Re-establishing Reliability of an existing psychological Test-

General self – esteem scale

Submitted by

Second Year [Link] Psychology (B batch) Students

Submitted to

Dr. Vandana V S , Assistant professor

Submitted on

___________________________

Verified by

__________________________
AIM :
To determine the consistency of a test using reliability methods

INTRODUTION :
Psychologically Testing

Definition

Psychological testing is a core method in psychology that involves the systematic use of standardized
instruments to measure behaviour, cognitive abilities, personality traits, and emotional functioning. It provides a
structured way to gather objective data about individuals, allowing psychologists to make informed decisions in
clinical, educational, organizational, and research contexts.

According to Anastasi & Urbina (1997) a test is defined as “an objective and standardized measure of a sample
of behaviour.” This means that tests are designed to assess specific psychological constructs such as
intelligence, aptitude, personality, interests, and emotional functioning under controlled conditions.

Similarly, Kaplan & Saccuzzo (2017), emphasize that psychological tests are not merely tools for measurement
but also scientific procedures designed to predict, classify, and understand human behavior. They argue that
well-constructed tests provide both reliability (consistency of results across time and situations) and validity
(accuracy in measuring the intended construct), which are essential for their usefulness.

To be effective and meaningful, a test must possess certain characteristics:

Objectivity

The scoring of a psychological test must be free from personal bias or examiner influence. Objectivity ensures
that two different examiners will assign the same score when evaluating the same performance.

Standardization

A test should be administered and scored under uniform [Link] allows comparison of an
individual’s score with normative data since all individuals are measured in the same way.

Reliability

The test must yield consistent results across time, items, or raters.A reliable test reduces measurement errors and
ensures stability in outcomes (e.g., similar IQ scores on repeated administrations).

Validity
A test must measure what it is intended to measure. Without validity, test results are meaningless even if the test
is reliable.

Norms

Psychological tests must have norms or reference groups to interpret individual scores meaningfully. Norms as
statistical data that allow comparison of a person’s performance with that of a representative sample.

Practicality

Beyond technical qualities, a test should be practical in terms of cost, time, ease of administration, and scoring.

Self esteem Scale

Definition
Self-esteem refers to an individual’s overall evaluation of their worth or value. It is an important aspect of
personality that influences motivation, behaviour, relationships, and mental health. People with high self-esteem
generally feel confident, competent, and valuable, whereas those with low self-esteem may struggle with
selfdoubt, insecurity, and vulnerability to psychological distress.

A self-esteem scale is a psychological tool designed to measure an individual’s overall sense of self-worth or
personal value. Self-esteem reflects how people evaluate themselves whether they see themselves as competent,
worthy, and capable, or inadequate and unworthy.

Rosenberg self esteem scale

The Rosenberg Self-Esteem Scale is the most widely used measure of self-esteem in psychology. It was
developed by Morris Rosenberg . It is a self-report inventory consisting of 10 items, designed to assess an
individual’s overall evaluation of self-worth. The scale uses a 4-point Likert response format ranging from
“strongly agree” to “strongly disagree.” Five of the items are positively worded while the other five are
negatively worded, which are reverse scored. The total score ranges from 0 to 30, with higher scores indicating
higher self-esteem; scores between 15 and 25 are considered normal, scores below 15 suggest low self-esteem,
and scores above 25 indicate high self-esteem. The RSES has demonstrated strong reliability, with Cronbach’s
alpha values typically ranging from 0.77 to 0.88, and good test–retest reliability, showing that it provides stable
results over time. It also has strong validity, correlating well with related constructs such as depression, anxiety,
and life satisfaction, and it has been validated across various cultures and populations.

Scoring

Positive items are scored directly. Negative items are reverse scored. Higher scores indicates higher self-esteem
and lower scores shows low self-esteem, which may indicate self-doubt, insecurity, or vulnerability to mental
health difficulties. The Rosenberg Self-Esteem Scale has been found to have high reliability and validity across
cultures and populations.

The self esteem scales can be used in the field of

Clinical psychology to assess self-worth in patients with depression, anxiety, or adjustment issues.

Educational settings to study self-concept in adolescents or students.

Organizational psychology to examine links between self-esteem, job satisfaction, and performance.

Research to explore how self-esteem relates to personality, motivation, or social behaviour.

OBJECTIVES:

1. To examine the reliability of the measurement instrument through multiple approaches,

including:

• Split-half reliability: to assess the internal consistency by correlating scores from two halves of
the same test.

• Test-retest reliability: to determine the stability of the test scores over time by administering
the same instrument on two different occasions.

• Internal consistency reliability: to evaluate the degree of interrelatedness among items within
the test.

