1

Level A: Basic Psychometrics

Chapter 1: Introduction To Psychometrics

Professor Muhammad Kamal Uddin

(PhD, Kyushu University, Japan)
Department of Psychology
University of Dhaka, Bangladesh
Phone: 01713456644, Email:kamaluddin67@hotmail.com
 Preface
Whether we like it or not, testing is pervasive in the modern world. It is difficult to imagine any aspect of life in
which testing is not involved. Of course, testing is widely used in education, psychology, employment settings,
and certification for various professions.
People may be involved in testing for a variety of reasons that can be classifies as follows:
1. To develop tests and study their properties,
2. To select and administer tests and interpret their results, and
3. To use tests in research or evaluation studies.
These audiences differ considerably in what they need to know about measurement theory and the depth at
which they need to know it.

Given this, I could make (and have made; see Bandalos & Kopp, 2012) the argument that some
knowledge of the theory and practice of testing is essential for an informed citizenry.
Bangladesh Psychometric Society (BPS) 2
 Preface…
Unfortunately, even in professions such as teaching, in which knowledge of
testing is clearly essential, the majority of training programs provide little
instruction in this area (Plake, Impara, & Fagan, 1993; Schaefer & Lissitz,
1987; Wise & Conoley, 1993). Aiken, West, and Millsap (2008) reported that
fewer than half of the professors teaching in graduate-level psychology
departments felt their students had adequate knowledge of even the most basic
measurement concepts.

Bangladesh Psychometric Society (BPS) 3

 Why

How What

Psychometrics

When Who

Where

4
 Contents
1. Common Terminologies
2. What is Psychometrics?
3. Why Psychometrics Matters?
4. Observable Behavior and Unobservable Psychological Attributes
5. Assumptions in Psychological Testing and Assessment
6. Definition of Psychological Tests
7. Types of Psychological Tests
8. Principles of Psychological Testing
9. Who Uses Psychological Tests and for What Purposes
10. Why Control the Use of Psychological Tests?
11. Challenges to Measurement in Psychology
12. Psychometrics as a Profession
13. Guidelines of Evaluating a Psychological Test
5
 Common Terminologies
 Psychometry
The measurement of psychological characteristics.
 Psychometrics
The science of Psychometry, i.e., evaluating the characteristics of tests
designed to measure psychological attributes of people.
 Psychometrists
Persons trained in using psychometric tools under the guidance of a Psychologist
or Psychometrician
 Psychometricians
Persons trained in measurement theory aimed toward psychological
measurement; they propose and evaluate methods for developing new tests and
other measurement instruments.
 Psychological Assessment
 Measurement
 Psychological Test and Testing
 Survey 6
 What is Psychometrics?
 The branch of psychology that deals with the design, administration, and interpretation of
quantitative tests for the measurement of psychological variables such as intelligence,
aptitude and personality traits.
 Psychometrics is the study of the operations and procedures used to measure variability
in behavior and to connect those measurements to psychological phenomena.
 It is the science concerned with evaluating attributes of psychological tests.
 It has 3 attributes: (1) type of information generated by the psychological tests, (2) the
reliability of data from psychological tests and (3) issues concerning the validity of data
obtained from the tests.

Bangladesh Psychometric Society (BPS) 7

 What is Psychometrics?

Psychometrics is a field of study concerned with the theory and technique

of psychological measurement. As defined by the US National Council on
Measurement in Education (NCME), psychometrics refers to psychological
measurement. Generally, it refers to the field in psychology and education that
is devoted to testing, measurement, assessment, and related activities.

Bangladesh Psychometric Society (BPS) 8

 Psychological Assessment

It can be defined as the gathering and integration of psychology-related

data for the purpose of making a psychological evaluation,
accomplished through the use of tools such as tests, interviews, case
studies, behavioral observation, and specially designed apparatuses and
measurement procedures.

