Likert scale is practical equally one of the almost cardinal and frequently used psychometric tools in educational and social sciences research. Simultaneously, information technology is also subjected to a lot of debates and controversies in regards with the analysis and inclusion of points on the scale. With this context, through reviewing the available literature and so clubbing the received information with coherent scientific thinking, this paper attempts to gradually build a construct around Likert scale. This analytical review begins with the necessity of psychometric tools like Likert calibration andits variants and focuses on some convoluted issues like validity, reliability and analysis of the scale.

Survey instrument for measuring attitude towards classroom lectures
Choice of Analysis of Likert Items: Aim and Construct of Research

Figures - uploaded by Ankur Joshi

Author content

All figure content in this area was uploaded by Ankur Joshi

Content may be subject field to copyright.

Join for gratuitous

_____________________________________________________________________________________________________

*Corresponding author: Electronic mail: drankurjoshi7@gmail.com;

British Journal of Applied Science & Technology

seven(4): 396-403, 2015, Article no.BJAST.2015.157

ISSN: 2231-0843

SCIENCEDOMAIN international

www.sciencedomain.org

Likert Scale: Explored and Explained

Ankur Joshi

ane*

, Saket Kaleastward

2

, Satish Chandel

3

and D. Thou. Pal

1

1

Department of Community Medicine, Gandhi Medical College, Bhopal, 462001,

Bharat.

2

Technical Support Unit, Madhya Pradesh State AIDS Control Guild, India.

3

Department of Pharmacology, All India Plant of Medical Sciences, Bhopal,

Bharat.

Authors' contributions

This piece of work was carried out in collaboration between all authors. Writer AJ initiated the idea, wrote the

first typhoon and contributed in further refinement with critical inputs to literature reviewestward. Author SK

conceptualized the variation of Likert calibration and provided critical input to the several drafts of

manuscript and literature review. Author SC contributed for common understanding of psychometrics

with disquisitional inputs. Author DKP reviewed and facilitated the final shape of paper. All authors read and

approved the terminal manuscript.

Article Information

DOI: x.9734/BJAST/2015/14975

Editor(s):

(1)

Meng Ma, Anhui University, Hefei, Anhui, China and Icahn Institute for Genomics and Multiscale Biology, Icahn School of

Medicine at Mountain Sinai, New York, United states.

Reviewers:

(1)

Anonymous, Usa.

(two)

Adalberto Campo-Arias, Faculty of Researches and Publications, Human Behavioral Research Institute, Bogota, Republic of colombia.

(3)

David Magis, Department of Education, University of Liège, Belgium.

(iv)

Anonymous, Republic of croatia.

(v)

Anonymousa, Canada.

Complete Peer review History:

http://www.sciencedoprincipal.org/review-history.php?iid=773&id=5&assistance=8206

Received 30

thursday

October 2014

Accepted 27

th

January 2015

Published 20

th

Feb 2015

ABSTRACT

Likert calibration is applied as ane of the most fundamental and frequently used psychometric tools in

educational and social southciences inquiry. Simultaneously, it is also subjected to a lot of debates

and controversies in regards with the analysis and inclusion of points on the southwardcale. With thisouth

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 Likert scale.

This analytical review begins with the necessity of psychometric tools like Likert scale andits

variants and focuses on some convoluted issues like validity, reliability and analysis of the scale.

Keywords: Psychometrics; Likert scale; points on calibration; analysis; instruction.

Joshi et al.; BJAST, vii(iv): 396-403, 2015; Article no.BJAST.2015.157

397

ane. INTRODUCTION

Nothing is more than than a fright you cannot name.

― Cornelia Funke, Inkheart

Since the inception of human race there is an

inclination to capture the etheexistent attributes of

human behaviour and performance.

Simultaneously, information technology has been a challenge from the

aforementioned time to quantify the thing which cannot be

measured through conventional measurement

techniques. The perceived demand of this

quantification lies in the necessity to transform an

individual's subjectivity into an objective reality.

Mental attitude, perceptions and opinions are such

qualitative attributes amenable for quantitative

transformation due to to a higher place mention reason.

Qualitative research techniques do endeavor to

compensate, by depicting the complexity of

man thoughts, feelings and outlooks through

several social science techniques, still the

quantification of these traits remains a

requirement and that'south how psychometric

techniques come into picture.

2. PSYCHOMETRICS AND LIKERT SCALE

Psychometrics techniques are existence developed,

instituted and refined in club to encounter the

quantification of traits similar ability, perceptions,

qualities and outlooks- theastward requirement of social

sciences and educational researches [ane,2].

Psychometrics operates through two ways; the

showtime is to formulate approaches (theoretical

construct) for measurements, followed by

evolution of measuring instruments and their

validation. Stanford Binet test (measures human

intelligence) and Minnesota Multiphasic

Personality Inventory (measures human

personality) are thursdaye example for the same. The

content in such instruments are rather 'pre-fixed'

[3,4,five]. The another path is same up to

formulation of theoretical construct for the

measurement. This conceptualization is followed

by operational assembly of abstruse

ideas/experiences/issues under investigation into

some statements (items) largely guided by the

aim of the study. This permits the contents

(items) in such scales/models to be rather

flexible and demand based. Rasch measurement

model (use for estimation of ability), Likert scale

(measures human attitude) are the examples of

such scales in Psychometrics used widely in the

social science & educational inquiry [3,4,5].

Likert scale was devised in social club to mensurate

'mental attitude' in a scientifically accepted and validated

manner in 1932 [half-dozen,7]. An attitude can be defined

as preferential ways of behaving/reacting in a

specific circumstance rooted in relatively

enduring organization of belief and ideas (effectually

an object, a subject or a concept) acquired

through social interactions [8]. This is clear from

this discourseastward mentioned above that thinking

(knowledge), feeling (affective) and action

(psychomotor) all together in various

combination/permutation constitute delivery of

attitude in a specified condition. The consequence is how

to quantify these subjective preferential thinking,

feeling and action in a validated and reliable

style: a help is offered by Likert scale [9,10].

