RITEE COLLEGE OF NURSING, RAIpUR
(C.G.)
SESSION:-2022-2023
SUBJECT - Nursing education
Clinical Evaluation Tool
On
Summated Scale
Submitted to:
Submitted By:
MRS. PRIYANKA DAS MR. SANJAY
PATEL
ASSISTANT PROFFESOR MSC
NURSING 1ST Year RITCON
RITCON
SUMMATED SCALE
INTRODUCTION
Summated scales are a collection of related questions that measure underlying constructs. For
example, the Work Orientation Scale (Vande Walla, 1997) is a validated scale with 13
questions that measures 3 constructs or work orientation each determined by assuming a set
of 4 or 5 related questions. A summated scale is different form a response scale, which is an
ordered series of response choices to survey questions if u used an existing summated scale,
you must provide research evidence of validity and its reliability. The summated should
correlate strongly with established measures of the same characteristics, correlated somewhat
with measures of related characteristics, and show no correlation with measures of unrelated
characteristics. Response on summated scale should show consistency over time (test-retest
reliability) and across questions which indicates the questions are measuring the same thing
(internal consistency).
DEFINITION:
The summated scale refers to assigning a grade for student’s achievement at the end of a
term, course or instructional program.
(According to Nima bhaskar)
Summated scale describes judgment about the merits of an already completed prom.
(According to A. J. Nico 1983)
To develop a new summated scale, there are five major steps (Sector, 1992):
Define the concept or characteristics you intend to measure. For example, you may want to
create a summated scale that measures academic honesty.
Design the summated scale, writing the questions and response choices.
Pilot test the summated scale and revise it, using the critiques of a small number of
respondents.
Administer the summated scale to 100-200 people and determine if the questions are highly
interrelated. If not, revise the scale and re-administer it.
ATTITUDE SCALE TYPES SUMMATED (LIKERT) SCALE
1. A likert-type scale, named for Rensis likert (1932) who developed this type of attitude
measurement.
2. To measure the social attitude, likert type scale is used
3. It uses only the definitely favourable and unfavourable statements. It excludes
intermediate opinions.
4. It consists of a series of statements which the respondent is to react. The respondent
indicates the degree of agreement or disagreement.
5. Each response is given a numerical score and the total score of a respondent is found
out by summing up his different scores for different purposes. This total score
indicates his position on the continuum
6. The Likert scale uses several degrees of agreement or disagreement , e.g. : strongly
approve, approve undecided, disapprove and strongly disapprove. These five points
will constitute the scale .each point of the scale carries a score . “Strongly approve” is
given the highest score(5 or +2) and “Strongly disapprove” is given the least score(1
or -2). Others point will have scores accordingly (i.e..5,4,3,2,1)
1 2 3 4 5
Strongly Approve Undecided Disapprove Strongly
approve disapprove
(4 or +1) (3 or 0) (2 or -1) (1 or -2)
(5 or +2)
E.g., statement 1: Prohibition should me made compulsory.
CONSTRUCTION OF A LIKERT SCALE:
The researcher gathers a large number of statements which clearly indicate favourable or
unfavourable attitude towards the issues in questions.
The questionnaire of the above five points with respects to a statement are administered to the
respondents who indicate the responses.
The response will imply various scores. The scores are consistently arranged either from the
highest to the lowest, or from the lowest to the highest.
By adding up the different scores of an individual, his total score is calculated (i.e.
Summation of different scores for different statements).
The researcher should identify the items which have a high discriminatory power. The
response are interpreted to determine which of the statement discriminate very clearly
between the high scores and low scores of the total scales.
It has to be ensured that the questionnaire is consistent. To achieve this items with low
discriminatory power for those having no significant correlation with total scores are
eliminated.
Example
It indicates degree of agreement or disagreement with each of the following statements about
marijuana by circling one of the following letters.
SA = strongly agree
A = Agree
U = undecided
D = disagree
SD = strongly disagree
Marijuana use corrupts the individual SA A U D SD
Its use can be beginning of a sad situation SA A U D SD
Marijuana does some people a lot of good SA A U D SD
People who are very favourable towards marijuana used would be expected to strongly agree
with favourable statements and strongly disagree with the unfavourable statements. They
would earn a high score on scale when the items scores are added together. Conversely
people with very unfavourable attitudes would be expected to strongly disagree with
favourable statements and agree with favourable statements, and would score low on the
scale. Note the importance of reverse scoring the negative items. A persons who strongly
disagrees with the statement “Marijuana use corrupts the individual” is expressing a positive
attitude towards marijuana use, hence the item is scored as a 5 rather than 1.
SELECTING THE FINAL ITEMS
Take the top and bottom quarters (which will be the people with the most and least
favourable attitudes)
For each group, calculate the average (mean) score for each individual item.
Keep only those items that distinguish the two groups. In other words both the high (very
favourable) and low (very unfavourable) scores rated an item in same way, that item is not
discriminating and should be dropped.
SCORING AND ANALYSIS: Sort the questionnaires from lowest to highest on the basis of
the total score (negative items scored in reverse direction)
After the questionnaire is completed each item may be analysed separately or in some cases
item responses may be summed to create a score for a group of items. Hence, Likert scales
are often called summative scales.
When treated as ordinal data , Likert response can be collated into bar charts, central
tendency summarised by the median or the mode (but not the mean), dispersion summarised
by the range across quartiles (but not the standard deviation), or analysed using non-
parametric test, e.g., Chi-square test, mann-whitney test, Wilcoxon signed-rank test, or
kruakal-wallis test.
ADVANTAGES OF LIKERT SCALE OVER THE THURSTONE
SCALE:
The method of construction of likert type scale is less cumbersome.
It supplies more precise and definite response towards an issue. The intermediate vague
points are absent in this scale.
The likert scale permits the revelation of several (five) degrees of agreement or disagreement
but turnstone scale are based on only two alternative responses i.e., acceptance or rejection.
Thus, likert scale so more informative and reliable than Thurston scale.
In likert scale, any item or statement empirically consistent with the statement may be
included. In turnstone scale, only the strictly related items are included. Thus, likert type
scale has a border area or a reference has also a method of checking internal consistency
which is conspicuous by its absence in turnstone scale.
DEFECTS IN SUMMATED (LIKERT) TYPE SCALES:
The judgement on the basis of total score, which is estimated by calculating the mean or
median, is not scientific. The total score values may be the same in many cases, but the
attitudes may be different towards an issues .
The scores on the likert type scale may be helpful for making an ordering of the people
scientific and objective basis.
There is no objective basis for expressing different degrees of agreement or disagreement.
However, despite some limitations, it remains an important ordinal scale
BIBLIOGRAPHY:
1. D. Elakkuvana Bhaskare Raj Nima Bhaskar, “TEXT BOOK OF NURSING
EDUCATION” First Edition 2013, publisher by emmess, page no- 242-245
2. B.T. Basavanthappa “NURSINGEDUCATION”, First Edition 2003, publisher by jaypee
brothers page no- 328-331.
3. Mathew V.K, “A NEW TEXTBOOK FOR NURSING EDUCATION”, Fourth Edition
2005, published by jaypee brothers page no- 366-368
4. 1971 (pp.118-146), San Francisco. CA : Jossey-Bass
5. Bollen, K. A. (1989). Structural equations with latent variables. New York: Wiley.
6. Bollen, K. A. & Lennox, R. (1991). Conventional wisdom on measurement: a structural
equation perspective, psychological Bulletin. 110.305-314.