• Cronbach’s alpha coefficient: to provide a quantitative estimate of the internal consistency

reliability of the instrument.

2. To compare the present reliability results with previously reported reliability indices in order to
determine whether the current findings align with established evidence or reveal variations due to sample
characteristics, testing conditions, or methodological differences.

3. To ensure the psychometric soundness of the tool, thereby confirming its suitability for further
research and practical applications in the relevant field.
METHOD:

participants:

• The study included 52 undergraduate psychology students.

• Among them, 9 were boys and 43 were girls.
• The participants’ ages ranged from 18 to 25 years.
• Random sampling was used to select the participants.
• All participants took part voluntarily.
• Informed consent was obtained from every participant before the study began.
• Participants were assured of the confidentiality of their responses.

INSTRUMENTS:

1. Rosenberg Self-Esteem Scale (RSES; Rosenberg, 1965):

This is a 10-item questionnaire used to measure self-esteem. It uses a 4-point scale from Strongly
Agree (1) to Strongly Disagree (4).
Five items are positive and scored directly, while the other five are negative and scored in reverse.
The total score ranges from 10 to 40. Higher scores mean higher self-esteem.

2. Demographic Information Sheet:

A short form prepared by the researcher to collect details like age, gender, and academic background.

PROCEDURE:

• First, participants were informed about the purpose of the study.

• They were told that their responses would remain confidential.
• After giving informed consent, they filled out a demographic form.
• Then, they completed the Rosenberg Self-Esteem Scale.
• The entire process took about 10–15 minutes.
• Same instructions were given to all participants.
• They answered the questionnaire individually under the researcher’s supervision.
• The responses were scored according to Rosenberg’s scoring guidelines
STASTICAL ANALYSIS:

1. The collected data were entered into SPSS for analysis.

2. Karl Pearson’s correlation coefficient was calculated.
3. The purpose of this analysis was to find the reliability of the test.

RESULT :

Table 1 : Reliability data for Self-Esteem scale

[Link]. Reliability Coefficient Interpretation

1. Cronbach’s Alpha 0.06 Very low internal

consistency

2. Split half reliability 0.10 Very low internal

Consistency

3. Test – retest reliability 0.05 Poor temporal stability

Table 1 shows the reliability obtained using three methods—Cronbach’s alpha, split-half, and test-retest. The
reliability coefficients obtained were 0.06, 0.10, and 0.05, respectively. All these values are below the
acceptable standard of 0.70, indicating very low internal consistency and poor temporal stability of the
SelfEsteem Scale.

DISCUSSION :
The aim of the experiment was to examine the reliability of the measurement instrument through multiple
approaches. The resulting scores consistently show that the instrument lacks reliability across all approaches.
The internal consistency, measured by Cronbach's alpha, was α = 0.06. Given that a higher alpha indicates
better internal consistency and coefficients below 0.50 are considered unacceptable, this score suggests a
critical failure of the scale items to correlate with one another.

Similarly, the Split-Half reliability yielded a correlation of r = 0.10. Since a higher correlation indicates better
internal reliability, it shows minimal correlation between the two halves of the test. This implies that the items
are not functioning uniformly and may contain inconsistencies in wording or content.

The Test-Retest correlation for temporal stability was r = 0.05. Considering that reliability is deemed weak for
scores below 0.80, this near-zero value indicates that participant scores are completely unstable and vulnerable
to random error across separate administrations.

Low reliability could have resulted from several factors. The items in the Self-Esteem Scale might have been
poorly worded, ambiguous, or not clearly related to the intended construct, leading to inconsistent responses.
Additionally, participants might not have been attentive or motivated during testing, introducing random error.
External factors such as variations in testing environment or mood changes between sessions could also have
influenced the results, reducing stability and internal consistency.

Overall, the combined evidence from all three reliability assessments indicates that the Self-Esteem Scale is
unreliable. It fails to meet the basic psychometric standards for internal consistency and temporal stability.

CONCLUSION :

The findings clearly indicate that the Self-Esteem Scale demonstrates very low reliability across all methods
used—Cronbach’s alpha, Split-Half, and Test-Retest. The instrument therefore fails to provide consistent and
dependable measurements, suggesting that it requires substantial revision and refinement before being used for
further research or assessment purposes.
REFERENCE

Anastasi, A., & Urbina, S. (1997). Psychological testing (7th Eda)

Prentice Hall.
Kaplan, R. M., & Saccuzzo, D. P. (2017). Psychological testing:
Principles, applications, and issues (9th ed.)
Cengage Learning.
Rosenberg, M. (1965). Society and the adolescent self-image.
Princeton University Press.