The original Likert calibration is a gear up of statements

(items) offered for a real or hypothetical situation

under study. Participants are asked to due southhow their

level of understanding (from strongly disagree to

strongly concord) with the given statement (items)

on a metric scale. Here all the statements in

combination reveal the specific dimension of theastward

attitude towards the upshot, hence, necessarily

inter-linked with each other [eleven].

With this context, this exploratory article attempts

to describe two confusing issues related westwardith

Likert scale- (would be) preferable numbers of

points on a scale and analysis of the calibration.

During one of the contributing authors'

participation in a web based conversational

learning forum on medical education. These ii

bug emerged as thrust expanse acquiescent for

further exploration and fiftyucid explanation for thursdaye

educational researchers. An initial literature

searched by authors led to aggregation of common

conflicting evidences which compelled us to re-

explore and further construct arguments based

upon accumulated knowledge.

iii. LIKERT SCALE AND ITS VARIATION

Before proceeding further, let's take a brief look

on several constructional diversities of a Likert

scale as the analytical treatment and

interpretation with Likert calibration largely depends

upon these diversities.-Symmetric versus

asymmetric Likert calibration- If the position of

neutrality (neutral/don't know) lies exactly in

between two extremes of strongly disagree (SD)

to strongly concur (SA), it provides independence

to a participant to choose any response in a

balanced and symmetric due westay in either directions.

This construction is yardnown every bit symmetric scale.

On the other hand, asymmetric Likert scale offering

less choices on one side of neutrality (average)

as compared to other side. Asymmetric scale in

Joshi et al.; BJAST, seven(4): 396-403, 2015; Article no.BJAST.2015.157

398

some cases as well indicatesipsative (forced)

choices where there is no perceived value of

indifference/neutrality of the researcher

[12, xiii,fourteen].

Vii /ten point scale - They are the variation of

five point scale in which adjacent options are less

radically unlike(or moreast gradually unlike)

from each other as compare to a 5 point scale.

This larger (stride by stride) spectrum of choices

offers more independence to a participant to

choice the 'verbal' one (which he prefers almost)

rather than to pick some 'nearby' or 'close' option

[15]. These variations are discussed in more

details (in reference with validity and reliability)

further in this paper.

Likert and Likert type scale- The construction of

Likert (or Likert type) calibration is rooted into the aim

of the research Sometimes the purpose of the

research is to understand about the

opinions/perceptions of participants related with

single 'latent' variable (phenomenon of interest)

.This 'latent' variable is expressed by several

'manifested' items in the questionnaire. These

constructed items in a mutually exclusive manner

address a specific dimension of phenomenon

nether inquiry and in cohesion measure the whole

phenomena. Here during analysis, the scores of

the all items of the questionnaire are combined

(sum) to generate a composite score, which

logically in totality measures anuni-dimensional

trait. This musical instrument is known equally Likert scale.

Sometimes the master interest of the researcher

is not to synorththesize the stance of the participants

per se only to capture feelings, actions anorthwardd

pragmatic opinion of the participants about

mutually exclusive issues around phenomenon/s

under study. This fact demands the individual

assay of particular to ascertain the participants'

collective degree of agreement effectually that

issue. The scale used and so can be labeled every bit Likert

type and non Likert scale [1six]. A word of caution;

this 'management of inquiry' must be decided during

the planning phase and at least during the

designing of questionnaire and not at the time of

analysis.

4. IS vii Betoken LIKERT SCALE BETTER

THAN v Indicate LIKERT SCALE? - A

PERSPECTIVE CONTROVERSY OR

ESTABLISHED WITH A CONSENSUS?

Since the advent of Likert scale in 1932, there

have been debates among the users most its

best possible usability in term of reliability and

validity of number of points on the calibration [17-twenty].

Likert (1932,7) in his original newspaper, discussed

about the infinite number of definable attitudes

existing in a given person with possibility of

grouping them into "clusters" of responses. He

further conversed about the assumption of his

"survey of opinions" on westhich he provided his

results and psychological interpretations [21].

The fundamental assumptions of his survey being firstly,

the presentation of item on calibration are such that,

so as to permit the participants to cull conspicuously

opposed alternatives. Secondly, the conflicting

issues chosen were empirically important problems

thus, results themselves constituting an empirical

check on the caste of success.

Thus, it is argued in detail context of

clustering of attitudes. Considering reliability of

the responses from participants in a survey,

chances are that the vii betoken scale may perform

amend compared to 5 point scale owing to the

choice of items on calibration divers by the construct

of survey. The 7 point scale provides more

varieties of options which in turn increase the

probability of meeting the objective reality of

people. Equally a 7-point scale reveals more

description about the motif and thus appeals

practically to the "faculty of reason" of the

participants [19,20].

A respondents' absolute agreement with the

motif of topic may lie between the two descriptive

options provided on a five bespeak calibration. On repeated

administration, he/she may differ in choosing 1

of the options, e.grand. 3 instead of 4 when the

person thinks in betweenorth the 2 of the response

options on 5 signal scale. A vii point scale may

eliminate this problem up to an extent, by eliciting

retrieval beyond the utmost level of agreement

provided by a 5 point scale, the dilemma of

choosing between the two undesirable points on

v point. Hence this dilemma of forced choosing

between ii equally undesirable point imposed

by the 5-point Likert scale may be addressed upward

to a extent by offering moreastward choices (idue north between)

by a vii-point scale [2ii-24]. The provision of

number of scale points, 5 bespeak or 7 point, would

exist more engaging to the minds of respondents

when the items on the scale carry thursdaye statement

of ideas near the truth of the universe for both

the participants and the surveyor. It may create

the 'curves of reliability' around the 'zenith of

validity'. The dilemma of choice and explicit

greater extent of measurement by vii point calibration

is very much in the territory of the reason of

Joshi et al.; BJAST, 7(4): 396-403, 2015; Article no.BJAST.2015.157

399

response without which consideration of

reliability is of no weight [19].

