This open-access article is distributed under

Afropolitan Journals Creative Commons Attribution 4.0 license

ISSN: 3027-2882 www.afropolitanjournals.com

Assessment of Measures of Central Tendency and Dispersion

Using Likert-Type Scale
Yaska, Mutah; and Nuhu, Bata Malgwi
Department of Mathematics and Statistics, Federal Polytechnic, Mubi, Adamawa State, Nigeria.

Corresponding author: batamalgwi2006@gmail.com

DOI: https://doi.org/10.62154/ajastr.2024.016.010379

Abstract
This research aims to analyzing measures of central tendency (mean, median, and mode), and
measures of dispersion (variance and standard deviation) and to graphically present the
simulated data using Likert scale measurement. Mean (μ), Median (Md), Mode (Mod), Variance
(σ2 ), and Standard deviation (σ) have been calculated on simulated data using 5 and 4 points
Likert scales with four different statements. Data analysis is key in any development especially
when there is need to understanding people's opinions on a particular issue that has attracted
the attention of a specific population. Likert scale of measurement is one of the methods that
use statement problems in collecting statistical data in which the respondent agrees with the
opinion or disagrees. Considering the 5-point Likert scale, the measure of dispersion in which
statement two had the highest standard deviation of 1.53 and the mean value of 2.35 being the
least of the mean values implies the significant spread of the data across opinions. Statement
one of the 4-points Likert scale has two modes (bimodal) where the opinions “Strongly Agree”
and “Agree” have ties of 20 responses each. This implies that interpretation of such data may be
difficult, because the data can be roughly split into two different groups, and can be useful for
further research to find a mode to draw conclusions. The best form of Likert scale can be
recommended for 5-point Likert scale so as to give room for undecided opinion. Other measures
of central tendency and dispersion can be useful in interpretation but the recommended
statistical tool is standard deviation as it shows the spread of the opinions about the mean.
Keywords: Data, Likert, Analysis, Measurement, Opinion.

Introduction
Likert's scale is a measurement method to assess an individual's opinions about specific
issues. It might be either bipolar reflecting two opposite states of the responses or unipolar
reflecting a regular graduation in the degree or status of the problem being measured. A lot
of descriptive studies in educational and psychological research collect data measured on
Likert scales. However, there are arguments among researchers about which methods are
appropriate for descriptive analysis and interpretation of data from Likert scales. The paper
describes the nature of Likert scales and illustrates ways of descriptively analyzing and
interpreting data collected using Likert scales, also presenting types of bias in Likert scales,
and differentiating between Likert scale and Likert-type items (Alkharusi, 2022).

33 Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research
 AJASTR

According to (Tanujaya, Prahmana and Mumu, 2022). The Likert scale is one of the essential
rating scales used as a measurement tool in social sciences research, especially in the
qualitative approach. Unfortunately, this scale has a great deal of controversy surrounding
how data is obtained from Likert questionnaires and the appropriate statistical analysis of
these data. A systematic review was performed to address this issue. Research publications
from various recognized national and international articles served as research objects. The
research provides a comprehensive study of the two perspectives of the rating scales based
on measurement experts, statisticians, education researchers, and other practitioners. The
experts' opinions, analyses, suggestions, and solutions are obtained from journal articles,
proceedings, theses, and books. After reading this article, the reader should be able to know
that the accurate Likert scale produces data intervals for social sciences research. However,
some requirements must be considered, specifically the composite score, midpoint, and the
number of points. If these conditions are implemented, statistical methods, parametric and
nonparametric, can be used to analyze the data depending on the research purpose.
Likert scale due to its simple application and understanding among respondent and the
popularity among researchers, the old Likert scale have been expanded into many
variations of Likert-type scales.
It is commonly used as survey instruments for design of experiments such as: measuring
employee performance in the workplace (Purdey, 2013), communications research (Ryan,
1980), marketing research (Garland, 1991), mathematical attitudes of elementary students
(Adelson, & McCoach, 2010), political opinion research (Raaijmakers, van Hoof, ‘t Hart,
Verbogt, & Vollebergh, 2000), and psychometric research (Kulas and Stachowski, 2013). Its
popularity, however, does not necessarily equate to its validity as a data collection method
(Johns, 2005). Debates over validity arise from the variations in Likert-type scales in the
context of these applications.
The Likert scale is applied as one of the most fundamental and frequently used
psychometric tools in educational and social sciences research. Simultaneously, it is also
subjected to a lot of debates and controversies regarding the analysis and inclusion of
points on the scale. With this context, through reviewing the available literature and then
clubbing the received information with coherent scientific thinking, this paper attempts to
gradually build a construct around the Likert scale. This analytical review begins with the
necessity of psychometric tools like the Likert scale and its variants and focuses on some
convoluted issues like validity, reliability, and analysis of the scale (Joshi Joshi, Kale,
Chandel and Pal, 2015).
Likert scales are useful in social science and attitude research projects. The General Self-
Efficacy Exam is a test used to determine whether factors in educational settings affect
participant’s learning self-efficacy. The original instrument had 10 efficacy items and used
a 4-point Likert scale. The Cronbach’s alphas for the original test ranged from 0.76 to 0.90.
A 5-item Likert scale was created from this instrument by first adding a “3 =
neutral/undecided” option and also by adding five negatively-worded items to the
instrument. The instrument was piloted with 20 participants. The Cronbach’s alpha for this

Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research 34
www.afropolitanjournals.com
Afropolitan Journals

pilot study was 0.87. The instrument was subsequently used in a large research study, and
the Cronbach’s alpha was found to be 0.88. This yielded an instrument that showed strong
internal consistency (James, 2011).
Likert’s scale is a measurement method developed by Rensis Likert in 1932 to assess
individuals’ attitudes toward any object (Alkharusi, 2022). Validity of Likert scale is driven
by the applicability of the topic concerned; in context of respondents’ understanding and
judged by creator of the response item (Joshi et al, 2015).
Likert scale’s type and Cronbach’s Alpha analysis in determining the reliability and inter-
item consistency of questions regarding the assessment of passengers’ satisfaction and
service quality of Murtala Muhammed Airport 2. The essence of adopting Cronbach’s Alpha
coefficient for checking the reliability and internal consistency of Likert-type scales cannot
be overemphasized as it does not provide reliable estimates for single items or individual
items, but for summated scales or subscales so as to have a known reliability of the items.
Likert scale’s type is suitable with studies in social and behavioural sciences that have to do
with perceptions, attitudes, emotions, opinions, personalities, and descriptions of people’s
environment. It was revealed from the survey of 114 respondents (air passengers) that the
reliability test for statements of thirty-nine airport services blended into five service quality
attributes for service quality and passengers’ satisfaction was 0.893, and 0.861 respectively.
The two Alpha values indicate high reliability of questionnaire instrument and internal
consistencies of the five-point Likert-type scales. The research recommended that for every
perception study particularly in airport study, the reliability and consistency of the
questionnaire instrument enhance the reliability of results (Adeniran, 2019).
A Likert survey question is a specific type of question that collects rank ordered responses
to assess levels of satisfaction, quality, importance, agreement, disagreement, or
frequency. Often, we are interested in concepts that cannot be easily captured in a
dichotomous variable (yes/no) or in a strictly quantitative way. Instead, we expect there is a
range of possible levels of our concept of interest (i.e., self-confidence, satisfaction,
agreement, sense of belonging), the questions often use a declarative statement followed
by a rating scale (Harpe, 2015).
According to Iwona (2016), the variables used in statistical research can be measured on
different scales. According to Stevens the most common division of measurement scales
distinguish four main types: nominal, ordinal, interval and ratio. The chosen scale of
measurement implies further the possibility of applying certain statistical methods. For
socio-economic research it is frequent that among independent variables appear variables
of a qualitative nature. The study presents the idea of the application of the Likert and
Osgood scales for the evaluation and quantification of qualitative variables in the real estate
valuation process. Taking into account the fact that the property features used in the
process of estimating its value are very often measured on weak scales, this research
attempted to apply the aforementioned scales to measure the qualitative features of real
estate property. Additionally, all the qualitative data can be expressed only on nominal or
ordinal scales. This means that they cannot be uncritically treated as metrical variables and