Bangladesh Psychometric Society (BPS) 9

 Tools of Psychological Assessment
1. Psychological test
2. Interview
3. Portfolio
4. Case History Data
5. Behavioral Observation
6. Role-Play Tests
7. Computers as Tools
8. Other Tools

Bangladesh Psychometric Society (BPS) 10

A Taxonomy of Psychological Assessment

11
 Why Psychometrics Matters?
1. Whether you wish to be a practitioner of behavioral science, a behavioral researcher or a
sophisticated member of modern society, your life is likely to be affected by psychological
measurement.

2. Whether you are a clinical, counseling, developmental, educational, industrial, or school

psychologist, a human resources director or a teacher, your work might require to make decisions
on the basis of scores obtained from some kind of psychological test.

3. When a patient responds to a psychopathology assessment, when a student completes a test of

cognitive ability, or when a job applicant fills out a personality inventory, there is an attempt to
measure some type of psychological characteristics.

4. Without a solid understanding of the basic principles of psychological measurement, test users
risk misinterpreting or misusing information.
12
 Why Psychometrics Matters?...
5. Such misinterpretation or misuse might harm patients, students, clients, employees, and
applicants, and it can lead to lawsuits for the test user.

6. Proper test interpretation and use can be extremely valuable for test users and beneficial for test
takers.

7. Whether your area is psychology, education or other behavioral sciences, measurement is at the
heart of your research process.

8. If something is not measured well, it cannot be studied with any scientific validity.

9. If you wish to interpret your research findings in a meaningful and accurate manner, then you
must evaluate critically the data.

10. Given the widespread use and importance of psychological measurement, it is crucial to
understand the process, properties, and other aspects of psychological measurements.
13
Observable Behavior and Unobservable Psychological Attributes

• Psychological tests are used as instruments to measure observable events in the

physical world.

• In the behavioral sciences, these observable events are typically some kind of
behavior.

• Psychologists measure a behavior because they are interested in that specific behavior
in its own right.

• For example, some psychologists have studied the way facial expressions affect the
perception of emotions.

Bangladesh Psychometric Society (BPS) 14

Observable Behavior and Unobservable Psychological Attributes…

• Behavioral scientists observe human behavior as a way of assessing unobservable

psychological attributes such as intelligence, depression, knowledge, aptitude,
extroversion or ability.

• In such cases, they identify some type of observable behavior that represents the
particular unobservable psychological attribute, state or process.

• They measure the behavior and try to interpret those measurements in terms of the
unobservable psychological characteristics reflected in the behavior.
• For example, identifying greater working memory status between two persons.

Bangladesh Psychometric Society (BPS) 15

 Observable Behavior and Unobservable Psychological Attributes…

• As there is no way to observe directly working memory, it requires an inference—an

overt behavior, the number of recalled digits, is systematically related to an
unobservable mental attribute (working memory).

 First, an inference is made.

 Second, for interpretation, the recall task had to be theoretically linked to the
unobservable mental attribute.

• Psychologists turn to theoretical concepts to explain differences in people’s behavior,

referred as hypothetical constructs or latent variables. The operations used to
measure these constructs are called operational definitions.
16
 Assumptions in Psychological Testing and Assessment

 Assumption 1: Psychological traits and states exist.

 Assumption 2: Psychological traits and states can be quantified and measured.
 Assumption 3: Test–related behavior predicts non–test–related behavior.
 Assumption 4: Tests and other measurements techniques have strengths and weaknesses.
 Assumption 5: Various sources of error are part of the assessment process.
 Assumption 6: Testing and assessment can be conducted in a fair and unbiased manner.
 Assumption 7: Testing and Assessment Benefit Society.

