PSYCHSTATS UNIT 2 (DATA COLLECTION & SAMPLING)

Data collection

is the systematic and planned process of gathering information from participants, settings, or existing sources in order to answer a research question or test a hypothesis.

Survey/questionnaire, interview, observation, psychological tests, archival records

Commkn data collection method in psychology

Survey/questionnaire

uses written or digital questions answered by participants to measure attitudes, beliefs, experiences, behaviors, or characteristics.

By item format, by structure, by mode of administration

Types of syurvey/questionnaires

Closed-ended, open-ended, mixed-format

Types of surveys/questionnaires according to item format

Structured, semi-structured

Types of surveys/questionnaires according to structure

Paper-and-pencil, online, telephone-based, group-administered

Types of surveys/questionnaires according to mode of administration

Closed-ended

(fixed choices): yes/no, multiple choice, rating scales

Open-ended

(free response): participants answer in their own words.

Mixed-format

combination of closed and open questions

Structured

same questions in the same order for all respondents.

Semi-structured

mostly fixed questions with a few open follow-ups.

Online

(Google Forms, SurveyMonkey, etc.)

Group-administered

(in class or clinic setting)

Questionnaire survey, cross-sectional survey, longitudinal survey, census survey

Types of Survey

Questionnaire survey

Respondents answer written questions. Can be paper-based or online.

Cross-sectional survey

Data collected at one point in time

Longitudinal survey

Data collected from the same group over a period of time.

Census survey

Data collected from the entire population.

Interview

collects data through direct verbal interaction, allowing deeper exploration of thoughts,

emotions, and experiences.

Structured interview, semi-structured interview, unstructured interview

Types of interview

Structured interview

fixed questions, standardized format, useful for consistency and comparison across participants

Semi-structured interview

guiding questions with follow-up probes, common in psychological research because it balances structure and depth

Unstructured interview

conversational, flexible, minimal pre-set questions, useful for exploratory research or sensitive topics

Face-to-face, phone, video call, focus group interview

Additional classification (by method) interview

Focused group discussion (FGD)

involves a small group of people who talk about a specific topic or issue. The researcher guides the discussion and takes note of the group’s opinions and ideas.

Observation

involves watching and recording behavior as it occurs in real settings or controlled environments.

By setting, by role of the observer, by awareness of participants, by structure

Types of observation

Naturalistic observation, laboratory/controlled observation

Types of observation by setting

Naturalistic observation

behavior observed in reallife context (school, home, public spaces)

Laboratory/controlled observation

behavior observed in a structured setting with controlled conditiono

Participant observation, non-participant observation

Types of observation by role of the observer

Participant observation

researcher becomes part of the group being studied

Non-participant observation

researcher remains separate and only observes

Overt observation, Covert observation

Types of observation by awareness of participants

Overt observation

participants know they are being observed

Covert observation

participants do not know (used only under strict ethical limits)

Structured observation, Unstructured observation

Types of observation by structure

Structured observation

uses checklists/rubrics and clearly defined behaviors

Unstructured observation

open-ended notes about behaviors/events

Psychological tests

are standardized instruments designed to measure mental abilities, personality traits, emotional functioning, or specific psychological symptoms.

Intelligence tests, Achievement tests, Personality tests, Neuropsychological tests, Clinical symptom inventorie

Types of psychological test

Intelligence tests

cognitive ability/IQ measures

Achievement tests

academic skills

Objective, projective

2 Personality tests

Objective personality test

structured items; e.g., rating scales

Projective personality test

open interpretation of stimuli; used less often in research due to reliability concerns

Neuropsychological tests

memory, attention, executive functioning

Clinical symptom inventorie

depression, anxiety, stress checklists

Standardization

Same instructions and scoring procedures, norms for interpreting scores

Archival records

are existing data sources originally collected for other purposes but used in research (documents, databases, institutional records).

Public records, Institutional records, Digital/online archives, Existing datasets

Types of Archival Record

Public records

census data, government statistics

Institutional records

school attendance, clinic reports, HR data

Digital/online archives

posts, forum data, website logs (with ethical safeguards)

Existing datasets

previously collected research data (secondary data analysis)

Error Source (Non-response Bias)

Occurs when a significant portion of selected participants does not respond, leading to a non-representative sample.