Validity of Likert scale is driven by the

applicability of the topic concerned; in context of

respondents' understanding and judged past

creator of the response item. We can appreciate

it by an example: "How efficacious isouthward a

therapeutic modality in treating a particular

affliction?" This question when asked to a group

of individuals, indifferent with the disease or the

modality, the response pattern may remain

similar, independent of thursdayeast number of point on

the scale. The responses may cluster around

heart or to theast extreme ends. On the contrary,

when the topic concerned is relevant to the

respondents' context provision of more than option,

may add to the content & construct validity of the

calibration. Providing options more close to the

original view of the respondent reduce the role of

ambivalence in the responses [23,12]. Furthermore,

comprehension of all items and points on a scale

needs a judgment time and a memory bridge

different for different means and also depends on

communication mode. While listening to the

responses of a long scale may discern the

various options on the scale with bottom time to

judge compared to a written scale. Westwardritten scale

thus will add to validity even with more points on

the Likert calibration. Also research concerning bridge

of immediate memory due southupport this notion of

accuracy of response categories effectually vii,

as human being thousandind hasouthward span of absolute judgment

that tin can distinguish seven categories at a fourth dimension [25].

v. ANALYSIS OF THE Information technologyEM RESPONSE

Before we go on to the method of analysis

bachelor to Likert scale, a very fundamental but

every bit controversial question should be

addressed- which type of scale Likert is?

There are two southwardchools of thoughts - One schoolhouse

considers Likert scale as ordinal and other treats

it asouth Interval scale. This conflict is primarily

rooted into the question: whether points on a

items are equivalent and equidistant? Points on

scale are not close enough to consider them

equal (in other westwardords strongly agree is definitely

away from agree and agree is abroad from

neutral), they should exist considered as non-

equivalent entity. There is an understanding inorthward both

schools for the above fact. The conflict arises on

request some other question: if the points on scale

are non –equivalent, are they equi-distant (in

other words is 'neutral' of same distance from

'agree' as 'hold' from 'strongly 'agree')? This

question isouth important as past answering of this

question only, one can make up one's mind whether Likert

scale can be treated equally Interval scale?

The offset school of researchers and statisticians

consider Likert calibration as ordinal scale. They

fence that choices or responses are arranged in

some ranking order. Howalways, as this scale

doesn't bear witness the relative magnitude and

distance between two responses quantitatively, information technology

can't be treated as interval scale. The other

school interprets this dilemma from a different

perspective, stating that when the aim of the

researcher is to 'combine' all the items in order to

generate a 'composite' score for an individua50

rather than dissever analysis of single item

responded by all individuals, then this

individualistic summative score (for all the items)

of a participant shows a sensible realistic

distance from the individual summative score of

some other individual; hence, can be labeled as

'interval estimates' [26,xvi].

To understand this concept, let's presume a

scenario in which the aim of the inquiryer is to

measure out the attitude towards classroom lectures

and to make out relative adoptences (library

reading and small grouping teaching) compared

with lecture. (Fig. one) He designs the following

survey instrument on a 5 point Likert scale for the

stated aim-

The commencement question of importance is: 'Can these

items be clubbed (see together) in order to

generate a blended index for measuring the

attitude?' In gild to evaluate their

appropriateness for transformation into a single

composite index, following points can be

considered-

1. Whether the items are arranged in logical

sequence?

2. Whether the items are closely interrelated

simply provide some independent information

as well?

3. Whether there is some chemical element of

'coherence/expectedness' between

responses (whether adjacent response tin be

predicted up to some extent based upon

previous one)?

4. Due westhether each item measures a distinct

element of the issue?

Joshi et al.; BJAST, vii(iv): 396-403, 2015; Article no.BJAST.2015.157

400

Fig. ane. Survey instrument for measuring attitude towards classroom lectures

Fig. two. Selection of Analysis of Likert Items: Aim and Construct of Research

If respond to all the above questions isouthward affirmative

for all the items of a set, they thouay be combined

to construct a composite index which measures

the collective stance of the participant towards

miracle under written report. In the above example

as item one, two and 3 fulfill all four criteria for each

other, they may be combined and can be treated

further in unison.

On the other hand, item-4 and detail-5, offering

separate and sovereign (mutually exclusive)

preferences regarding two different pedagogy-

learning methods: self-directed reading and small

grouping educational activity. Hence, they can't be combined

and further they should be analyzed

independently from detail i, ii and iii and even

from each other.

Joshi et al.; BJAST, vii(4): 396-403, 2015; Article no.BJAST.2015.157

401

Later on this assertion of eligibility for combination,

the next question ascendsouth- On what scale can item

1, 2 and 3 be treated and westchapeau is the appropriate

measurement calibration for item4 and detail-v?

The answer of the above question fiftyies in another

question asked past Stevens in his famousouthward paper:

'what are the rules (if any) under which numerals

are assigned?' Hither we see (a) the minimum

score one can secure for outset 3 items is 3

(and not an absolute aught). The reason for this

patently dislike for nix fiftyies in the fact that in

psychometrics, attitude is preferably measured in

positive degree and existence the 'strongly disagree

'cannot be equated with 'absolute disagreement';

in that location is ever something below than southtrongly

disagree. Zero also gives the notion of neutrality

rather disagreement (the attitude is nothing; means

one is apathetic to issue) (b) Each numeral

conveys thdue east aforementioned meaning in all 3 items (i.e.