Bangladesh Psychometric Society (BPS) 17

 Psychological Tests
According to Cronbach (1960) – ―A psychological test is a systematic procedure for
comparing the behavior of two or more people‖.
According to Anstey (1966) – ―Psychological tests can be defined as devices and
techniques for the quantitative assessment of psychological attribute of an individual‖.
According to Anastasi (1969) – ―A psychological test is an objective and standardized
measure of a sample of behavior‖.
According to Gregory (1996) – ―A test is a standardized procedure for sampling behavior
and describing it with categories or score‖.
According to Anastasi and Urbina (1997) – ―A psychological test is essentially an
objective and standardized measure of a sample of behavior‖.
18
 Psychological Tests…
In its Report of the Task Force on Test User Qualifications, the APA (2000)
defines a psychological test as ―a measurement procedure for assessing
psychological characteristics in which a sample of an examinee’s behavior is
obtained and subsequently evaluated and scored using a standardized
process‖

According to AERA, APA, and NCME (2014) –―a device or procedure in

which a sample of an examinee’s behavior in a specified domain is obtained
and subsequently evaluated and scored using a standardized process‖.
19
Psychological Assessment, Psychological
Tests, Measurements, and Surveys

20
Psychological Assessment, Psychological
Tests, Measurements, and Surveys…

21
Psychological Assessment, Psychological
Tests, Measurements, and Surveys…

22
Psychological Assessment, Psychological
Tests, Measurements, and Surveys…

Bangladesh Psychometric Society (BPS) 23

 Types of Psychological Tests
 Tests may be classified according to their content, how they were constructed, what
they were designed to measure or be used for and even how they are administered,
scored and interpreted.
 Tests based on content: achievement tests, aptitude tests, intelligence tests, personality
tests, attitude surveys.
 Tests based on the type of response required: open-ended tests and close-ended tests.
 Psychological tests are categorized as either criterion referenced or norm referenced.
 The words- measure, instrument, scale, inventory, battery, schedule and assessment- all
are used in different contexts as synonyms for the word ‘test’.

Bangladesh Psychometric Society (BPS) 24

 Subject Tests
The Twentieth Mental Measurements Yearbook (MMY; Carlson, Geisinger, & Jonson, 2017)
classifies thousands of tests into 17 major subject categories:

25
Types of Psychological Tests

Bangladesh Psychometric Society (BPS) 26

 Creativity

Intelligence
Cognitive
Dimension
Aptitude

Achievement
1. Behavioural Psychomotor
Dimension Dimension
Interest

Values
Affective
Dimension
Attitude

Personality 27
4. Mode of Administration
Individual Testing 5.
Mode of Scoring
Group Testing

Paper-Pencil Testing

Computer Assisted Testing Hand Scoring Machine Scoring

6. 7.
Criterion of Mode of
Scoring Interpretation

Norm- Criterion-
Objective Subjective Referenced Referenced
Interpretation Interpretation

28
 Speed Test

9. Rate of Response

Power Test

29
 Comparison of Criterion-Referenced
and Norm-Referenced Measures
Although criterion-referenced and norm-referenced measures are developed so that scores will be
interpreted differently, they have characteristics in common as well as distinct differences. Common
characteristics include the following according to Gronlund (1988, p. 4).

1. Both require specification of the achievement domain to be measured.

2. Both require a relevant and representative sample of test items.
3. Both may use the same types of test items.
4. Both have the same rules for item writing (except for item difficulty).
5. Both are judged by the same qualities of goodness (reliability and validity), although there are
sometimes differences in statistical methods employed.
6. Both are useful in the measurement of health variables and in educational measurement.

30
 Comparison of Criterion-Referenced
and Norm-Referenced Measures…
Criterion-Referenced Measures Norm-Referenced Measures
Interpretation Absolute interpretation. Amount of Relative interpretation. Amount of
attribute measured is specified based attribute measured is compared to
Type of

on known placement in a category others for interpretation.

or by percent.
Content

Used to categorize attributes or for Used primarily to obtain scores for

mastery testing. purposes of comparison.

Focuses on a delimited domain or Typically focuses on a large domain,

Measurement

subdomains with a relatively with a few items measuring each

Type of

large number of items measuring task, objective, category, or subscale.

each task, objective, category, or
subscale.