35 Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research
www.afropolitanjournals.com
 AJASTR

their measurement scale implies the possible application of mathematical operations and
statistical instruments. On the other hand, by analysing the type and the character of the
qualitative features of the property, we can observe a substantial connection of such
features with the assessment of their level of intensity expressed as a semantic interval or
the acceptance level of a given phenomenon. This paper attempts to show how to apply the
scales developed to measure attitudes in order to quantify the qualitative features of real
estate property in the valuation process and shows the interval character of the data
measured by the Osgood scale through comparison among three correlations specific for
the mentioned type of scale.
Likert (1932), Likert scales involve the presentation of a set of items related to a certain
issue. Each item assesses a unique aspect of the overall issue. An individual is asked to rate
his or her feelings, perceptions, opinions, or attitudes in terms of agreement or satisfaction
or frequency using a response set consisting of equally spaced numbers accompanied by
approximately equally spaced.
Likert data produces data intervals so that statistical operations can be carried out, such as
sums, means, median, and mode under measures of central tendency and variance and
standard deviations under measures of dispersion. With Likert scale data the mean cannot
be used as a measure of central tendency as it has no meaning in some data analysis while
others use the mean to judge the rate of response, for example what average is the strongly
agree or disagree? The result makes no sense in the interpretation of the result. The most
appropriate measure is the mode of the most frequent responses or the median. The best
way to display the distribution of responses is to use a bar chart or pie chart.
Data analysis is one of the statistical methods of solving problems in any development such
as education, research, business analyses, information and communication, political
science, public administration, sciences, engineering, and above all understanding people's
opinions on particular issues that have attracted the attention of a particular population.
Various methods of data collection have been developed and applied in statistics which
among others are questionnaires, interviews, published documents, pilot surveys, census,
and many other methods. This method developed questions that are open-ended, closed-
ended, or subjective. Likert scale of measurement is one of the methods that use statement
problems in which the respondent agreed to the opinion or disagreed, scale is given to each
opinion for 4 Points Likert scale such as strongly agreed=1, agreed=2, strongly disagreed=3
and disagreed=4, likewise 3 points, 5 points or more points on the Likert scale depending
on the number of opinions This research is to analyze the measures of central tendency and
measures of dispersion of Likert scale data.

Statement of the Problem

Data analysis is key in any research development especially when there is need to
understanding people's opinions on a particular issue that has attracted the attention of a
specific population. Likert scale of measurement is one of the methods that use statement
problems in collecting statistical data in which the respondent agrees with the opinion or

Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research 36
www.afropolitanjournals.com
Afropolitan Journals

disagree. Researchers used Likert scale question as method of data collection, in this
research, the paper will explore likert scale as method or tool for analysis not as material for
data collection.

Aims and Objectives of the Study

This research aims at analyzing measures of central tendency (Mean, Median and Mode)
and dispersion (Variance and Standard deviation) of Likert scale data. The objectives is to
simulate data and apply it on five and four Likert Scale statement to determine the mean,
median, mode, variance and standard deviation. The outcome will be applied on which
measurement is best fit for interpreting the Likert scale data.

Methodology
In this section of the research the data source, size of the sample, statistical tools, graphical
presentation, findings, results and recommendations will be explained in details.

Sources of Data and Sample Size

Simulation studies of data was used for the testing of the models or equations, data was
simulated at various Likert scale of measurement which include three, four and five
opinions of the Likert scale and the statistical tools involves are mean, median, mode,
variance and standard deviation. The sample sizes involved in this study are 50, 100, 200
and 300 at various likert scale of measurement which include 4 and 5.

Likert Scale
Consider the table below which indicates a simple Likert scale of the method of data
collection.