3 denotes the neutral in all three items) (c) As

mentioned above, all three items can be clubbed

while satisfying thdue east content and criterion validity.

This sentence needs a little more than explanation.

The idea or concept behind framing detail i, ii and

3 is to capture the stance of participants most

the lecture. Thisouthward theoretical construct how westell

tin can be transformed into operating reality, can be

ascertained by looking at relevant content

domains (content validity/reflection of construct),

ability to distinguish opinion on lecture from other

teaching modality (concurrent validity) and

similarities among items one to three and dissimilarities

from item 4 and 5 (convergent and discriminant

validity). Concurrent, convergent and

discriminant validities are the domains of criterion

validity. Before deciding any southwardtatistical treatment

to items, all the items must be scrutinized for

validity issues.

If we await into point (a), (b) and (c) in cohesion

for the set of item one, 2 and 3, that blended

score for the item-one, 2 and 3 can be compared

with another composite score for another

private on an interval calibration. A 'rank-order'

among the composite scores can be presumed

as welfifty as equality of interval amid related

composite scores tin also be postulated. The

specific point on a detail information technologyem is conveying

the same meaning for all individuals (for item -ii

point 3 on Likert scale denotes 'neutral' among

all individuals.) Moreover a specific point (say ii

for disagree) is conveying the same meaning

(same extent of disagreement) in all the items

and in that location is no accented goose egg in scale (minimum

achievable score is three). From the discourse, this

tin can besafely assumed (afterwards yardoing through all

these mathematical characteristics with due

consideration of validity related issues) that the

obtained composite data for item 1, two and 3 for

all the participants tin can be treated on an interval

scale.

The truth has different dimension in case of item

4 and item 5. Particular -4 and 5 being a mutually

exclusive observation from each other (stance

on cocky-directed reading/ minor group educational activity)

and from item 1, 2 and iii should be treated

differently. They may not be combined (validity

restriction) for an individuafifty as they are nowhere

providing complementary observatiodue north.

Still item iv and v tin can be treated on a certain

measurement calibration. The arguments for this

supposition are –first, a specific bespeak (say point -

4) for a particular item ( (say for detail-4) conveys

the same meanin1000 (hold) for all individuals

treated on that detail and second, response

variables obtained for a single item from all the

individuals tin can beastward arranged in any social club

preserving transformation (50ike square,

multiplication, square root etc.) to the response

variable(the rank lodge remains unaffected) ....

so an ordinal calibration's assumptions and treatment

is applicable on this subset of items (4 and five).

Once it is clear that under which rules the items

are categorized and what the direction of inquiry

is, it becomes obvious that the further statistical

treatment as per their assignment into ordinal or

interval scale.

6. CONCLUSION

The crux that can be extracted from the above

inductive arguments and logical interpretation is

that the methods adopted for Likert calibration

analysis largely depends on the item response

variable assignment into ordinal or interval scale

which in turn depends odue north the construct of the

research instrument. This construct of research

instrument tin can be derived from objectives of

written report and objectives are the operational form of

theoretical construct of miracle under

inquiry. In other words, designing of instruments

based upon objectives and frameworks of study

decides further statistical handling.

Hence if one wishes to combine the items in

social club to generate a composite score (Likert

scale) of a set up of items for unlike participants,

then the assigned calibration will be an interval scale

(Fig. ii abovdue east). The measures for central

tendency and dispersion for an interval scale are

Joshi et al.; BJAST, vii(four): 396-403, 2015; Commodity no.BJAST.2015.157

402

mean and standard departure. Further this information

set can beastward statistically treated due westith Pearsons'

correlation coefficient (r), Analysis of Variance

(ANOVA) and regression analysidue south.

As opposed to, if researcher wishes to analyze

separate detail (no composite score; Likert type

scale), the assigned scale for such information set volition

exist ordinal (Fig. 2 above). Needless to say, the

recommended measure of central tendency and

dispersion for the ordinal data are the median (or

the mode) & frequency (or range). An ordinal

information set can further be statistically tested by non-

parametric techniques such as Chi-square examination,

Kendall Tau B or C examination.

Before wrapping up, it is imperative to transform

an abstract consequence into figurative shape in gild to

measure it upward to best possible extent.

Simultaneously, this is an integrate process

reason being influenced by perspective anorthd

subjectivity of researcher. Still all attemptsouth should

be directed for quantification of such qualitative

attributes as -'westchapeau get measured, get managed.'

(Peter Druker).

COMPETINOne thousand

INTERESTS

Authors have declared that no competing

interests exist.

REFERENCES

1. Cook DA, Beckman TJ. Current concepts

in vahatity and reliability for psychometric

instruments: Theory and application. The

American Periodical of Medicine. 2006;119

(ii). DOI:10.1016/j.amjmed.2005.10.036.

2. Shea JA, Fortna GS. Psychometric

Methods. In: Norman ThousandR, Van der Vleuten

CPM, Newble DI, editors. International

Handbook of Research in Medical

Education. Dordrecht: Kluwer Academic

Publisher. 2002;97-126.

3. Youngstrom EA, Glutiing JJ, Watkins MW.

Stanford-Binet intelligence scale: Quaternary

Edition (SB4): Evaluating the due eastmpirical

bases for interpretations. In: Reynolds CR,

Kamphaus RW, editors. Handbook of

psychological and educational

cess: Intelligence, aptitude, and

achievement. New York: Guilford press.

2003;217-242.

4. Wu 1000, Adams R. Applying theast Rasch

model to psycho-social measurement:

A practical approach. Melbourne:

Educational Measurement Solutions; 2007.

5. Croasmun JT, Ostrom L. Using Likert-type

scales in the social sciences. Journal of

Adult Education. 2011;40:19-22.