31
 Comparison of Criterion-Referenced
and Norm-Referenced Measures…
Criterion-Referenced Measures Norm-Referenced Measures
Purpose of
Testing
To assess the amount of an attribute or To spread out objects or persons
material known by each in isolation of across a continuum on the
others. attribute measured.
Distribution

Distribution of scores vary, often are Normal distribution of scores is

Measure or Test of Scores

not normally distributed. expected around the mean.

Homogeneous, well-defined item More heterogeneous and relatively

Structure of

content matched to each domain, long subtests or subscales.

subdomain, or subscale.

Students know the content to Students have little or no idea of

of questions
Knowledge
of nature

if testing

expect test questions to address. nature of content to expect in

questions.
32
 Standardized Versus Non-standardized Measures
Broadly defined, a standardized measure, first proposed by Kelley (1914), is one that is constructed, administered,
scored, and interpreted in a prescribed, precise, and consistent manner in order to reduce external influences that
compromise reliability (Nunnally & Bernstein, 1994). The defining characteristics of a standardized measure refer
to the properties of the measure itself and the way it was developed, rather than to the nature of the entity being
measured (Nunnally & Bernstein, 1994). In order to be considered standardized, a measure must be carefully
developed, rigorously tested before general use, consistently administered and scored, and interpreted on the basis
of established norms or criteria. Standardized tests are constructed by test construction specialists, usually with the
assistance of curriculum experts, teachers, and school administrators. They may be used to determine a student’s
level of performance relative to (a) the performance of other students of similar age and grade or (b) a criterion,
such as state academic standards, or the new Common Core State Standards. When standardized tests are used to
compare performance to students across the country, they are called standardized norm-referenced tests, and when
they are used to determine whether performance meets or exceeds criteria like state standards, they are called
standardized criterion-referenced tests. 33
 Standardized Versus Non-standardized Measures…

As used in this text, the term ―standardized‖ is applied to measures that have four essential
characteristics:
1. A fixed set of items or operations designed to measure a clearly defined concept,
attribute, or behavior;
2. Explicit rules and procedures for administration and scoring;
3. Provision of norms to assist in interpreting scores;
4. An ongoing development process that involves careful testing, analysis, and revision in
order to assure high technical quality.

34
 Standardized Versus Non-standardized Measures…
Standardized Measures Non-standardized Measures
Involves input of experts; method of construction is designed Advantage May be carried out in situations in which
to enhance technical quality, reliability, and validity; time and resources are limited; short span of time is
Construction

procedure used in construction and testing is usually required between planning and use of the measure.
described.
Costly, time-consuming; requires adequate resources. Disadvantage Construction procedure is variable and
does not necessarily assure high quality; procedure
generally is not described in detail; amount of expert
input is variable and may be unknown.
Measures attributes or behaviors that are common to a Advantage Well-adapted to specialized needs and emphasis;
variety of settings and situations; is applicable to many flexibility allows adaptation to changes in materials
settings; reflects widespread consensus rather than localized or procedures; allows inclusion of controversial or
emphasis; is applicable across time and locale; is well timely information.
Content

defined and fixed, allowing consistent comparison;

parameters are usually specified.
Inflexible; cannot be adapted to local or specialized Disadvantage May reflect unique views or biases that are not
situations; may reflect consensus views that are incongruent deemed relevant by recognized authorities. Time-
with specialized needs and purposes; precludes innovative, and situation-specificity precludes widespread use.
controversial, or time-bound material.

35
 Standardized Versus Non-standardized Measures…
Standardized Measures Non-standardized Measures
Reliability (internal consistency and test-retest) is high, Advantage Technical properties to be optimized are determined
yielding stable results; procedures to establish reliability and based on purposes of the measure (e.g., qualitative
Psychometrics

validity are reported, so are known to the user; items and studies).
operations have high discriminating power.
Stability of scores results in insensitivity to minor Disadvantage Technical properties frequently are unknown and
fluctuations that may be desirable to measure. may be highly variable, dependent on the
construction procedures used.
Administration and Scoring

Established procedures provide consistency, giving Advantage Procedures can be developed based on specific
comparable results; effects of different testing conditions and needs and resources; flexible procedures permit last-
environments are minimized; centralized or automated minute alterations; local and/or hand scoring is cost-
scoring is cost-efficient for large-scale efforts. efficient for small samples; time lag between
administration and scoring is determined by the user.
Inflexibility precludes altering to fit individual circumstances Disadvantage Consistency between different
and resources; may be costly and time-consuming; administrations of the same measure is variable;
scheduling of administration and return of scored results may different rules may be applied in scoring, thus
be controlled externally. yielding incomparable results.

