💡 The Concept of Variable
A variable is any stimulus or event that varies (takes on different values) and can be measured.
Objects themselves are not variables, but their attributes are (e.g., a pen is not a variable, but its
shape, size, and color are).
Independent Variable (IV):
The variable that is manipulated, altered, or whose strength is varied by the
researcher.
Its change is intended to cause an effect on another variable.
Example (Latane and Darley study): Presence or absence of other persons in the room.
Dependent Variable (DV):
The variable on which the effect of the independent variable is observed.
It represents the phenomenon the researcher wants to explain.
Changes in the DV are expected to result from changes in the IV.
Example: Frequency of reporting smoke.
Relationship: The IV is the cause, and the DV is the effect. They are interdependent and
cannot be defined without each other.
Extraneous Variables: Many other relevant variables can influence the dependent variable
but are not the focus of the study. These must be controlled to ensure a clear cause-effect
relationship between IV and DV.
👥 Experimental and Control Groups
Experiments typically involve different groups to isolate the effect of the independent variable.
Experimental Group:
The group whose members are exposed to the manipulation of the independent
variable.
Control Group:
A comparison group that is treated identically to the experimental group, except that
the manipulated variable is absent.
Example (Latane and Darley):
Control Group: Participants alone in the room (no other persons present).
Experimental Group 1: Participants with two naive persons (no instructions).
Experimental Group 2: Participants with two confederates (instructed not to react).
The performance of the control group is compared to the experimental group(s) to
determine the effect of the IV.
Controlling Variables: All conditions, except the experimental manipulation, are kept
constant for both groups.
Random Assignment: Participants are assigned to groups randomly to ensure each
person has an equal chance of being in any group, minimizing systematic differences.
Types of Variables to Control:
Organismic variables: Individual characteristics (e.g., anxiety, intelligence).
Situational/Environmental variables: Factors in the setting (e.g., noise, temperature).
Sequential variables: Effects arising from the order of conditions (e.g., fatigue,
practice effects).
Control Techniques:
Elimination: Removing extraneous variables from the setting (e.g., sound-proof room).
Holding Constant: Keeping extraneous variables at a consistent level.
Matching: Equating relevant variables across groups (e.g., matching participants on
socio-economic status).
Counter-balancing: Minimizing sequence effects by varying the order of tasks (e.g., ABBA
design).
Random Assignment: Distributing potential differences evenly across groups.
Strengths of Experimental Method:
Provides convincing evidence of cause-effect relationships.
Limitations of Experimental Method:
Often conducted in highly controlled laboratory settings, which may not generalize well to
real-world situations (low external validity).
Not always feasible or ethical to study certain problems experimentally (e.g., nutritional
deficiency on intelligence).
Difficult to identify and control all relevant variables.
🏕️ Field Experiments and Quasi Experiments
To address the limitations of laboratory experiments:
Field Experiment:
Conducted in natural settings where the phenomenon actually exists.
Aims for higher generalizability to real-world situations.
Example: Comparing learning methods (lecture vs. demonstration) in a school setting.
Limitation: Less control over relevant variables, more time-consuming and expensive
than lab experiments.
Quasi Experiment:
Used when the independent variable cannot be manipulated by the experimenter (e.g.,
natural disasters, pre-existing conditions).
The independent variable is selected (e.g., children who lost parents in an earthquake).
Uses naturally occurring groups to form experimental and control groups.
Example: Studying the effect of an earthquake on children by comparing those who lost
parents to those who did not.
🔗 Correlational Research
Correlational research aims to determine the relationship between two variables for prediction
purposes, without manipulating either variable. It assesses whether variables are associated, or
covary.
Correlation Coefficient: A number representing the strength and direction of the
relationship between two variables.
Ranges from +1.0 (strong positive) through 0.0 (no correlation) to -1.0 (strong
negative).
Types of Correlation:
Positive Correlation: As the value of one variable (X) increases, the value of the other
variable (Y) also increases. Conversely, as X decreases, Y decreases.
Example: More study time is positively correlated with higher achievement scores (e.g.,
+.85).
Negative Correlation: As the value of one variable (X) increases, the value of the other
variable (Y) decreases.
Example: Increased study time might be negatively correlated with hours spent in
other activities.
Zero Correlation: No significant relationship exists between the two variables.
Correlation values are close to 0 (e.g., -.02 or +.03).
📝 Survey Research
Survey research is used to study opinions, attitudes, and social facts. Initially focused on
finding existing realities (e.g., literacy rates, religious affiliations), it has evolved to infer causal
relationships.
🛠️ Techniques for Collecting Information in
Surveys
Personal Interviews:
One of the most frequently used methods, involving face-to-face interaction where an
interviewer asks questions and a respondent answers.