6. Edmondson DR. Likert scales: A history.

Proceedings of the 12

th

Conference on

Historical Analysis and Research in

Marketing (Amuse). April 28-May1,

California, U.s.; 2005.

7. McLeod S. Likert Calibration; 2014.

Simplypsychology.org.

Retrieved:http://world wide web.simplypsychology.org

/Likert-scale.html/pdf

8. Park K. Social sciences and health. In Park

1000, editor. Park Text Volume of Preventive

and Social Medicine. Jabalpur: Bhanot

Publishers. 2013;54x-54x.

9. Culbertson JM. Due westhat is an attitude?

Journal of Cooperative Extension. 1963;

79-84.

10. Schwarz N, Bohner Grand. The construction of

attitudes. In: Tesser A & Schwarz Due north,

Editors. Blackwell Handbook of Social

Psychology. Oxford: Blackwell. 2001;436-

457.

11. Singh YK. Fundamental of Enquiry

Methodology and Statistics. New Delhi:

Newage International (P) Ltd. Publisher;

2006.

12. Lobsy J, Wetmore A. CDC Coffee Break:

Using Likert Scales in Due eastvaluation Survey

Piece of work [Internet]; 2014. Cdc.gov.

Retrieved:www.cdc.gov/dhdsp/pubs/exercisecs/

CB_February_14_2012.pdf

xiii. Tsang KK. The use of midpoint on Likert

scale: The implications for educational

research. Hong Kong Teachers Centre

Journal. 2012;11:121-130.

xiv. Malhotra NK. Questionnaire Blueprint and

Scale Development. In: Grover R, Vriens

One thousand, editors. The Handbook of Marketing

Research. California: Sage Publications,

Inc; 2006.

15. Dawes J. Do data characteristics modify

according to the number of scale points

used? An experiment using 5-point, seven-point

and10-bespeak scales. International Periodical of

Market Enquiry. 2008;50(1):61-77.

16. Boone HN, Boone DA. Analyzing Likert

Data. Journal of Extension. 2012;v0(2).

Retrieved:http://world wide web.joe.org/joe/2012april/t

t2.php

17. Colman AM, Norris CE, Preston CC.

Comparison rating scales of different

lengths: Eastwardquivalence of scores from 5-

point and seven-signal scales. Psychological

Reports. 1997;fourscore:355-362.

Joshi et al.; BJAST, vii(four): 396-403, 2015; Commodity no.BJAST.2015.157

403

18. Preston CC, Colman AM. Optimal number

of response categories in rating scales:

reliability, validity, discriminating power,

and respondent Preferences. Deeda

Psychologica. 2000;104;i-15.

19. Chang Fifty. A psychometric evaluation of 4-

point and 6-point Likert-type scale in

relation to reliability and validity. Applied

Psychological Measurement. 1994;18:205-

215.

20. Cox EP. The optimal number of response

alternate for a scale: A review. Journal of

Marketing Research. 1980;17(four):407-422.

21. Likert R. A technique for the

measurements of attitudesouth. Archives of

psychology. 1932;140(22):v-55.

22. Pearse N. Deciding on the scale

granularity of response categories of Likert

type scales: The Case of a 21-Indicate Scale.

Electronic Journal of Business organisation Research

Methods. 2011;9(two):2011.

23. Finstad Thou. Response interpolation and

scale sensitivity: Evidence confronting 5-point

scales. Journal of Usability Studies.

2010;5(three):104-110.

24. Komorita SS and Graham WK. Number of

calibration points and the reliability of scales.

Educational and Psychological

Measurement. 1965;25(4):987-995.

25. Miller GA. The magical number 7, plus

or minus two: Some limitdue south on our capacity

for processing information. The

Psychological Review. 1956;63:81-97.

26. Carifio J, Perla RJ. Ten common

misunderstandings, misconceptions,

persistent kyths and urban legends about

Likert scales and Likert response formats

and their antidotes. Journal of Social

Sciences. 2007;3(3):106-116.

_________________________________________________________________________________

© 2015 Joshi et al.; This is an Open Access article distributed nether the terms of the Creative Mutualsouthward Attribution License

(http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium,

provided the original work isouth properly cited.

Peer-review history:

The peer review history for this newspaper tin can be accessed here:

http://www.sciencedomain.org/review-history.php?iid=773&id=5&aid=8206

... In both surveys, a v-signal Likert scale was used as a means of measurement. This method is widely used in the social sciences and in educational research to mensurate human being attitudes, specially for obtaining knowledge on the degree of acceptance of phenomena, views, processes, features, etc. [59][60][61][62]. The first survey, addressed to those entities related to the structure sector, included closed questions, with the possibility of respondents' adding and evaluating their own examples. ...

... The main benchmark for the selection of expert respondents was their type of activity linked to In both surveys, a 5-signal Likert scale was used as a ways of measurement. This method is widely used in the social sciences and in educational inquiry to measure human attitudes, particularly for obtaining knowledge on the degree of credence of phenomena, views, processes, features, etc. [59][threescore][61][62]. The showtime survey, addressed to those entities related to the construction sector, included closed questions, with the possibility of respondents' calculation and evaluating their own examples. ...

The demand for forest has increased in recent years due to new technical possibilities and environmental concerns. This paper provides an assay of the factors that touch on the utilise of wood in the construction sector, and an assessment of their importance in individual countries and for groups of stakeholders. The study covers the technical, societal, political, economic, and gender aspects of woods structure, with the aim of increasing global agreement regarding national differences, the current state of affairs, and the potential for further development. The subject was investigated using a survey, and the virtually important opportunities for and barriers to growth in the utilise of wood in the construction sector were selected, post-obit a statistical analysis. The results bespeak potent regional and cultural differences regarding the acceptance of some of the opportunities and barriers related to the development of woods construction. The findings bespeak that there is a need to promote woods construction based on its technical and economical benefits rather than its societal ones. On the other hand, the current societal barriers should be addressed as a priority, together with the institution of common and harmonized policies. The results of this study, therefore, will contribute to the generation of regional-sensitive information that can be useful for policymakers when updating the building codes in their private countries.

