Lecture Notes: The Foundations of Quantitative Research
1. What is Quantitative Research? The Science of Measurement
Quantitative research is a systematic, empirical investigation of observable phenomena via statistical,
mathematical, or computational techniques. Its fundamental goal is to develop and employ
mathematical models, theories, and hypotheses pertaining to phenomena. The process of measurement
is central to quantitative research because it provides the fundamental connection between empirical
observation and mathematical expression of quantitative relationships.
Core Premise: Reality is objective and singular, existing independently of the researcher. It can be broken
down into variables, measured, and analyzed to uncover facts, laws, and predictable patterns.
Formal Definition: A formal, objective, deductive process for generating knowledge about the world. It is
used to describe variables, examine relationships between variables, and determine cause-and-effect
interactions between variables.
2. The Philosophical Underpinnings: Positivism & Post-Positivism
The quantitative approach is historically rooted in Positivism, which asserts that only knowledge gained
through direct observation and measurement is authoritative. A more contemporary and nuanced
version is Post-Positivism, which acknowledges that while an objective reality exists, it can only be
known imperfectly and probabilistically. The researcher must strive for objectivity by designing studies
that minimize their influence on the outcome.
This leads to a key methodological principle: The Researcher is Detached. They are an independent
observer who does not influence the data or the subjects being studied.
3. The Major Goal: Inference and Generalization
Unlike qualitative research, which seeks depth in a specific context, the primary ambition of most
quantitative research is to generalize findings from a sample to a larger population.
• Population: The entire group of individuals or entities you wish to study (e.g., all university
students in Canada).
• Sample: A subset of the population selected for the actual study.
• Inference: The process of using sample data to draw conclusions about the population.
This is why sampling is so critical in quantitative research. The goal is to obtain a sample that
is representative of the population, often through probability sampling methods (e.g., random sampling),
where every member of the population has a known, non-zero chance of being selected.
4. Core Components of Quantitative Research
To understand quantitative design, you must master its basic building blocks:
1. Variables: A characteristic or attribute that can take on different values.
o Independent Variable (IV): The presumed cause. The variable that the researcher
manipulates or selects to determine its effect on the dependent variable. (e.g., Type of
Teaching Method).
o Dependent Variable (DV): The presumed effect. The outcome that is being measured. It
depends on the independent variable. (e.g., Student Test Scores).
o Control Variable: A variable that is held constant or neutralized to prevent it from
influencing the outcome. (e.g., ensuring all students are the same age).
2. Hypotheses: A formal, testable prediction about the relationship between two or more variables.
o It is a tentative, specific, and falsifiable statement.
o Example: "Students taught with the active learning method (IV) will have
significantly higher test scores (DV) than students taught with the traditional
lecture method."
3. Operationalization: The process of strictly defining variables into measurable factors. It defines
how a variable will be measured or manipulated.
o Example: "Anxiety" cannot be measured directly. It must be operationalized, perhaps as
"a score on the Hamilton Anxiety Rating Scale" or "heart rate measured in beats per
minute."
5. Major Quantitative Research Designs
The design is the overall strategy for answering the research question.
1. Experimental Design (The "Gold Standard" for Causation)
o Purpose: To establish a cause-and-effect relationship.
o Key Features:
▪ Manipulation: The researcher actively manipulates the Independent Variable.
▪ Random Assignment: Participants are randomly assigned to either the treatment
group (gets the IV) or the control group (does not get the IV, or gets a placebo).
This minimizes the effect of confounding variables.
▪ Control: The researcher controls the environment to isolate the effect of the IV.
o Example: Randomly assigning patients to a new drug (treatment) or a sugar pill (control)
to see if the drug causes a reduction in symptoms.
2. Quasi-Experimental Design
o Purpose: To approximate an experiment when random assignment is not possible or
ethical.
o Key Feature: Has manipulation of the IV, but lacks random assignment.
o Example: Studying the effect of a new teaching method on one intact classroom
(treatment) and comparing it to another intact classroom (control). The groups are pre-
existing, not randomly created.
3. Non-Experimental/Descriptive & Correlational Design
o Purpose: To describe characteristics of a population or to examine relationships between
variables without implying causation.
o Key Features: No manipulation of variables. The researcher simply observes and
measures what already exists.