36
 Standardized Versus Non-standardized Measures…
Standardized Measures Non-standardized Measures
Scores can be uniformly compared with norm Advantage Comparisons and interpretations can be
groups, often at the national level; geared to specific needs and unique
Interpretation of Scores

interpretation is likely to be consistent across circumstances; amenable to situations for

applications; explicit instructions may be which comparison to a defined group is
provided to facilitate interpretation. not an appropriate way to assign meaning
to a score.
National norms may be inappropriate for Disadvantage No established basis for interpretation
unique purposes; utility for decision making in exists; consistency and accuracy of
specific settings is variable; inappropriate for interpretation is variable, depending on
purposes that do not require comparison with the procedure used and the statistical skill
the status quo. of the interpreter.

Bangladesh Psychometric Society (BPS) 37

 Construction of Standardized Measures
Standardized measures are constructed by following a number of sequential steps. Although there is some variation, the following
procedure is generally used (Johnston & Pennypacker, 2008; Nunnally & Bernstein, 1994):

1. Objectives, specifications, and a blueprint are developed.

2. Items are written and operations identified.
3. The items are pretested and analyzed using item statistics.
4. Acceptable items are assembled into a preliminary form (or preliminary equivalent forms) of the measure.
5. The preliminary form of the measure is experimentally administered to criterion groups of examinees to determine or verify the
adequacy of item limits and instructions, difficulty level, discriminating power, reliability, and validity.
6. Revisions are made to eliminate items or operations that are unnecessary, problematic, or do not contribute to the measure’s reliability
and validity.
7. A final form of the measure is assembled.
8. Uniform mechanisms for administration and explicit instructions for scoring are established.
9. The final form of the measure is administered to carefully selected referent groups in order to develop norms.
10. The final version of the measure, a manual, and supplementary materials are made available for use.

38
 Questions to Guide Evaluation of Standardized Measures
1. Purpose: Are the stated purpose and recommended uses for the measure congruent with the purpose for which it will be
employed? Will the measure yield the desired information?
2. Conceptual basis: Is the theoretical model that guided the development of the measure identical to (or, at the very least,
compatible with) the model being employed? What are the assumptions and potential biases underlying the measure?
Are the values inherent in the development of the measure congruent with those that are to be maximized in the current
situation?
3. Content: Is the content of the measure appropriate without modification for the use intended? Is it up to date? Is the
content appropriate for the ages, reading abilities, and frames of reference of potential subjects?
4. Technical quality: What types of reliability and validity have been established? What is the nature of evidence
supporting the reliability and validity of the measure? How was the measure developed and tested? What were the
qualifications of the individuals involved?
5. Norms: How were norms established? How was the referent group selected and what are its characteristics? Are the
norms appropriate and sufficiently detailed for use as a basis of comparison? Are the norms clear and easily
interpretable? Are they up to date? 39
Questions to Guide Evaluation of Standardized Measures
6. Administration: Are clear and explicit instructions provided for administration? What resources are required
for administration? How easy, costly, and time-consuming is the administration? Is training required? What
about subject burden?
7. Scoring: Is the measure hand- or machine-scored? What costs or special equipment are required? How likely
are errors to occur in scoring? What is the time required for scoring?
8. Interpretation: Can scores be easily and consistently interpreted? Are materials provided to aid in
interpretation?
9. Cost: What is the cost for employing the measure, including purchase, administration, and scoring costs?
What is the cost (if any) to subjects? Are the costs proportional to the relative importance of the information
that will be obtained?
10.Critical reviews: What are the evaluations provided by others who have used the measure? What problems,
strengths, and weaknesses have been identified?
40
 Stages in the Development and Validation
of Criterion-Referenced Measures
1. Specify the conceptual model of the measure.
2. Specify the purpose(s) of the measure.
3. Explicate objective(s) or the domain definition.
4. Prepare test specifications including:
a. Method of administration
b. Number or proportion of items that will focus on each objective or subscale
c. Type of items and how they will be created
d. Test restrictions and givens
e. General scoring rules and procedures
5. Construct the measure including:
a. Develop a pool of items or tasks matched to the objective(s) or subscales
b. Review items or tasks to determine content validity and their appropriateness
c. Select items after editing or deleting poorly developed items from the item pool
d. Assemble the measure (including preparation of directions, scoring keys, answer sheets, etc.)
6. Set standards or cut score for interpreting results.
7. Field-test or administer the measure.
8. Assess reliability and validity of measure (including determining the statistical properties of items,
and deleting and revising items further based on empirical data).
41
 Principles of Psychological Testing
By principles of psychological testing we mean the basic concepts and fundamental
ideas that underlie all psychological and educational tests.
Reliability
• Reliability refers to the accuracy, dependability, consistency, or repeatability of test
results.
• In more technical terms, reliability refers to the degree to which test sores are free of
measurement errors.
Validity
• Validity refers to the degree to which a certain inference or interpretation based on a
test is appropriate.
• Another principle of psychological testing concerns how a test is created or
constructed.
42
 Names and Web Addresses of Test Publishers
Publisher Website Popular Published Tests