... We commencement sample 200 ELI5 test set questions and generate answers of various lengths {80, 100, ..., 260} (260 is the average sequence length in training set) with beam search, sampling, reflective (West et al., 2021), and Child. We then ask humans to rate these generations with 7-point Likert scoring (Joshi et al., 2015) how likely the generated text is a natural sentence. Each generation receives at least xv ratings. ...

Pre-trained linguistic communication models (LMs) have been shown to memorize a substantial amount of knowledge from the pre-training corpora; however, they are however limited in recalling factually correct knowledge given a certain context. Hence, they tend to suffer from counterfactual or hallucinatory generation when used in knowledge-intensive natural language generation (NLG) tasks. Recent remedies to this problem focus on modifying either the pre-training or task fine-tuning objectives to incorporate noesis, which normally require additional plush grooming or architecture modification of LMs for practical applications. We present Noesis Infused Decoding (KID) -- a novel decoding algorithm for generative LMs, which dynamically infuses external knowledge into each stride of the LM decoding. Specifically, we maintain a local cognition retentivity based on the current context, interacting with a dynamically created external cognition trie, and continuously update the local memory as a knowledge-aware constraint to guide decoding via reinforcement learning. On half dozen diverse cognition-intensive NLG tasks, task-agnostic LMs (e.g., GPT-2 and BART) armed with Kid outperform many task-optimized state-of-the-art models, and show specially potent performance in few-shot scenarios over seven related cognition-infusion techniques. Man evaluation confirms Child's power to generate more relevant and factual language for the input context when compared with multiple baselines. Finally, KID as well alleviates exposure bias and provides stable generation quality when generating longer sequences. Code for KID is bachelor at https://github.com/microsoft/Child.

... Nosotros use a seven phase Likert scale to permit the person to express how much they concord or disagree with a detail statement [33]. The UX questionnaire often adopts the Likert scale to reduce the well-known central trend bias for such items. ...

The anthropomorphization of human-robot interactions is a fundamental aspect of the blueprint of social robotics applications. This article describes how an interaction model based on multimodal signs similar visual, auditory, tactile, proxemic, and others can improve the communication betwixt humans and robots. We accept examined and appropriately filtered all the robot sensory information needed to realize our interaction model. We have as well paid a lot of attention to communication on the backchannel, making it both bidirectional and evident through auditory and visual signals. Our model, based on a job-level architecture, was integrated into an application called W@ICAR, which proved efficient and intuitive with people not interacting with the robot. It has been validated both from a functional and user feel bespeak of view, showing positive results. Both the pragmatic and the hedonic estimators have shown how many users particularly appreciated the application. The model component has been implemented through Python scripts in the robot operating system environment.

... Furthermore, regarding the number of response options in the questionnaire, participants suggested a wide range of options, from 0-signal upwards to 10-point calibration. Still, researchers claim that the 7-indicate scale provides more diversity of options than 5 items, which in plough increase the probability of accurately reflecting respondent perceptions (Joshi et al., 2015). Hence items in the CEUTIE model are measured on a seven-signal Likert scale (0 = strongly disagree to 6 = strongly hold). ...

Although a large variety of methodologies, contexts and perspectives have been used to examine educational application of technology, there is a paucity of instruments that are designed to comprehensively evaluate the use of engineering in instruction. This paper presents a Confirmatory Gene Assay (CFA) of an instrument that incorporates eight key dimensions: learning, melancholia, behavioral, applied science, blueprint, education, presence/community, and institutional environment. These dimensions were derived from rigorous systematic literature review and field specialist validation processes. The model was then refined and empirically confirmed in this written report past ane,352 participants undertaking a Coursera open online course. The results of applying the musical instrument, as well as qualitative feedback from participants, are shared to illustrate its breadth and utility. The final 28 item "Comprehensive Evaluation of Use of Technology in Education" musical instrument is provided in full to support consistent, holistic and robust evaluation and comparing of technology employ across educational contexts.

... To study whether the proposed preparation influences the students' perception of Computer Scientific discipline, we designed a questionnaire based on Likert scales [34] for the students to complete twice, once before and once after the training. The questionnaire used in the pre-training stage is denoted as pre-examination, while the questionnaire administered after the Computational Thinking training is called the mail service-examination. ...

Although Computer science has grown to become one of the most highly demanded professional careers, every year, merely a small percentage of students choose a caste directly related to Information science. Mayhap the problem lies in the lack of information that society has most Computer Science itself, and peculiarly about the work computer scientists do. No one doubts the part of Mathematics or Languages as cadre subjects in every principal and secondary education syllabus; nonetheless, Computer Science plays a negligible role in most current syllabuses. Merely in a few countries have governments paid special attention to content related to Computer Science and to learning to analyze and solve issues the manner computer scientists do (Computational Thinking). In this paper, we present Piens@ Computacion@ULLmente, a project that provides a methodology to promote Figurer Scientific discipline through Computational Thinking activities amidst primary and secondary teaching students. The results obtained from an exhaustive statistical analysis of the data we collected demonstrate that the perception of Estimator Science that pre-university students have can be improved through specific training. Moreover, we can also ostend that the performance of pre-academy students involving Computational Thinking skills is independent of gender, particularly at the main educational activity level.