▪ Descriptive: Seeks to describe the current state of a variable (e.g., a survey to
determine the percentage of voters supporting a candidate).
▪ Correlational: Seeks to associate two or more variables (e.g., examining the
relationship between hours spent studying and final exam grades).
o Crucial Note: Correlation does not imply causation. Just because two variables are
related does not mean one causes the other (e.g., ice cream sales and drowning
incidents are correlated because of a third variable: hot weather).
6. Common Data Collection Methods
• Surveys/Questionnaires: The most common tool. Uses closed-ended questions (e.g., multiple-
choice, Likert scales) to generate numerical data from a large sample.
• Experiments: Conducted in controlled settings (labs) or in the field, following an experimental or
quasi-experimental design.
• Structured Observations: The researcher observes behavior using a pre-defined coding scheme
to count the frequency or duration of specific behaviors.
• Secondary Data Analysis: Using existing datasets collected by others (e.g., government census
data, organizational records, large-scale national surveys).
7. The Pillars of Quantitative Research: Rigor, Reliability, and Validity
The quality of a quantitative study is judged by specific, technical criteria:
1. Reliability: The consistency and stability of a measurement tool.
o Question: Would you get the same result if you measured the same thing repeatedly?
o Types: Test-retest reliability, inter-rater reliability.
2. Validity: The accuracy and truthfulness of the measurement and the research conclusions.
o Internal Validity: The degree to which the study establishes a causal relationship. Are you
sure the IV caused the DV, and not something else? (Threatened by confounding
variables).
o External Validity: The degree to which the results can be generalized beyond the
immediate study to other populations, settings, and times.
o Construct Validity: The degree to which a test or instrument accurately measures the
theoretical construct it is intended to measure.
8. A Simplified Overview of Data Analysis
Quantitative analysis is a sequential process:
1. Data Preparation: Cleaning the data, checking for errors, and entering it into statistical software
(e.g., SPSS, R, Stata).
2. Descriptive Statistics: Summarizing and describing the basic features of the data.
o Measures of Central Tendency: Mean, Median, Mode.
o Measures of Variability: Range, Standard Deviation.
o Visualization: Graphs, charts, and frequency tables.
3. Inferential Statistics: Using statistical tests to make inferences about the population based on the
sample data. This is where hypotheses are tested.
o Tests for Relationships:
▪ Correlation (e.g., Pearson's r): Measures the strength and direction of a
relationship between two variables.
▪ Chi-Square: Tests for a relationship between two categorical variables.
o Tests for Differences:
▪ t-test: Compares the means of two groups (e.g., treatment vs. control).
▪ Analysis of Variance (ANOVA): Compares the means of three or more groups.
4. Interpretation: Determining the practical and statistical significance of the results. A "statistically
significant" result (typically p < .05) is one that is unlikely to have occurred by chance alone.
9. Strengths and Limitations
Strengths Limitations
Objective: Data is less influenced by researcher bias due to Lacks Contextual Detail: The "why" behind the numb
detachment and blinding. is often missing.
Generalizable: When done correctly, findings can be projected Superficiality: Can oversimplify complex human
to a larger population. phenomena into numbers.
Precise: Provides numerical, precise data that can be Inflexible: The design is fixed at the start and cannot
statistically tested. easily adapt to new findings.
Efficient for Large Samples: Data from surveys can be collected Artificial: Controlled settings (like labs) may not refle
and analyzed from thousands of people. real-world conditions.
Establishes Causation: Well-designed experiments are the best Can Miss the Human Element: Struggles to capture l
method for establishing cause-and-effect. experience, meaning, and emotion.
Conclusion & Key Takeaways
• Quantitative research is about measurement, quantification, and statistical analysis.
• It operates from a positivist/post-positivist paradigm, viewing reality as objective.
• It uses deductive logic to test pre-existing theories and hypotheses.
• Its primary goal is generalization from a sample to a population.
• Key designs are experimental, quasi-experimental, and correlational.
• Rigor is established through reliability and validity (internal/external/construct).
• The goal is to describe, relate, and determine cause-and-effect between variables.
The Take-Home Message: Qualitative and Quantitative research are not "better" or "worse" than each
other. They are complementary. They answer different kinds of questions. The best research often uses
a Mixed-Methods approach, harnessing the strengths of both to provide a more complete picture of the
phenomenon under study.