Purpose: To derive factual information, opinions, attitudes, and reasons for behavior.
Types:
Structured (Standardized) Interview: Questions are clearly written in a specific
sequence, with little to no liberty for the interviewer to change wording or order.
Responses may be pre-specified (close-ended questions).
Unstructured (Non-standardized) Interview: Interviewer has flexibility in choosing
questions, wording, and sequence. Responses are not specified, allowing open-ended
answers.
Combinations of Participants:
Individual to Individual
Individual to Group (e.g., Focus Group Discussion - FGD)
Group to Individuals (e.g., job interview panel)
Group to Group
Advantages: Provides in-depth information, flexible, adaptable, can be used with
children and non-literate persons.
Limitations: Time-consuming, may not be cost-effective.
Questionnaire Survey:
A self-report method consisting of a predetermined set of questions, where respondents
read and mark answers on paper.
Similar to highly structured interviews.
Can be distributed to groups or sent via mail.
Types of Questions:
Open-ended: Respondents write their own answers.
Closed-ended: Questions and probable answers are provided (e.g., Yes/No, True/False,
Multiple choice, Rating scales like 3-point, 5-point).
Uses: Collecting demographic information, past behavior, attitudes, opinions, knowledge,
expectations.
Main Problem with Mailed Questionnaires: Poor response rate.
Telephone Survey:
Surveys conducted over the phone, or via mobile SMS.
Advantage: Reduces time.
Limitations:
Lack of rapport can lead to uncooperativeness, reluctance, and superficial answers.
Potential for biased results as respondents may differ significantly from non-
respondents (e.g., age, gender, income).
General Limitations of Survey Method:
Respondents may give inaccurate information due to memory lapses or unwillingness to
disclose true beliefs.
Respondents may offer socially desirable responses (what they think the researcher wants
to hear).
🧠 Psychological Testing
Psychological tests are used to assess individual differences in various human characteristics.
Purpose: Personnel selection, placement, training, guidance, diagnosis across diverse
contexts (educational, clinical, industrial, defense).
Characteristics:
Standardized: Uniform procedures for administration, scoring, and interpretation.
Objective: If multiple researchers administer the test, they should obtain similar scores for
individuals. Items are worded clearly, instructions are specified, and scoring procedures
are defined.
Construction of a Test: A systematic process involving item analysis, and estimating
reliability, validity, and norms.
Reliability: Refers to the consistency of scores obtained by an individual on the same
test over different occasions or within the test itself.
Test-retest reliability: Indicates temporal stability; assessed by correlating scores
from two administrations of the same test to the same group.
Split-half reliability: Indicates internal consistency; assessed by correlating scores
from two halves of the same test (e.g., odd vs. even items).
Validity: Addresses the question, "Does the test measure what it claims to measure?"
(e.g., a math test should measure math achievement, not language proficiency).
Norms: Average performance standards for a specific group, developed by
administering the test to a large sample. Norms (based on age, sex, residence) allow
comparison of an individual's score to a relevant group.
분류 Types of Tests
Psychological tests are classified by language, administration mode, and difficulty.
By Language:
Verbal Tests: Require literacy, items written in language.
Non-verbal Tests: Items use symbols or pictures.
Performance Tests: Require manipulation of objects in a specific order.
By Mode of Administration:
Individual Tests: Administered to one person at a time by a researcher who observes
responses. Time-consuming but effective for children or non-literate individuals.
Group Tests: Administered to a large number of persons simultaneously. Instructions
are often written, and the administrator explains them to the group. Easy to administer
and less time-consuming, but responses can be affected by motivation or faking.
By Difficulty Level:
Speed Test:
Time limit for answering all items.
Evaluates performance based on time taken for accurate answers.
All items are typically of the same difficulty.
Power Test:
No time limit (sufficient time allowed).
Assesses underlying ability by presenting items in increasing order of difficulty.
Designed to see how far an individual can go in solving increasingly complex
problems.
Most tests are a combination of both speed and power.
Important Considerations: Tests should be selected and used carefully, not as the sole basis for
decisions. Test data should be combined with other information like background, interests, and
past performance.
📝 Case Study
The case study method focuses on an in-depth study of a particular case.
Focus: Cases that provide critical information or new learning about less understood
phenomena.
Scope of "Case": Can be an individual (e.g., patient with psychological disorder), a small
group (e.g., creative writers), institutions (e.g., a school), or specific events (e.g., children
affected by tsunami).
Characteristics:
Cases are unique and rich in information.
Employs multiple methods for data collection (e.g., interviews, observations,
psychological tests) from various respondents associated with the case.
Provides narrative or detailed descriptions of events in a person's life.
Applications: Valuable in clinical psychology and human development (e.g., Freud's
psychoanalytic theory, Piaget's theory of cognitive development, studies on child
socialization).