Organizations often face difficulties when measuring their social performance. The lack of international standards, the qualitative/quantitative nature of data, and the unavailability of primary sources all hinder social impact assessments, especially in manufacturing settings. To fill these gaps, the method proposes a unproblematic application protocol of Social Organizational Life Wheel Assessment (SO-LCA), customized for an Italian ceramic tile manufacturer. The method leverages Manufacture iv.0 digital technologies to collect real-time main and site-specific social data, making the social assessment dynamic. The managerial approach adopted for the selection of social metrics and weighting of indicators and indexes, can support the transition of the manufacturing arrangement into Arrangement 4.0. The method also provides a contribution to the operational validation of the UNEP guidelines by extending their surface area of application. Finally, the proposed method gives substance to social responsibility through social accounting, helping the organization to measure the correct social impact starting from the detailed data, namely the decisions made in the business and in production. •Social Organizational Life Bike Assessment (SO-LCA) application protocol validated in Industry iv.0 surroundings. •Social metrics directly linked to production and business processes for the dynamic assessment of social functioning. •Piece of cake replicability of the method in other organizational contexts.

  • Suci Ramadhani
  • Santun R. P. Sitorus
  • Didit O. Pribadi

In preparing the management of the regional development plan, it is necessary to pay attending to determining the main focus of development. 1 of the strategies that tin exist used in Pasaman Regency is to develop areas based on leading agricultural commodities. This written report aims to provide direction for regional development program based on leading bolt in Pasaman Regency. The area that became the object of research consisted of 12 sub-districts and 62 nagari (villages). In determining the sub-district's leading commodities, each nagari is represented by 2 respondents then that the total number of respondents entirely is 124 people. For the training of directions for regional development plan based on leading commodities, interviews were carried out with 5 experts using the AHP questionnaires. The results showed that the leading commodities of food crops in Pasaman Regency were paddy field, rainfed paddy field and corn with a suitable land area of iv.197,9 ha, while the leading commodities of plantation crops were rubber, cocoa and oil palm with a suitable state expanse of fifteen.880,3 ha. At that place are three levels of regional development in Pasaman Regency, namely hierarchy I, II and III. Two sub-districts are included in hierarchy I, v sub-districts are included in bureaucracy Ii, and five sub-districts are included in Hierarchy Iii. Priority for the direction of the regional development programme based on leading commodities in Pasaman Regency is ordered from priority 1 to priority 12. The results of this study can exist used every bit a reference in preparing the direction of regional development plan based on leading commodities in Pasaman Regency.

Context Web engineering involves managing a high diversity of artifacts implemented in different languages and with different levels of granularity. Technological companies usually implement variable artifacts of Software Product Lines (SPLs) using annotations, being reluctant to adopt hybrid, oftentimes complex, approaches combining composition and annotations despite their benefits. Objective This paper proposes a combined approach to support fine and coarse-grained variability for spider web artifacts. The proposal allows web developers to proceed using annotations to handle fine-grained variability for those artifacts whose variability is very difficult to implement with a composition-based approach, but obtaining the advantages of the limerick-based arroyo for the fibroid-grained variable artifacts. Methods A combined approach based on feature modeling that integrates annotations into a generic composition-based arroyo. We propose the definition of compositional and annotative variation points with custom-defined semantics, which is resolved by a scaffolding-based derivation engine. The arroyo is evaluated on a real-world web-based SPL by applying a set up of variability metrics, likewise as discussing its quality criteria in comparison with annotations, compositional, and combined existing approaches. Results Our approach finer handles both fine and coarse-grained variability. The mapping between the feature model and the web artifacts promotes the traceability of the features and the uniformity of the variation points regardless of the granularity of the spider web artifacts. Conclusions Using well-known techniques of SPLs from an architectural point of view, such every bit feature modeling, can improve the blueprint and maintenance of variable web artifacts without the need of introducing complex approaches for implementing the underlying variability.

Climate change has posed serious risks to littoral cities effectually the globe. Effective urban disaster management calls for the coordination between the local government and residents. We propose a comprehensive framework to study urban disaster resilience under climatic change with New Orleans of Louisiana in the U.S. as the report area. Municipal take chances mitigation must exist sufficient to mitigate these hazards. Residents' risk perceptions are a vital component of social vulnerability and can shape public decisions to increase disaster resiliency. Because climate change is expected to intensify, information technology becomes of import to ensure that residents' risk perceptions are considered when developing municipal plans to maximize regional resiliency. This research aims to identify a gap in the hazard mitigation procedure that tin exist closed to ameliorate set up the customs to manage coastal hazards. To achieve this, an online survey is distributed in the New Orleans metropolitan area to determine residents' hazard perceptions and expectations of the local authorities'due south action. Policy analysis is conducted to identify the priorities held by municipal planners in these issues. Although there is no gap in the perception of risk and municipal mitigation of current littoral hazards, there is a gap between the municipal approach to climate change mitigation and the concern and expectation of actions the residents hold regarding the future effects of climate change. The approach to climate change should be reconsidered on a municipal level and new minor personal incentives should be promoted to maximize resiliency toward coastal hazards in the hereafter.

  • John Dawes John Dawes

This study examined how using Likert-type scales with either 5-point, 7-signal or ten-betoken format affects the resultant information in terms of hateful scores, and measures of dispersion and shape. Three groups of respondents were administered a series of eight questions (group n's = 300, 250, 185). Respondents were randomly selected members of the general public. A different scale format was administered to each group. The five-and 7-betoken scales were rescaled to a comparable mean score out of ten. The study found that the 5-and seven-betoken scales produced the same mean score as each other, in one case they were rescaled. Even so, the 10-point format tended to produce slightly lower relative means than either the v-or 7-betoken scales (afterward the latter were rescaled). The overall hateful score of the eight questions was 0.3 scale points lower for the ten-point format compared to the rescaled 5-and 7-point formats. This departure was statistically significant at p = 0.04. In terms of the other data characteristics, in that location was very little departure amid the scale formats in terms of variation about the mean, skewness or kurtosis. This written report is 'practiced news' for research departments or agencies who ponder whether changing calibration format will destroy the comparability of historical data. 5-and 7-bespeak scales can hands exist rescaled with the resultant data being quite comparable. In the case of comparing 5-or 7-point data to 10-point information, a straightforward rescaling and arithmetic adjustment easily facilitates the comparison. The study suggests that indicators of customer sentiment – such equally satisfaction surveys – may be partially dependent on the choice of scale format. A 5-or vii-point calibration is likely to produce slightly higher mean scores relative to the highest possible attainable score, compared to that produced from a 10-indicate calibration.

