Descriptive vs. Inferential Statistics in Psychology
This paper provides an overview of core research methods and statistical approaches used in psychological research. It distinguishes between descriptive and inferential statistics, explaining how each applies to different research goals and population sizes. It then compares the case study method with single-subject experimental design, highlighting their respective uses and limitations. The paper goes on to define the criteria of a true experiment, including randomization and control groups, and discusses threats to internal validity. Finally, it examines quasi-experiments as a flexible alternative when true experimental conditions cannot be met, emphasizing their capacity to generate broader generalizations about larger populations.
- Introduction to Descriptive and Inferential Statistics: Contrasts two statistical approaches and their scope
- Case Study Method and Single-Subject Experimental Design: Compares two individual-focused research designs
- True Experiments: Defines true experiments and internal validity threats
- Quasi-Experiments: Explains quasi-experiments as flexible real-world alternatives
✍️ How to write this paper — guide, tools & examples ▾
What makes this paper effective
- Each section clearly defines a research concept before applying it with concrete examples, making abstract methodology accessible to readers new to the subject.
- The paper consistently uses comparison as an organizing strategy, contrasting descriptive vs. inferential statistics, case study vs. single-subject design, and true experiments vs. quasi-experiments.
- Practical examples — such as studying one classroom or a shopping mall population — ground abstract methodological distinctions in recognizable scenarios.
Key academic technique demonstrated
The paper demonstrates effective use of definitional comparison: each method is introduced with a formal definition, then immediately distinguished from a related method by explaining what it can and cannot conclude. This technique prevents conflation of similar concepts and helps the reader understand not just what each method is, but when and why a researcher would choose it.
Structure breakdown
The paper is organized into four discrete sections, each addressing a distinct research methodology. The first section contrasts two statistical frameworks. The second compares two individual-level study designs. The third defines the gold standard of experimental research and its limitations. The fourth introduces a practical alternative for real-world research settings. The progression moves from descriptive tools toward increasingly complex experimental designs, creating a logical scaffold for understanding psychological research methodology.
Introduction to Descriptive and Inferential Statistics
Descriptive statistics is a style of analysis used when the goal is to describe an entire population under study. However, the population studied must be small enough to include every case, or every subject ("Definition"). Inferential statistics, by contrast, also studies a population, but its purpose is to extend the results to a much larger population in general (Healey). In descriptive statistics, the results can be used to draw conclusions about the population studied — and only that particular population. Inferential statistics, meanwhile, allows a researcher to draw conclusions about larger groups based on the results of a study of one particular group.
Descriptive statistics can be applied when studying a population such as one particular class in a school or one group of workers, with results used to draw conclusions from only that group. For example, a study might compare girls in one class to girls in another. Inferential statistics, on the other hand, can be used when studying a population that is representative of a much larger group — for instance, using the results of a study of one class to draw conclusions about students in general. It is important that a study be constructed in a way that only supports conclusions the data actually allow. For instance, studying people in one particular shopping mall does not permit a researcher to claim that the results apply to all people at all shopping malls.
Case Study Method and Single-Subject Experimental Design
When studying groups of subjects, researchers can take two broad approaches: the case study method and the single-subject experimental design. While both deal with groups of subjects and study individuals within those groups, the single-subject design — sometimes called the "small N research design" — establishes a baseline against which individual subjects are compared. This baseline is created by the subjects themselves, observed under normal conditions. The results are then compared to the subjects' reactions during the experiment in order to draw conclusions. This method is particularly useful for testing the introduction of a new variable and observing the subjects' responses.
The case study method also studies individuals or groups within a population, but it does not create a baseline for comparison. Instead, it simply examines subjects in order to draw conclusions about their behavior and reactions. Case study methods are not intended to produce general conclusions; they deal mainly with individual cases. For instance, a case study might involve one patient and their behavior before and after a specific event. While the conclusions of such a study may be limited to the individual involved, these studies serve as useful examples, and when many are compiled together, they can form the basis for another type of research called a quasi-experiment. By connecting the results with another study, it may then be possible to draw broader conclusions.
Create your account
Always verify citation format against your institution’s current style guide requirements.