Module II

Classification of scales
It is very necessary to know when to use what scales for which reasons, another way to put it is - RATIONALE. When
implementing a test the rationale behind it must be concrete enough, for one to go forward with it.

So, here are a few tests based on certain functions it serves :

1. Method of Testing
2. Objective of Testing
3. Medium of Instruction
4. Time limit
 Method of Testing
Here, the method of testing refers to to whom it's being implemented on i.e.; the test-takers.

INDIVIDUAL TESTING

Individual testing involves administering a test to one person at a time. A trained examiner typically administers and observes
the test-taker closely throughout the assessment.

Uses: This approach is commonly used for tests that require detailed observation or assessments where direct interaction
and observation of responses are essential.
Advantages: Individual testing allows for in-depth observation of the test-taker’s behavior, responses, and thought
processes, enabling more tailored insights. It’s especially useful for assessments where nonverbal cues or performance
under direct supervision are important.

Limitations: It is time-consuming and costly, as it requires dedicated time from an examiner for each test-taker. Also,
individual tests might introduce examiner biases.

GROUP TESTING

Group testing allows multiple individuals to take a test simultaneously, typically in a more structured, less interactive format.
Instructions are given to the whole group, and each individual completes the test independently.

Uses: Group tests are often used for academic, aptitude, and standardized testing (e.g., CUET, NET) where large groups need
to be assessed at once. These tests are usually multiple-choice or have standardized formats to facilitate quick scoring. But,
they are not just limited to the above and can beyond to corporate , psychological and many more areas.

Advantages: Group testing is efficient, enabling large groups to be tested quickly and at a lower cost. It’s useful in settings
like schools or organizations where individual observation isn’t required.
Limitations: There’s less control over individual test-taker behavior, and it’s challenging to account for individual differences.
Some individuals may perform better or worse in group settings due to factors like test anxiety or distractions.
Objective of Testing
In psychology, different tests serve distinct purposes, each aligned with specific objectives based on what these assessments
aim to measure and understand about an individual. Here only two will be explore :

PERSONALITY TESTS

The primary goal of personality testing is to assess individual differences in characteristic patterns of thinking, feeling, and
behaving. It seeks to understand aspects of a person’s temperament, emotional responses, interpersonal interactions,
motivations, and behavioral tendencies.

Examples :

Personality testing is often used in clinical settings to inform treatment planning, in occupational settings to guide career
counseling, and in research to study personality traits and their influence on behavior.

INTELLIGENCE TESTS

Intelligence testing aims to measure cognitive abilities and intellectual potential, focusing on areas like reasoning, problem-
solving, memory, and abstract thinking. It seeks to quantify cognitive abilities and assess an individual’s intellectual strengths
and limitations.

Examples :

Intelligence testing is used in educational settings to assess learning abilities, in clinical settings to diagnose intellectual
disabilities or cognitive impairments, and in research to study the relationship between intelligence and other psychological
variables.
Medium of Instruction
The instruction in which tests can effect the test-taker, as culture might play a role in the way it is communicated, considering
this, tests of different mediums were created to cater to a different and diverse population.

Here are three of the many :

VERBAL TESTS

Verbal tests require the use of language for both instructions and responses. Test-takers must understand and respond to
verbal questions or prompts, making these tests language-dependent.

Examples :

Use: These tests are suitable for individuals who are fluent in the language of the test and have adequate reading or verbal
comprehension skills

NON-VERBAL TESTS

Non-verbal tests minimize or avoid the use of language for instructions and responses. Instead, they often use symbols,
pictures, or visual prompts that do not rely on specific language skills.

Examples :

Use: These tests are useful for assessing individuals with limited language proficiency, such as young children, individuals with
language disorders, or non-native speakers.

PERFORMANCE TESTS

Performance tests require test-takers to complete specific tasks or solve problems that demonstrate cognitive or motor skills,
often under timed conditions. These tasks are usually non-verbal but may involve understanding minimal instructions.

Use: Performance tests are useful for assessing cognitive abilities like problem-solving, perceptual speed, and motor
coordination, especially in individuals who may not perform well on language-based tests.
Time Limit
Time limit-based tests measure :

processing speed (how quickly information is processed)

attention and focus (ability to concentrate under time pressure)

cognitive efficiency (effectiveness in performing repetitive tasks)
decision-making under pressure
visual-motor coordination (accuracy and speed in physical tasks)
working memory (capacity to hold and manipulate information quickly).

POWER TESTS

Power tests are designed to measure the depth of an individual's ability. They typically do not have a strict or challenging time
limit, allowing test-takers ample time to complete the test. Instead, the questions or tasks increase in difficulty to assess the
individual’s maximum level of capability.

Examples :

The focus is on how well the test-taker can solve problems as they get more complex, rather than on how quickly they can
respond. Power tests aim to determine the upper limit of a person’s abilities in areas such as reasoning, knowledge, and
problem-solving.

SPEED TESTS

Speed tests are designed to measure how quickly an individual can complete a large number of relatively simple tasks within a
strict time limit. All tasks are usually of equal or similar difficulty, emphasizing speed and efficiency rather than problem-
solving depth.