  • Andrew M. Colman Andrew M. Colman
  • Claire East. Norris
  • Carolyn C. Preston

Using a cocky-administered questionnaire, 227 respondents rated service elements associated with a eating place, retail shop, or public transport company on several 5-point and 7-signal rating scales. Least-squares regression showed that linear equations for estimating seven-indicate from five-signal and 5-point from 7-betoken ratings explained over 85% of the variance and fitted the data almost besides equally higher-gild polynomials and power functions. In a cross-validation on a new information set, the proportion of variance explained fell to about 76%. Functionally inverse versions of the derived linear equations were calculated for the convenience of researchers and psychometricians.

  • Eli P. Cox

A conceptual framework employing the distinction between stimulus-centered and subject-centered scales is presented as a basis for reviewing 80 years of literature on the optimal number of response alternatives for a scale. Concepts and research from information theory and the absolute judgment paradigm of psychophysics are used. The author reviews the major factors influencing the quality of scaled data, points out areas in particular need of additional research, and makes some recommendations for the applied researcher.

  • H.N. Boone Jr
  • D.A. Boone

This commodity provides data for Extension professionals on the correct analysis of Likert data. The analyses of Likert-type and Likert scale information require unique data analysis procedures, and equally a upshot, misuses and/or mistakes often occur. This article discusses the differences betwixt Likert-blazon and Likert scale data and provides recommendations for descriptive statistics to exist used during the assay. Once a researcher understands the difference betwixt Likert-type and Likert scale data, the determination on appropriate statistical procedures will be apparent.

  • Lei Chang Lei Chang

Reliability and validity of iv-betoken and six-point scales were assessed using a new model-based ap proach to fit empirical data. Different measurement models were fit past confirmatory factor analyses of a multitrait-multimethod covariance matrix. 165 gradu ate students responded to ix items measuring three quantitative attitudes. Separation of method from trait variance led to greater reduction of reliability and heterotrait-monomethod coefficients for the 6-bespeak scale than for the 4-point scale. Criterion-related valid ity was not affected by the number of scale points. The issue of selecting four- versus half dozen-signal scales may not be generally resolvable, but may rather depend on the empirical setting. Response conditions theorized to in fluence the use of scale options are discussed to pro vide directions for further inquiry. Index terms: Likert-type scales, multitrait-multimethod matrix, reli power, scale options, validity.

From the Introduction: A growing body of literature suggests that attitudes may be much less enduring and stable than has traditionally been assumed. ... cocky-reports of attitudes are highly context dependent and can exist greatly influenced past minor changes in question wording, question format, or question society. For some researchers, this malleability just reflects measurement error ... For other researchers, the same findings indicate that all we assess in attitude measurement are evaluative judgments that respondents construct ... based on whatever information happens to be accessible (e.yard. Schwarz & Strack, 1991). From this perspective, the traditional attitude concept may not be particularly useful and we may learn more than about human being noesis and beliefs from a detailed assay of the underlying judgmental processes. Other researchers have taken intermediate positions ... For example, Lord & Lepper (in press) and Tourangeau and his colleagues (e.1000. Tourangeau, 1992) equate attitudes with relatively stable retention structures, but presume that individuals sample from these structures when they reply attitude questions. Hence, a stable attitude can result in variable attitude reports, depending on which aspect of the knowledge construction (mental attitude) is accessed. Others (e.1000., Wilson, 1998) suggested that individuals may hold multiple attitudes about an object, accessing different ones at different points in time. As we illustrate below, information technology is surprisingly difficult to design conclusive empirical tests to evaluate the relative merit of these proposals ... Yet, a scientific concept like "attitude" is to exist evaluated on the basis of its explanatory power – and without taking judgmental processes into account, at that place is little that the attitude concept explains. In fact, the contemporary definition of attitudes as "likes and dislikes" (Bem, 1970, p. 14) equates attitudes with evaluative judgments. Hence, the first section of this affiliate highlights judgmental processes and the 2d section applies these process assumptions to some findings that are typically considered evidence for the indelible nature of attitudes. In response to the malleability of attitude reports, social psychologists have repeatedly tried to supersede or supplement verbal self-written report measures with other, presumably more direct, ways to assess individuals' evaluative responses to attitude objects. These attempts range from the "bogus pipeline" (Jones & Sigall, 1971) of the 1970s to the recent development of sophisticated "implicit" measures of attitudes (eastward.g. Dovidio & Fazio, 1992). Recent findings suggest that such measures may exist only every bit context dependent as exact reports, although the relevant contextual variables may differ. The third department addresses these developments, which are discussed in more item by Banaji and colleagues (Affiliate vii, this volume) and Bassili (Chapter 4, this volume). Much every bit the indelible nature of attitudes has been called into question, some other body of research suggested that attitudes may not be closely related to beliefs either (see Wicker, 1969, for an influential early on review). Instead, nosotros may expect a close relationship between attitudes and behavior only under some specific, and relatively narrow, conditions (see Chapter 19, this volume). These weather condition can be fruitfully conceptualized within a judgment perspective, equally nosotros review in the final section.