Table 1: Attitude study of 5 points Likert Scale

Statement: Statistics as a course should be compulsory in all fields of study
Opinion: Strongly Agreed Agreed Undecided Disagreed Strongly
disagreed
Likert scale: (1) (2) (3) (4) (5)

The table 1 indicates a common form of statement problem regarding the interest of a
population in which each citizen has different perspectives regarding collection of loan and
its uses. An individual who strongly believes that the loan will be used judiciously will mark
“strongly agreed”, some one believes the may be used for a particular sector may agree for
the collection and will mark “Agreed” while someone who did not see reason for the
collection of the loan will go for “Undecided” and an individual who has the mindset that
the loan will not be used for the development of the country will mark “disagreed” option
and finally a citizen will strongly disagreed if such viewed the loan as method of corruption.

37 Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research
www.afropolitanjournals.com
 AJASTR

Table 2: Perspectives study of 5 points Likert Scale

Statement: Statistical analysis is widely applied in every field of research and survey
studies
Opinion: Strongly Agreed Agreed Undecided Disagreed Strongly
disagreed
Likert scale: (5) (4) (3) (2) (1)

The table 2 implies the reversing order of table 1 whichever is adopted in the study will yield
the same result.

Table 3: Likelihood Statement of 4-point Likert scale

Statement: Statistical analysis if properly applied will yield result in a survey.
Opinion: Definitely Won’t Probably Won’t Probably Will Definitely Will

Likert scale: (4) (3) (2) (1)

Table 3 is a likelihood statement and has 4-points Likert scale, the respondent either agreed
that statistics if properly applied will yield a result or not but still based on the likelihood
application of statistics in a survey.

Table 4: Agreement Statement of 4-point Likert scale

Statement: Statistical result or values can best be interpreted by a Statistician.
Opinion: Strongly agree agree Disagree Strongly disagree

Likert scale: (0) (1) (2) (3)

The arrangement in table 4 is an agreement statement which has 4 point Likert scale that
starts with zero, such likert scale can also be applied in any form of survey, but has limitation
and effect on analysis of the measures of central tendency and dispersion.

Table 5: Quality Statement of 3-points Likert scale

Statement: What is your opinion on statistical softwares?
Opinion: Good Fair Poor

Likert scale: (3) (2) (1)

Table 5 is a good example of determining the quality of a product, policies, bills or act like
Performance of statistical software, such will determine if the software is good for various
statistical data or can only analyze a specific statistical data.

Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research 38
www.afropolitanjournals.com
Afropolitan Journals

Table 6: Dichotomous Statement of 2-points Likert scale

Statement: Can statistical data be analyzed without statistical software?
Opinion: Yes No

Likert scale: (2) (1)

Table 6 is a good example of dichotomous statement that has only two opinions, the
respondent must agree with one of the opinions as there is no room for undecided, such
likert method may not be applied in all survey fields of study.

Mean
The mean of any data set is the average rate of response, in applying Likert scale of
analyzing a data the mean value indicates the position of the opinion from the statements
under review. In this study the mean value will lie between 1.00 to 4.99 using 5 and 4 points
Likert scale, the Likert scale values is the weights, where the value can be round up or
truncate to the nearest whole number such value will indicate the rate of responses. For any
set of data, there is only one mean.
Mathematically:
𝐿1 𝑛1 + 𝐿2 𝑛2 + ⋯ + 𝐿𝑘 𝑛𝑘 ∑𝑘𝑖=1 𝐿𝑖 𝑛𝑖
𝑀𝑒𝑎𝑛 (𝜇) = = (1)
𝑛1 + 𝑛2 + ⋯ + 𝑛𝑘 𝑁
Where 𝐿𝑖 is the likert scale value (weight)
𝑛𝑖 is the total response of a statements (question)
𝑁 total number of respondents

Median
The median of a distribution is the middle value (if number of values is odd) or the average
of two middle values (if number of values is even) when the measurements are arranged in
order of magnitude (ascending or descending order). Invariably, the median may be
computed using:
𝑀𝑑 =
𝑛+1
𝑀( 2
) , if 𝑛 is odd
{1 𝑛 𝑛
(2)
2
{𝑀 (2 ) + 𝑀 (2 + 1)} , if 𝑛 is even

Mode
The mode of a set of observation is the most frequent value. A frequency distribution may
have one mode (unimodal) or two modes (bimodal) or three modes (trimodal) or many
modes (multimodal). In Likert Scale analysis the mode is determine from the option that
has the highest respondent and the corresponding Likert scale value is the mode of the
statement. Bimodal or trimodal and even multimodal can also be available in Likert Scale
of measurement. For instance, if the highest number of respondents is 50 and it tallies with

39 Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research
www.afropolitanjournals.com
 AJASTR

option “strongly agree” with likert scale “5”, then it interprets as the mode is 5 and is
“strongly agree” opinion. It is most frequent value in a set of data.

