QUANTITATIVE RESEARCH DESIGNS

Quantitative research designs are built on a positivist view of reality: measurable, objective variables that can be converted into numbers to test hypotheses and explain cause-and-effect patterns. The core takeaway is that philosophical assumptions—especially epistemology (how knowledge is known), axiology (values), ontology (what reality is), and methodology (how methods fit the approach)—shape how researchers frame problems, collect data, and analyze results. Quantitative work typically uses objective measurement, structured instruments, and controlled or standardized procedures, aiming to generate numerical data that can be analyzed statistically.

A major emphasis falls on what “numerical” actually means. It is not limited to counting people (e.g., how many males or females), but includes any variable that can be quantified—such as converting respondents’ answers about “causes of divorce” into categories and then into percentages. The class also draws a careful distinction between open-ended questions and qualitative research: an open-ended question can still be quantitative if responses are coded and converted into numbers. Conversely, qualitative data tends to remain narrative—stories and in-depth accounts that resist conversion into numeric measures.

The session then contrasts quantitative and qualitative research along several dimensions: purpose (prediction and testing hypotheses versus in-depth understanding), group size and sampling (larger, randomly selected samples for generalization versus smaller information-rich samples), data type (numerical versus narrative), and instrument structure (questionnaires and structured interviews with minimal probing versus researcher-led depth). Despite these differences, the lesson stresses that no approach is inherently superior. The right choice depends on the research question and the kind of evidence needed to answer it.

From there, the class defines research design as a “plan” that specifies sources and types of information relevant to the research problem—covering sample selection, instruments, analysis methods, and how findings will be presented. Coherence is treated as essential: the research title/problem, the design, the population, sampling strategy, and analysis must align. A mismatch—such as claiming “factors influencing community participation” while using a case study design—signals a flawed design-problem fit.

Quantitative designs are organized into two broad categories: non-experimental and experimental. Non-experimental designs include survey and ex post facto (comparative) designs. Survey research is described as a design for describing population attitudes, opinions, and threads by studying a sample and generalizing to a wider population. It uses structured questionnaires or structured interviews without probing, and it supports three kinds of research questions: descriptive, relational, and predictive. The class also clarifies common confusion: “survey” is a design, not the questionnaire instrument itself.

Ex post facto design is framed as “after the fact.” Researchers study pre-existing groups where an outcome has already occurred, then look back to identify factors that may explain changes. It mimics experimental logic by comparing groups exposed to different conditions, but lacks the researcher’s control over group formation and extraneous variables. That limitation creates risks such as spurious relationships and tentative cause-and-effect conclusions.

The session closes by previewing experimental designs for the next class, noting that topics like internal and external validity and control of extraneous variables will be central. Overall, the lesson positions quantitative design choices as a disciplined match between research questions, measurement strategy, and analytic goals—rather than a matter of preference for numbers over stories.