PRACTICAL RESEARCH II MODULE 4: DATA & DATA COLLECTION VOCABULARY

Vocabulary-style flashcards covering core terms from the lecture notes on research design, sampling, instruments, validity, reliability, and data analysis.

Mock Defense

A practice defense session where the final paper should be complete and guidance is given on presenting and answering questions.

Final Defense

The formal defense of the research paper scheduled for the group (schedule per group).

Research Design

A logical, coherent strategy to integrate all components of the research study.

Descriptive Research Design

An exploratory design that answers Who, What, Where, When, and How much; describes the phenomenon.

Correlational Research Design

Determines whether variables are related; establishes association but not causation.

Ex-Post Facto / Causal-Comparative Design

Measures a cause from pre-existing effects; no control over variables; cannot infer changes during the study.

Experimental Research

Aims to measure causal relationships under controlled/manipulated conditions; true experiments involve randomization and manipulation.

Quasi-Experimental Design

Aims to measure causality but lacks full randomization or control; uses existing groups.

True Experimental Design

Random assignment to treatment and control groups with manipulated independent variable; high internal validity.

Internal Validity

The extent to which a study demonstrates a true cause-effect relationship free from confounds.

External Validity

Generalizability of study findings to real-world settings and other populations.

Population

The totality of all objects, elements, or persons under consideration.

Target Population

The actual population of interest for a study.

Accessible Population

Portion of the population that the researcher can reasonably access.

Sample

A representative subset of the population chosen for analysis.

Sampling

Systematic process of selecting the group to be analyzed so it represents the target population.

Simple Random Sampling

Every member of the accessible population has an equal chance of being selected.

Stratified Random Sampling

Population divided into strata; samples drawn from each stratum; used when variables are grouped (e.g., gender, grade level).

Proportionate Stratified Sampling

Sample sizes from subgroups are proportionate to their size in the population.

Clustered Sampling

Used for large-scale studies; sampling units are clusters; efficient for geographically dispersed populations.

Systematic Sampling

Selects every nth member of the population; interval = N/n.

Slovin's Formula

n = N / (1 + N e^2); used to estimate an acceptable sample size given population N and margin of error e.

Literature Review

Review of related literature to inform the study and, if applicable, determine an appropriate sample size (e.g., using Slovin’s formula).

Research Instrument

Tools used to gather data (e.g., performance tests, questionnaires, interviews, observation checklists).

Concise

Instruments should be short yet capable of eliciting the needed data.

Sequential

Question order should progress from simplest to most complex.

Valid & Reliable

Instruments should be valid (measure what they intend) and reliable (consistent results).

Easily Tabulated

Data from the instrument should be straightforward to organize and present in tables.

Adopt an Instrument

Use an existing instrument as-is for your study.

Modify an Existing Instrument

Adapt an instrument to fit the study’s context or needs.

Make Your Own Instrument

Create a new instrument tailored to the study’s objectives.

Likert Scale

A commonly used scale in quantitative research (e.g., 5-point: Strongly Agree to Strongly Disagree) to measure attitudes.

Semantic Differential

A scale that uses bipolar adjectives (ratings between opposite descriptors) to assess perceptions.

Validity

The degree to which an instrument measures what it is supposed to measure.

Face Validity

Judgment that an instrument appears to measure what it intends to measure.

Content Validity

Extent to which the instrument covers all aspects of the construct aligned with study objectives.

Construct Validity

How well an instrument relates to theoretical constructs and other measures as expected.

Concurrent Validity

Instrument predicts results similar to other validated tests administered at the same time.

Predictive Validity

Instrument predicts results similar to future measures or outcomes.

Reliability

Consistency of the instrument’s measurements across time, items, or forms.

Test-Retest Reliability

Stability of scores when the same test is administered to the same respondents on two occasions.

Equivalent Forms Reliability

Consistency between two comparable tests given to the same group with different items.

Internal Consistency Reliability

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

Cronbach’s Alpha

A statistic of internal consistency; common interpretation ranges: 0.91–1.00 Excellent, 0.81–0.90 Good, 0.71–0.80 Good/Acceptable, 0.61–0.70 Acceptable, 0.01–0.60 Non-acceptable.

Univariate Analysis

Statistical analysis of a single variable.

Bivariate Analysis

Analysis of two variables (e.g., IV and DV) to assess relationships.

Multivariate Analysis

Analysis of multiple variables and their relationships simultaneously.

Parametric Tests

Statistical tests assuming normal distribution and interval/ratio data (often with n ≥ 30).

Non-parametric Tests

Statistical tests not assuming normal distribution; suitable for ordinal/nominal data or small samples.

Pearson’s r

A parametric measure of the strength and direction of the linear relationship between two continuous variables.

Phi Coefficient

A measure of association for nominal/dichotomous variables (binary data).

Spearman’s Rho

A non-parametric measure of rank correlation for ordinal variables.

T-test for Dependent Samples

Compares means from the same group at different times or under different conditions (paired samples).

T-test for Independent Samples

Compares means between two independent groups.

Two-way Chi-Square

Non-parametric test for relationship between two nominal variables across groups.

Mann-Whitney U Test

Non-parametric test comparing two independent groups when data are ordinal or not normally distributed.

Wilcoxon Signed-Rank Test

Non-parametric test for paired ordinal data or non-normal distributions.

ANOVA (Analysis of Variance)

Parametric test comparing means across three or more groups.

Regression

Statistical method to assess the strength and form of the relationship between one dependent and one or more independent variables.