Variance
For an analysis that involves Likert Scale of data collection the formula can be written as:
𝑛1 (𝐿1 − 𝜇)2 + 𝑛2 (𝐿2 − 𝜇)2 + ⋯ + 𝑛𝑘 (𝐿𝑘 − 𝜇)2
𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 𝜎 2 =
𝑁
∑𝑘𝑖=1[𝑛𝑖 (𝐿𝑖 − 𝜇)2 ]
= (3)
𝑁
where 𝑛 total response on a particular statement in opinion
𝐿 Likert scale associated to the particular opinion
𝜇 mean value of a particular statement

Standard Deviation
Standard deviation is a useful measure of dispersion commonly used to determine how the
data varies or disperse from the mean by taken the positive square root of the variance gives
the expected value of the standard deviation.
𝑆𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝐷𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛 (𝜎)

∑𝑘 [𝑛𝑖 (𝐿𝑖 − 𝜇)2 ]

= √ 𝑖=1 (4)
𝑁

Data Presentation and Analysis

Data simulated was used for the illustration of the measurements.
Let the opinions in Table 7 be defined as Strongly Agree (SA), Agree (A), Undecided (U),
Disagree (DA) and Strongly Disagree (SD)

Table 7: Simulated Data of four Statements with 5-points Likert scale

OPINION Likert Statement Statement Statement Statement
Scale One Two Three Four
(𝑳𝒊 ) (𝑺𝟏 ) (𝑺𝟐 ) (𝑺𝟑 ) (𝑺𝟒 )
Strongly Agree (SA) 1 5 40 25 50
Agree (A) 2 18 20 50 90
Undecided(U) 3 10 5 10 105
Disagree (DA) 4 7 15 40 40
Strongly Disagree 5 10 15 75 15
(SDA)

Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research 40
www.afropolitanjournals.com
Afropolitan Journals

Graphical Presentation of Data (Descriptive)

Figure 1: Bar chart showing the levels of Figure 2: Bar chart showing the levels of
responses on 5-points Likert Scale statement responses on 5-points Likert Scale statement

Figure 3: Bar chart showing the levels of Figure 4: Bar chart showing the levels of
responses on 5-points Likert Scale statement responses on 5-points Likert Scale statement

The figures 1 to 4 is the descriptive statistics of the opinions of the respondent, the mode of
the statement one is the agree opinion it has the tallest bar and the means majority of the
respondent agree with the statement, and statement two has the strongly agree as the
mode, like statement three and four have strongly disagree and undecided as the mode
respectively.

41 Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research
www.afropolitanjournals.com
 AJASTR

Table 8: Results of mean, median, mode, variance and Standard deviation of table 7.
OPINION 𝑳𝒊 𝑺𝟏 𝑳𝒊 𝑺𝟐 𝑳𝒊 ∗ 𝑺𝟐 𝑺𝟑 𝑳𝒊 ∗ 𝑺𝟑 𝑺𝟒 𝑳𝒊 ∗ 𝑺𝟒
∗ 𝑺𝟏
SA 1 5 5 45 45 25 25 50 50
A 2 18 36 20 40 50 100 90 180
U 3 10 30 5 15 10 30 105 315
DA 4 7 28 15 60 40 160 40 160
SDA 5 10 50 15 75 75 375 15 75
Total 50 149 100 235 200 690 300 780
Mean (𝜇) 2.98 2.35 3.45 2.6
Median 3.04 2.20 4.20 3.35
(𝑀𝑑)
Mode (𝑀𝑜𝑑) 2 1 5 3
2
Variance(𝜎 ) 1.7 2.33 2.25 1.14
Standard 1.304 1.53 1.50 1.07
dev. (𝜎)

