Research methods midterm 2

Acquiescence bias

Tendency for respondents to agree with statements regardless of content.

Action research

A participatory approach where researchers and practitioners collaborate to solve an immediate problem.

After-only design

Research design measuring outcomes only after a treatment/intervention.

Case study (case history)

In-depth analysis of a single individual, group, or event.

Causal hypothesis

Predicts a cause-and-effect relationship between variables.

Causation

When one variable directly influences another.

Control group

A group not exposed to the experimental treatment, used for comparison.

Dependent variable

The outcome measured or affected by changes in the independent variable.

Independent variable

The factor manipulated to determine its effect on the dependent variable.

Experiment

A controlled study where variables are manipulated to test causal relationships.

Field experiment

Conducted in a real-world setting rather than a lab.

Group time series design

Multiple measurements before and after treatment across different groups.

Non-equivalent control group design

Uses existing (non-random) groups, one of which receives treatment.

Posttest-only control group design

Measures only after the treatment.

Pretest-posttest control group design

Measures before and after treatment in both experimental and control groups.

Separate sample pretest-posttest design

Different samples are used for pretest and posttest phases.

Static group comparison design

Compares outcomes of treated vs. untreated groups without pretesting.

Treatment levels

Variations of the independent variable administered to different groups.

Area sampling

Selecting samples geographically by dividing a population into regions.

Cluster sampling

Population divided into clusters (groups), then clusters are randomly selected.

Convenience sample

Participants chosen based on ease of access.

Judgment sampling

Researcher selects participants based on their own judgment of who is most appropriate.

Non-probability sampling

Samples are not chosen randomly.

Probability sampling

Each member of the population has a known, nonzero chance of selection.

Quota sampling

Non-random sample where subgroups are filled to specific quotas.

Simple random sample

Every population member has an equal chance of selection.

Snowball sampling

Participants recruit others through their networks (useful for hidden populations).

Stratified random sampling

Population divided into strata (subgroups), random samples drawn from each.

Systematic sampling

Selecting every nth individual from a list after a random start.

Double sampling

Using two or more sampling stages to improve accuracy or reduce cost.

Proportionate stratified sampling

The sample size in each stratum reflects its proportion in the population.

Sample frame

The list or source from which a sample is drawn.

Sampling error

Difference between sample results and true population values due to chance.

Sampling

The process of selecting a subset from a population.

Target population

The entire group a researcher wants to draw conclusions about.

Asynchronous interview

Conducted via email or text, not in real time.

Synchronous interview

Real-time interaction (e.g., face-to-face, phone, or live chat).

Focus group

Group discussion led by a moderator to gather opinions on a topic.

Observation

Watching subjects and recording behaviors or events.

Survey

Structured data collection through questionnaires or interviews.

Self-administered survey

Respondent completes the survey independently.

Phone survey

Conducted via telephone.

Interview guide

Outline of questions/topics for an interview.

Convergent interviewing

Iterative interview process focusing on agreement and disagreement between participants.

Cultural interviews

Exploring beliefs, norms, and behaviors of a culture.

Individual depth interview

One-on-one, detailed discussion exploring motivations and attitudes.

Group interviews

Multiple respondents interviewed together.

Intercept interview

Conducted in public spaces (e.g., malls) by stopping passersby.

Debriefing

Informing participants after the study, especially if deception was used.

Informed consent

Ensuring participants understand and agree to their involvement.

Deception

Withholding or misleading information in research (must be ethically justified).

Blind

Participants unaware of the treatment they receive.

Double-blind

Neither participants nor researchers know who receives which treatment.

Behavioral

Data or measures based on observable actions or reactions of participants.

Biometrics

Measuring physiological or biological characteristics (e.g., fingerprints, eye movements).

Cell

A single data point or category intersection in a data table.

Coding scheme

Rules for categorizing and assigning values to qualitative or quantitative data.

Content analysis

Systematic coding and interpretation of textual, visual, or verbal content.

Context units

The smallest segment of material analyzed in content analysis.

Data collection protocols

Step-by-step procedures for gathering information.

Data collection

The process of obtaining information to answer research questions.

Data entry

Inputting data into a database or software for analysis.

Data field

A specific variable or attribute within a dataset.

Data file

The entire set of recorded data from a study.

Data missing at random (MAR)

Missingness depends on observed data but not on the missing value itself.

Data missing completely at random (MCAR)

Missingness is unrelated to both observed and unobserved data.

Data missing but not missing at random (NMAR)

Missingness is related to the missing value itself.

Data preparation

Cleaning, organizing, and formatting data for analysis.

Data record

A complete set of data for one observation or participant.

Data saturation

The point in qualitative research when no new insights emerge.

Data validation

Checking data accuracy and completeness.

Editing

Reviewing data for errors or inconsistencies.

Listwise deletion

Excluding cases with any missing values.

Pairwise deletion

Using all available data without discarding entire cases.

Recoding

Changing data values or categories for analysis.

Replication

Repeating a study to verify findings.

Exploratory data analysis (EDA)

Visual and statistical exploration to find patterns before formal testing.

Predictive replacement

Estimating missing data based on observed relationships.

Process (activity) analysis

Examining steps or activities within a process to understand efficiency or behavior.

Construct validity

How well a test or measure reflects the concept it's intended to assess.

Content validity

Extent to which a measure covers all aspects of a concept.

Criterion-related validity

How well one measure predicts or correlates with an outcome or criterion.

External validity

The generalizability of findings beyond the study sample.

Internal validity

Degree to which observed effects are due to the independent variable, not confounds.

Reliability

Consistency or repeatability of measurement results.

Inter-rater reliability

Agreement between different observers measuring the same thing.

Intra-rater reliability

Consistency of the same observer over time.

Internal consistency

How well the items in a test measure the same construct.

Equivalence

When different instruments or measures yield the same results.

Stability

Consistency of results over time.

Validity

The degree to which an instrument measures what it claims to measure.

Systematic variance

Variation in data due to real differences rather than error.

Systematic

Methodical and consistent in approach.

Social desirability bias

Respondents give socially acceptable rather than truthful answers.

Response error

Any inaccuracy in survey responses.

Nonresponse error

Bias from differences between respondents and non-respondents.