process through which a sample is extracted from a population.
Many sampling techniques exist. These can be divided into probability and nonprobability
techniques.
In probability sampling also known as random sampling, everyone in the sampling
frame has an equal probability of being chosen and hence the resultant sample is said to be
more representative of the population from which it is drawn from. To put it more accurately,
it is not having equal probability but rather the probability of selecting each participant is
known either in advance or once selection is done. Examples include simple random, multi-
stage, cluster, stratified and systematic sampling techniques.
The nonprobability sampling, the focus of my assignment, is also called non-
random sampling. With nonprobability sampling, there is no way of estimating the
probability of an element being included in a sample
There are different types of nonprobability sampling,
Convenience sampling is quick and inexpensive because it involves selecting
individuals who are readily available at the time of the study.
Quota sampling involves selection of a certain percentage of individuals from
specified subgroups of the population when the population is large and its list of members are
unavailable. Example is selecting 10 males and 10 females and 5 from each region of the
country to make the sample size needed.
Purposive sampling, also known as expert sampling, is where the researcher chooses
the participants as per his/her own judgement, keeping in mind the purpose of the study. The
participants are thought to represent the correct attitude than other class of people. Example is
a sample of health workers in studying of the attitude towards national immunisation.
Snowball sampling also known as chain referral sampling or respondent-driven
sampling. It starts with collecting data from a participant of the target population who then
links you to other potential respondents.
As Dorofeev and Grant (2006, p2) argue it out, it is not possible to have a comprehensive
list of the population from which to make our random selection, not possible to contact all the
randomly selected members within the inevitable constraints of time and resources,
unwillingness of those contacted to participate in the survey and this leads to use of non
probability sampling technique.
The relevance of non probability sampling is;
1. When there is lack of access to the study population like when study population is
scattered or when acknowledgement of membership to such a population is
potentially threatening or undesired by participants for example drug users and sex
workers. For example Schwitters et al, used snowball sampling in a study to estimate
prevalence of rape and client-initiated gender-based violence among female sex
workers in Kampala.
2. When the research aims to do a qualitative plot or explanatory study. Example
Fory JH et al used purposive sampling of patients and providers in New York State in
their qualitative study of the barriers of metformin use from the patient and provider
perspective.
3. When randomization is impossible as the target population size is very small. For
example purposive sampling was used by Swales et al, their research were speech-
language pathologists who currently work with Parkinson’s disease where recruited.
4. Used to demonstrate that a particular trait exists in the target population and
when the aim is not to generalisation results to the entire population. This is because
non probability sampling gives a sample that is not representative of the study
population and hence results from study donot necessarily apply to the population.
5. Budget, time and workforce constrains. In simple random method, a probability
sampling technique, there is need to generate a list of all participants in our target
population, assigning each a number. Use of either a random number generator or
random number table to get the required sample. Such is not possible for research
with constraints so a non-probability technique which does not require all that is used
as it is quick and cheap.
6. Used in an initial study in which probability sampling will subsequently be
employed. An example is a pilot study to determine whether the questionnaire works,
whether respondents understand the questions and find them relevant and easy to
answer.
In summary, the objective of the research, the cost in terms of money, resource and time
determines which sampling method to use.
Practical relevance of measure of central tendency in strategic planning.
Manikandan argues that in any research, enormous data is collected and to described it
meaningful, one needs to summarise it. Measuring the central tendency mean, mode and
median, summarises the data into a single value. Mode, median and mean are the methods of
a group of values. Mean is calculated by adding up all of the values and dividing by the
number of values observed. Median is the middle value of an ordered sample of numerical
values. Mode is the value which occurs most often in a group.
Accurate description of the entire data as it summarises all the data into one
value. Instead of looking at each data every time one intends to use the data, this one
value is enough to confer meaning of the data. Knowing normal or average for a set of
data saves time.
Comparing one data set with another data set and also comparing one value of
data with the entire data. For example laboratory test results are numbers not
meaningful by themselves. They derive meaning from comparison to reference lab
values which are obtained central tendency of population data.
Values from central tendency are used for further mathematical manipulation of
data. Mean is used in calculation of Standard deviation and variance which determine
the market volatility and hence the risk an investment poses.
Used in planning, setting acceptable working parameters and showing of trend
or deviation from the norm. From this the manager can investigate the root cause of a
problem. For example using mean to determine future monthly power consumption by
finding the mean of the previous 3 monthly power consumptions.
Use median to set salary scale or plan capacity. Mathis and Jackson (2010,
p.369) illustrate the use median from the salary data of the market to determine salary
for the employees. Manager can decide to set salaries at median so as to be positioned
in the middle of the market such as to balance employee cost pressure and the need to
attract and retain employees. The manager can use above median figure so as to
attract and retain employees with the required capabilities so as to bet competition.
Using mode to identify baseline for example consumer preference for the
different kinds of products hence determine stocking and pricing. Looking at mean,
median and mode, a manager can gauge what to charge customer for an item. When
the pricing is high, goods will be expensive and hence customers will switch to
competitors.
REFERENCES.
1. Mohsin, A. H. (2016) A Manual for Selecting Sampling Techniques in Research,
University of Karachi, Iqra University.
2. Dorofeev, S. and Grant, P. (2006) Statistics for Real-Life Sample Survey a non-
simple-Random Samples and Weighted Data. 1st Edition, Roy Morgan Research,
Melbourne, Australia, Page 2.
3. Schwitters, A., Swaminathan, M., Serwadda, D., Muyonga, M., Schiraishi, R, W.,
Benech, I., Mital, S., Bosa, R., Lubwama, G., Hladik, W. 2015. Prevalence of Rape
and Client-Initiated Gender-Based Violence Among Female Sex Workers: Kampala,
Uganda, 2012 AIDS and Behavior 19(Suppl 1):68-76.
4. Fory JH., Keatings, S., Guelce, D., Mushlin, Al. 2019. Overcoming barriers to use of
metformin: patient and provider perspective Patient Preference and Adherence
13:1433-41.
5. Swales, M., Theodoros, D, Hill, A J., Russell, T. 2018. Communication service
provision and access for people with Parkinson’s disease in Australia: A national
survey of speech-language pathologist, International Journal Speech Language
Pathology 29:1-12.
6. Manikandan S, 2011. Measure of central tendency: Median and mode Journal of
Pharmacology and Pharmacotherapeutics 2(3):214-215.
7. Robert L. Mathis & John H. Jackson, 2010 Human Resource Management 13th
Edition, South-Western Cengage Learning, USA.