Table 8 indicates the capability of determining the measures of central tendency which
include mean, median, and mode from the analysis implying convergence of the data or
opinion at the same time, statement two had close mean and median indicating evenly
distribution of the opinions. The measures of dispersion indicate absence of outlier or over
dispersion. The measure of dispersion which include the variance and the standard
deviation, the standard deviation indicated the level of spread of the data away from the
mean value in which statement two had the highest standard deviation of 1.53 and the
mean value of 2.35 being the least of the mean values implies the significant spread of the
data across opinions. The 5-point likert scale can be regarded and suggested as the best
compare to 4-point Likert scale statements, this is because it gives room for any audience
that has no knowledge of the statement to make choice of undecided.

Table 9: Simulated Data of four Statements with 4-points Likert scale

OPINION Likert Statement Statement Statement Statement
Scale One Two Three Four
(𝑳𝒊 ) (𝑺𝟏 ) (𝑺𝟐 ) (𝑺𝟑 ) (𝑺𝟒 )
Strongly Agree (SA) 4 20 50 75 155
Agree (A) 3 20 20 50 90
Disagree (DA) 2 7 15 40 40
Strongly Disagree 1 3 15 35 15
(SDA)

Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research 42
www.afropolitanjournals.com
Afropolitan Journals

Graphical Presentation of Data

Figure 5: Bar chart on levels of responses on 4- Figure 6: Bar chart on levels of responses of
points Likert Scale 4-points Likert Scale

Figure 7: Bar chart showing the levels of Figure 8: Bar chart showing the levels of
responses on 4-points Likert Scale responses on 4-points Likert Scale

The figures 5 to 8, displayed the level of responses to each statement, Figure 5 shows that
the respondents have ties as the strongly agree and agree show the same level of
acceptability, this indicates that there is a bi-mode and such data can be asses further so as
to have a simple mode, figure 6, shows that the mode is strongly agree where the mode has
more the twice of the other opinions, 50 responses strongly agree with the statement from
the simulated data. Figure 7 and 8 of the graphical presentation shows that the modal
values are the strongly agree opinion because they are the tallest bar.

43 Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research
www.afropolitanjournals.com
 AJASTR

Table 10: Results of mean, median, mode, variance and Standard deviation of table 9
OPTIONS 𝑳𝒊 𝑺𝟏 𝑳𝒊 𝑺𝟐 𝑳𝒊 ∗ 𝑺𝟐 𝑺𝟑 𝑳𝒊 ∗ 𝑺𝟑 𝑺𝟒 𝑳𝒊 ∗ 𝑺𝟒
∗ 𝑺𝟏
SA 4 20 80 50 200 75 300 155 620
A 3 20 60 20 60 50 150 90 270
DA 2 7 14 15 30 40 80 40 80
SDA 1 3 3 15 45 35 35 15 15
Total 50 157 100 335 200 565 300 985
Mean (𝜇) 3.14 3.35 2.83 3.28
Median 3.4 4.0 3.25 4.0
(𝑀𝑑)
Mode (𝑀𝑜𝑑) 4,3 4 4 4
2
Variance(𝜎 ) 0.76 1.34 1.24 0.77
Standard 0.87 1.16 1.16 0.88
dev. 𝜎

Table 10 results indicate the strength of the measures where statements two and three
having the highest standard deviation indicate the clustering of the data at all levels toward
the mean and has the highest degree of spread. Statement one has two modes (bimodal)
where the opinions “Strongly Agree” and “Agree” have ties of 20 responses each, this
implies that interpretation of such data may be difficult. This means that the data can be
roughly split into two different groups, the bimodal distribution is useful in identifying two
distinct groups that can be used for further research to find a mode to draw conclusion.