Educational www.ets.org  Graduate Record Examination General Test and Subject Tests
Testing Service  SAT Reasoning Test and SAT Subject Tests
 Test of English as a Foreign Language
 Graduate Management Admission Test

Pearson www.pearsonassessments.com  Bar-On Emotional Quotient Inventory

 Bayley Scales of Infant and Toddler Development, Third Edition
 Behavior Assessment System for Children, Second Edition, Behavioral and
Emotional Screening System
 Bender Visual-Motor Gestalt Test, Second Edition
 Watson–Glaser Critical Thinking Appraisal

Hogan www.hoganassessments.com  Hogan Personality Inventory

Assessment  Hogan Development Survey
Systems  Hogan Business Reasoning Inventory
 Motives, Values, Preferences Inventory 43
 Names and Web Addresses of Test Publishers…
Publisher Website Popular Published Tests
PAR www.parinc.com  Self-Directed Search
 NEO Personality Inventory
 Personality Assessment Inventory

Psytech International www.psytech.com  Occupational Interest Profile

 Clerical Test Battery
 Values & Motives Inventory

PSI www.psionline.com  Customer Service Battery

 Firefighter Selection Test
 Police Selection Test

Hogrefe www.hogrefe.co.uk  Rorschach Test

 Trauma Symptom Inventory
 Work Profile Questionnaire Emotional Intelligence Questionnaire

University of Minnesota www.upress.umn.edu  Minnesota Multiphasic Personality

Press Test Division

Wonderlic www.wonderlic.com  Wonderlic Personnel Test

44
45
46
 Who Uses Psychological Tests and for What Purposes
Educational Settings

Who Where Why

Administrators Primary schools To select students into schools

Teachers Secondary schools To award scholarships
School psychologists Colleges To place students in programs
Career counselors Universities To measure student learning
To identify problems
To identify career interests

47
 Who Uses Psychological Tests and for What Purposes…
Clinical Settings

Who Where Why

Clinical psychologists Mental health clinics To diagnose disorders

Psychiatrists Residential programs To plan treatment programs
Social workers Private practices To assess treatment outcomes
Counseling psychologists To counsel and advise
Licensed professional counselors
Marriage and family counselors

48
 Who Uses Psychological Tests and for What Purposes…

Organizational Settings

Who Where Why

Human resources professionals Organizations To make hiring decisions

Industrial/organizational practitioners Consulting companies To determine training needs