Limitations:
Generalizability: Caution is needed when generalizing findings from individual cases to a
broader population.
Validity: Challenging in single case studies.
Mitigation: Information should be collected using multiple strategies from different
sources by multiple investigators. Careful planning and maintaining a chain of evidence
are crucial.
Overall Research Strategy: Researchers should not rely on a single method. A combination of
two or more methods is desirable to obtain a comprehensive picture. If results from different
methods converge, confidence in the findings increases.
📈 Analysis of Data
After data collection, the next step is to analyze the data to draw conclusions. Two main
methodological approaches are used: quantitative and qualitative methods.
🔢 Quantitative Method
This method is used when data are in the form of numbers or scores, typically from
psychological tests, questionnaires with close-ended questions, or structured interviews.
Data Collection: Responses are often on scaled forms (e.g., 1 to 5, 7, or 11) indicating
strength or magnitude, or as right/wrong answers (assigned 1 or 0).
Quantification: Psychological attributes are converted into numerical quantities (aggregate
scores).
Analysis:
Comparing individual scores with group scores, or comparing scores between two
groups.
Utilizes statistical procedures (e.g., measures of central tendency like mean, median,
mode; measures of variability like range, standard deviation; coefficients of correlation).
Statistical methods enable researchers to make inferences and assign meaning to the
numerical data.
🗣️ Qualitative Method
This method is used for analyzing complex human experiences that are not easily quantified,
where the richness of the data would be lost through numerical conversion.
Data Collection: Data are typically in a descriptive form:
Participants' own words (e.g., from unstructured interviews).
Field notes from participant observation.
Photographs, audio/video recordings.
Personal diaries.
Analysis:
Cannot be converted into scores or subjected to statistical analysis.
Uses techniques like content analysis to identify thematic categories and build these
categories with examples from the data.
More descriptive in nature, focusing on understanding meaning and organization of
experiences.
Example: Understanding a mother's feelings about the loss of her child by hearing her
story.
Complementary Approaches: Quantitative and qualitative methods are complementary, not
contradictory. A suitable combination of both is often warranted for a holistic understanding of
a phenomenon.
⚠️ Limitations of Psychological Enquiry
Beyond the specific limitations of each method, psychological measurement faces general
challenges.
1. Lack of True Zero Point:
Unlike physical measurements (e.g., length), psychological measurements (e.g.,
intelligence) do not have an absolute zero point. No one has "zero intelligence."
Psychologists arbitrarily define a zero point, making scores relative, not absolute.
Ranks also illustrate this: the difference between rank 1 and 2 might not be the same as
between rank 2 and 3, highlighting the relative nature of psychological measurement.
2. Relative Nature of Psychological Tools:
Psychological tests are developed for specific contexts and may not be universally
applicable.
A test designed for urban students might contain stimuli unfamiliar to tribal children.
Tests from Western cultures may need modification and adaptation for use in Indian or
other cultural contexts to ensure relevance and accuracy.
3. Subjective Interpretation of Qualitative Data:
Qualitative data relies heavily on interpretation by both the researcher and the data
provider.
Interpretations can vary significantly between individuals.
Mitigation: It is often suggested that multiple investigators conduct fieldwork and
discuss observations to reach agreement. Involving respondents in the meaning-making
process can also enhance validity.
⚖️ Ethical Issues
Psychological research, dealing with human behavior, must adhere to strict ethical principles to
protect participants. These include respect for persons' privacy and choice, beneficence
(protecting from harm), and justice (sharing benefits).
1. Voluntary Participation:
Participants must have the free choice to decide whether to participate or not.
Participation should be without coercion or excessive inducement.
Participants must have the freedom to withdraw from the study at any point without
penalty.
2. Informed Consent:
Potential participants must receive comprehensive information about what will happen
to them during the study before data collection.
This allows them to make an informed decision about participation.
This is crucial when studies involve potential discomfort (e.g., electric shock, obnoxious
stimuli), private information, or deception (giving false information about the study or
performance).
3. Debriefing:
After the study, participants must be provided with necessary information to fully
understand the research.
This is especially important if deception was used, to explain its necessity and purpose.
Debriefing aims to ensure participants leave in the same physical and mental state as
they entered, and to remove any anxiety or adverse effects resulting from the study.
4. Sharing the Results of the Study:
Researchers have an obligation to share the study results with participants.
This fulfills participants' expectations and can provide researchers with new insights
based on participants' opinions about the findings.
5. Confidentiality of Data Source:
Participants have a right to privacy.
Researchers must safeguard privacy by keeping provided information in strict
confidence.
Information should only be used for research purposes and never shared with other
parties.
Most effective protection: Not recording identities. If identities must be recorded, use
code numbers and keep identification lists separate, destroying them after research is
complete.