Conclusion
In this study, Likert scale measurement is used as method of data collection and was
applied, statistical measures of central tendency and dispersion was used as statistical tools
which include mean, median, mode, variance, and standard deviation. To demonstrate the
performance and analysis of these statistical tools a simulation of data was carried out using
5 and 4 points Likert scale measurement of data collection in which various statements was
applied. The best fit statistical tool for analyzing Likert scale is the standard deviation as it
displayed the level of convergence of the data around the mean.

Recommendations
▪ The 5-point Likert scale is suggested as the best fit as it gives room for undecided
unlike 4-point Likert scale.
▪ The standard deviation is suggested as the best tool for analyzing Likert scale
method of data analysis as it shows the level of spread of the data toward the mean.
▪ Graphical presentation should be employed in the study of Likert Scale type of
measurement the graph will represent the mode clearly.

Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research 44
www.afropolitanjournals.com
Afropolitan Journals

References
Adelson, J. L., and McCoach, D. B. (2010). Measuring the mathematical attitudes of elementary students:
The effects of a 4-point or 5-point Likert-type scale. Educational and Psychological
Measurement, 70(5), 796–807.doi:10.1177/0013164410366694.
Adeniran, A. O. (2019). Application of Likert Scale’s Type and Cronbach’s Alpha Analysis in an Airport
Perception Study. Scholar Journal of Applied Sciences and Research, 2(4), 01-05
Alkharusi, H. (2022). A Descriptive Analysis and Interpretation of Data from Likert Scales in Educational
and Psychological Research, Indian Journal of Psychology and Education 12(2):13-16
Garland, R. (1991). The mid-point on a rating scale: Is it desirable? Marketing Bulletin, 2, 66-70. Available
at: http://marketing-bulletin.massey.ac.nz/V2/MB_V2_N3_Garland.pdf
Harpe, S. E. (2015). How to Analyze Likert and Other Rating Scale Data. Currents in Pharmacy Teaching
and Learning 7(6):836-850.
Iwona, F. (2016). Application of the likert and osgood scales to quantify the qualitative features of real
estate properties. Folia oeconomica stetinensia 7-16 DOI: 10.1515/foli-2016-002.
James, T.C. (2011). Using Likert-Type Scales in the Social Sciences. Journal of Adult Education 40(1),19-
22
Johns, R. (2005) One size doesn’t fit all: Selecting response scales for attitude items. Journal of Elections,
Public, Opinion and Parties, 15(2), 237-264, doi:10.1080/136898805001788
Joshi, A., Kale, S., Chandel, S. and Pal, D. K. (2015). Likert Scale: Explored and Explained. British Journal
of Applied Science & Technology 7(4): 396-403.
Kulas, J. T., & Stachowski, A. A. (2009). Middle category endorsement in odd-numbered Likert response
scales: Associated item characteristics, cognitive demands, and preferred meanings. Journal of
Research in Personality, 43(3), 489-493. doi:10.1016/j.jrp.2008.12.005
Likert, R. (1932). A technique for the measurement of attitudes. Archives of Psychology, 22(140), 5-55.
Purdey, B. (2013). Occupant stimulus response workplace productivity and the vexed question of a
measurement. Workplace Productivity, 31(11), 505-520. doi:10.1108/F-03-2012-0021
Raaijmakers, Q. A. W., van Hoof, a., 't Hart, H., Verbogt, T. F. M. A., & Vollebergh, W. A. M. (2000).
Adolescents’ midpoint responses on Likert-type scale items: Neutral or missing values?
International Journal of Public Opinion Research, 12(2), 208-216. doi:10.1093/ijpor/12.2.209
Ryan, M. (1980). The Likert scale's midpoint in communications research. Journalism Quarterly, 57(2),
305-313.
Stevens, S. S. (1946). On the theory of scales of measurement. Science, 103(2684), 677–680.
doi:10.1126/science.103.2684.677
Tanujaya, B., Prahmana, R.C. I. and Mumu, J. (2022). Likert Scale in Social Sciences Research: Problems
and Difficulties. FWU Journal of Social Sciences, Winter 16 (4), 89-101 DOI:
http://doi.org/10.51709/19951272/Winter2022/7

45 Vol. 16, No. 1 2024 African Journal of Advances in Sciences and Technology Research
www.afropolitanjournals.com