Consulting practices To evaluate employee performance

49
 Why Control the Use of Psychological Tests?
There are two principle reasons for controlling the use of psychological tests:

1. To ensure that the test is given by a qualified examiner and that the scores are
properly used;

2. To prevent general familiarity with the test content, which would invalidate the test.

Qualified Examiner:

The need for qualified examiner is evident in each of the 3 major aspects of the testing
situation:

1. Selection of the test

2. Administration and scoring

3. Interpretation of scores
50
 Why Control the Use of Psychological Tests?...

Role of the Test User:

 The test user is anyone who uses test scores as one source of information in
reaching practical decisions.
 The test user may or may not be the examiner who administers and scores the test.
 Examples of test users are teachers, counselors, administrators in school systems,
and personnel workers in industry or government.
 Most criticism of tests are directed, not to intrinsic features of the test, but to
misuse of test results by inadequately qualified users.
 Some misuse stem from a desire for shortcuts, quick answers and simple routine
solutions for real life problems.

51
 Why Control the Use of Psychological Tests?
Security of Test Content and Communication of Test Information
• Test content clearly has to be restricted in order to forestall deliberate efforts to
fake scores.
• Ensuring the security of specific test content need not-and should not- interfere
with the effective communication of testing information to takers, concerned
professionals, and the general public.
• Such communication serves several purposes as follows:

Bangladesh Psychometric Society (BPS) 52

 Why Control the Use of Psychological Tests?...
1. First, it tends to dispel any mystery that may have become associated with testing and
thereby helps to correct prevalent misconceptions about what tests are designed to do and
what their scores mean.
2. A second type of communication is concerned with the technical procedures whereby
particular tests are constructed and evaluated; they present the relevant data about reliability,
validity, and other psychometric properties of the test.
3. A third purpose of test communication is to familiarize test takers with testing procedures,
dispel anxiety, and ensure that each will perform to the best of her or his ability.
4. A fourth and highly significant type of communication is the feedback provided to test
takers regarding their own performance on any test they have taken.

Bangladesh Psychometric Society (BPS) 53

 Challenges to Measurement in Psychology
• One of the challenges is to try to identify and capture the important aspects of
human psychological attributes in a single number. Participant reactivity is another
such challenge.
• 2nd challenge is that, people collecting the behavioral data can bring biases and
expectations to their task. There may be observer or scorer bias also.

• The measures used in the behavioral sciences tend to differ from those used by
physical scientists is 3rd important aspect.
• 4th challenge is score sensitivity—the psychological process may not sensitive
enough to discriminate between real difference.
• A final challenge is an apparent lack of awareness of psychometric information.
54
 Psychometrics as a Profession
Psychometricians can find the scope of work in a wide variety of fields and job environments
including—
 Hospitals and mental clinics
 Educational settings (school, universities…)
 Large corporations like software development companies
 Market research, employee selection & training, performance analysis (industrial-
organizational psychology)
 Consultant
 Policy Advocacy

The work of Dr. Kevin McGrew, a Psychometrician presents a nice precedent for career in
this field. He is a school psychologist, an educational psychologist as well as the director and
founder of the Institute for Applied Psychometrics (IAP).
55
Bangladesh Psychometric Society (BPS) 56
Guidelines for Critiquing a Psychological Test
To make informed decisions about tests, one needs to know how to critique a test properly. A critique of a test
is an analysis of the test. A good critique answers many of the following questions. Not all questions can be
answered for all tests, as some questions are not relevant to all tests.

Bangladesh Psychometric Society (BPS) 57

Guidelines for Critiquing a Psychological Test…

Bangladesh Psychometric Society (BPS) 58

Guidelines for Critiquing a Psychological Test…

Bangladesh Psychometric Society (BPS) 59

Bangladesh Psychometric Society (BPS) 60
Guidelines for Critiquing a Psychological Test…

Bangladesh Psychometric Society (BPS) 61

Bangladesh Psychometric Society (BPS) 62