Examples :

Speed tests assess how fast a person can process information or complete a task, often evaluating attributes like processing
speed, attention, and motor coordination. These tests are useful in contexts where quick responses are essential.
 ASSESSMENT VS MEASUREMENT

MEASUREMENT
Measurement refers to the process of assigning numerical values or scores to an individual’s traits, behaviors, or abilities,
following a specific set of rules. It provides quantitative data that can be analyzed objectively.

Example: If a person takes an IQ test and scores 120, that score is the result of measurement, indicating a numerical
representation of their cognitive ability.

ASSESSMENT
Assessment is the broader process of gathering, interpreting, and making judgments about information from various
measurements or observations. It often involves multiple tools, including tests, interviews, and observations, to make a
comprehensive evaluation.

Example: In a psychological assessment of a child’s learning abilities, a psychologist might use IQ tests, achievement tests, and
observational data from teachers. The psychologist then integrates these measurements with case history, mse and their own
observations and evaluations to understand the child’s strengths, weaknesses, and educational needs.
 LEVELS OF MEASUREMENT
In statistics, levels of measurement refer to the different ways variables can be measured or classified. These levels dictate the
type of analysis that can be performed on the data. There are four primary levels of measurement.

NOMINAL
The nominal level of measurement involves categorizing data into distinct, mutually exclusive categories. These categories
do not have a meaningful order or ranking.
They just label or name the entity, no other quantitative analysis can be done here.

Characteristics: Data is simply classified into groups that are qualitative in nature.

Example:

Gender: Male, Female, Non-binary

Football and cricket jerseys

Marital Status: Single, Married, Divorced, Widowed

ORDINAL
The ordinal level of measurement involves ordering or ranking data. The categories have a meaningful order, but the intervals
between them are not necessarily equal.

Characteristics: While data can be ranked, the difference between ranks is not standardized or consistent.
Example:

Here, you can tell which category is "better" or "worse," but the exact difference between them is not measurable.

Survey Ratings: Very dissatisfied, Dissatisfied, Neutral, Satisfied, Very satisfied

Class Rankings: 1st, 2nd, 3rd place
Education Level: High School, Bachelor's, Master's, Doctorate

INTERVAL
The interval level of measurement has ordered categories with equal intervals between them, but it lacks a true zero point.
This means you can measure the differences between values, but ratios are not meaningful.
Arbitrary zero is present here, so that it can be kept as a standard for measuring since it lacks an absolute zero.

Characteristics: There is a consistent interval between measurements, but there is no absolute zero.

Example:

Temperature in Celsius or Fahrenheit: 0°C or 0°F is not the absolute absence of temperature; it's just a point on the scale.
IQ Scores: The difference between an IQ of 100 and 110 is the same as the difference between 110 and 120, but there's no
true "zero" IQ score.

(P.s. Most psychological tests and scales fall here, since no psychological trait can ever be zero. )

RATIO
The ratio level is the highest level of measurement. It has all the characteristics of the interval level, plus a true zero point,
which allows for meaningful ratios.

There is an absolute zero present here, hence, no need for arbitrary one.
Ordered with equal intervals.
True zero point (zero indicates the absence of the attribute)

Characteristics: Data at the ratio level has a true zero point, and both differences and ratios between values are meaningful.

Example:

The presence of a true zero allows for meaningful ratios, making it possible to perform all mathematical operations (addition,
subtraction, multiplication, and division).

Weight: A person who weighs 80 kg weighs twice as much as someone who weighs 40 kg.
 RESPONSE SCALES
The response scale format refers to how questions are phrased and how responses are collected and assessed.

TYPES OF RESPONSE SCALES

1. Free response vs choice
2. Number of response options
3. Types of responses
4. Rating scales
5. Attitude scales

FREE RESPONSES (OPEN-ENDED)

In a free-response format, respondents answer questions in their own words, without pre-set options.

Characteristics: This open-ended format allows for detailed, nuanced responses and encourages personal expression,
elaboration, and insight.
Example: "Describe a time when you felt truly happy."
Use: Often used in exploratory research where in-depth understanding is sought, as well as in qualitative studies.

CHOICE (CLOSE-ENDED)
In a choice format, respondents select from a list of predefined answers, restricting responses to specified options.

Characteristics: This close-ended format enables easier quantification and analysis of responses, though it limits the range
of expression.
Example: "How happy do you feel today? (Very happy, Happy, Neutral, Unhappy, Very unhappy)"
Use: Frequently used in quantitative research to gather standardized data, allowing for easier statistical analysis.
NUMBER OF RESPONSE OPTIONS
1. DICHOTOMOUS RESPONSES

Provides two response options.

Characteristics: Simple and clear, often used for straightforward, binary answers.

Example:

"Do you exercise regularly? (Yes/No)"

"Is the statement true or false? (True/False)"

2. TRICHOTOMOUS RESPONSES

Provides three response options.

Characteristics: Offers slightly more nuance than dichotomous but still limited; often includes a neutral or uncertain option.