Improvement (Non-response Bias)

Implement follow-up strategies, such as reminders or incentives, to encourage participation and reduce non-response bias.

Error Source (Response Bias)

Occurs when participants provide inaccurate or biased responses,

often due to social desirability or leading questions.

Improvement (Response Bias)

Use neutral and unbiased language in survey questions, ensure anonymity and confidentiality to reduce social desirability bias, pilot test surveys to identify and revise potentially problematic questions.

Error Source (Measurement Error)

Inaccurate measurement tools or methods lead to measurement error.

Improvement (Measurement Error)

Calibrate measurement instruments regularly to ensure accuracy, use standardised measurement protocols and procedures, train data collectors to minimise human errors.

Error Source (Selection Bias)

Arises when the selection of participants is not truly random, leading to unrepresentative results.

Improvement (Selection Bias)

Randomise the selection process or use stratified sampling to ensure diverse representation.

Error Source (Observer Bias)

Researchers or data collectors may unintentionally influence or misinterpret data due to their personal biases or expectations.

Improvement (Observer Bias)

Use double-blind studies when possible, where neither the participants nor the data collectors are aware of the research objectives or conditions, implement inter-rater reliability checks when multiple observers are involved.

Error Source (Data Entry Errors)

Mistakes during data entry, such as typos or transcription errors.

Improvement (Data Entry Errors)

Use data validation checks to catch and correct input errors, double-check data entries for accuracy, if possible, employ data entry software with error-checking features.

Error Source (Temporal Variability)

Data collected at different times may not reflect consistent conditions or circumstances.

Improvement (Temporal Variability)

Ensure data collection occurs under standardised conditions and at consistent time intervals, if possible, collect data over an extended period to account for temporal variations.

Error Source (Environmental Factors)

Environmental conditions (e.g., lighting, temperature) can affect measurements or observations.

Improvement (Environmental Factors)

Control environmental factors as much as possible during data collection, and record any conditions that may influence the data.

Error Source (DATA COLLECTION FATIGUE)

Data collectors may become fatigued or lose focus during extended data collection periods.

Improvement (DATA COLLECTION FATIGUE)

Rotate data collectors, take breaks, and monitor for signs of fatigue to ensure consistent data quality.

Population

The entire group of individuals of interest.

Sample

A subset of the population.

Sampling

is the process of selecting a subset of individuals from a population to participate in a study so that results can be used to understand the larger group.

Sample Size Determination

Before selecting participants, researchers often compute how many people should be included in the sample.

Margin of error

is the maximum expected difference between a sample result and the true population value.

Smaller margin of error =

more precise results

Larger margin of error =

less precise results

Probability Sampling, Non-Probability Sampling

Major Types of Sampling

Probability Sampling

every member has a known chance of being selected

Non-Probability Sampling

not all members have a known chance of being selected

Probability Sampling

reduces bias and improves representativeness

Simple Random Sampling

Each member of the population has an equal chance of selection

Systematic Sampling

Select every nth person from a list.

Stratified Random Sampling

Population is divided into subgroups (strata), then random samples are taken from each group.

Cluster Sampling

Population is divided into clusters (groups), and entire clusters are selected.

Non-probability Sampling

Used when probability sampling is difficult or impossible.

Convenience Sampling

Select people who are easily available.

Purposive (Judgmental) Sampling

Select participants who meet specific criteria.

Snowball Sampling

Participants refer other participants.

Quota Sampling

Select a fixed number from different groups without randomization.

Volunteer (Self-Selection) Sampling

Participants volunteer to join.

Research Design

is the overall plan or blueprint for how a psychological study will be conducted—how participants are chosen, how variables are measured or manipulated, and how data are analyzed—to answer a research question accurately and ethically.

Validity, Reliability, Control of bias, Ethical protection of participants

A good research design helps ensure:

Descriptive Designs, Correlational Designs, Quasi-Experimental Designs, Experimental Designs, Qualitative Designs

Major Research Designs in Psychology

Descriptive Designs

Used when the goal is to describe behaviors, attitudes, or characteristics without testing cause-and-effect.

Correlational Designs

Used to determine whether two variables are related (increase/decrease together).