Example:

"Do you agree with the following statement? (Agree/Neutral/Disagree)"

"How do you feel about this product? (Like/Neutral/Dislike)"

Trichotomous responses allow for a middle-ground response, which can capture respondents who feel uncertain or neutral.

3. POLYCHOTOMOUS RESPONSES

Provides four or more response options.

Characteristics: Offers a wider range of choices, enabling more detailed responses and granularity.

Example:

"How satisfied are you with our service? (Very Satisfied, Satisfied, Neutral, Unsatisfied, Very Unsatisfied)"

"How often do you experience stress? (Never, Rarely, Sometimes, Often, Always)"
TYPES OF RESPONSES
Here, types refer to different methods of evaluating responses, often based on the type of response that the test requires.

OBJECTIVE SCORING
It is used when responses can be evaluated with clear, predefined criteria, leaving little room for interpretation. It is typically
applied to structured, closed-ended responses

Types of Responses: Multiple-choice questions, true/false questions, rating scales, or any format where answers are
predetermined.

Scoring Process: Objective tests are scored based on exact answers (e.g., correct/incorrect), and the scoring is consistent
regardless of who scores it.

Examples: IQ tests, standardized tests (like the NET or CUET), or personality inventories with forced-choice items (like the
Myers-Briggs Type Indicator).

(pl note : In objective scoring, the reliability of the results is often higher because there is minimal scorer bias. For example, if a
test item asks, "2 + 2 = ?," the response "4" is correct regardless of who evaluates it)

SUBJECTIVE SCORING
It is used when responses are open-ended or require interpretation, often associated with unstructured, open-ended
responses.

Types of Responses : Essay questions, open-ended questions, stories, drawings, and many more

Scoring Process: Subjective tests require raters to use judgment, often based on criteria or rubrics. This scoring can vary
between different raters.

Examples: Thematic Apperception Test (TAT), Sentence Completion Test (SCT) or Children's Apperception Test (CAT)
RATING SCALES
LIKERT SCALE

The Likert scale, developed by psychologist Rensis Likert in 1932, is one of the most popular rating scales for measuring
attitudes, beliefs, and opinions.

Structure of a Likert Scale

A Likert scale typically presents a statement to which respondents indicate their level of agreement or disagreement. It usually
has five to seven response options that range from strongly negative to strongly positive, with a neutral or middle option.

Characteristics of Likert Scales

Ordinal Data: Each point on the scale represents an ordinal value, indicating order but not precise intervals.
Measuring Attitudes and Opinions: Widely used for understanding respondent agreement with statements about
behaviors, attitudes, and opinions.
ATTITUDE SCALES
GUTTMAN SCALE

The Guttman scale, also known as the cumulative scale or scalogram, is based on the principle of cumulative ordering. It is
designed so that agreeing with a statement at a certain level implies agreement with all lower-level items.

Characteristics of the Guttman Scale

Hierarchical Ordering: The statements are arranged in a progressive order of difficulty or intensity.

Cumulative Response: If a respondent agrees with a particular statement, they are assumed to agree with all preceding (easier
or less intense) statements. For example, if a person agrees with a statement rated 4, they should also agree with statements
rated 1, 2, and 3.

Binary Responses: The responses are often binary (yes/no or agree/disagree), making it easier to assess the cumulative
agreement.

THURSTONE SCALE

It is also called the equal-appearing intervals scale, was developed by L.L. Thurstone. It’s used to measure attitudes and is
based on scaling statements to reflect the intensity or favorability of a respondent’s attitude toward a topic.

Characteristics of the Thurstone Scale

Interval Scaling: Statements are assigned values on a scale, such as 1 to 11, based on their perceived intensity. Statements
closer in value are assumed to reflect similar attitudes.

Judgment-Based Scoring: Experts or raters evaluate each statement’s intensity or favorability toward the topic to determine
scale values.

Non-Cumulative: Unlike Guttman scales, Thurstone scales don’t assume cumulative agreement, as they focus on pinpointing
specific attitudes or intensities independently.
REFERENCES
1. Committee on Psychological Testing, Including Validity Testing, for Social Security Administration Disability Determinations;
Board on the Health of Select Populations; Institute of Medicine. Psychological Testing in the Service of Disability
Determination. Washington (DC): National Academies Press (US); 2015 Jun 29. 3, Overview of Psychological Testing. Available
from: https://www.ncbi.nlm.nih.gov/books/NBK305233/
2. Hodges B. (2013). Assessment in the post-psychometric era: learning to love the subjective and collective. Medical teacher,
35(7), 564–568. https://doi.org/10.3109/0142159X.2013.789134
3. Kyriazos, T. A., & Stalikas, A. (2018). Applied Psychometrics: The steps of scale development and Standardization process.
Psychology, 09(11), 2531–2560. https://doi.org/10.4236/psych.2018.911145
4. Cohen, R. J., & Swerdlik, M. E. (2018). Psychological Testing and Assessment: An introduction to tests and measurement.
http://ci.nii.ac.jp/ncid/BA19098412