The Research Process: Formulation of Hypothesis and Research Questions

The Research Process Overview

• Social scientists follow rigorous procedures when conducting research, known as the research process.

• This process involves several stages:

  • Review of Literature and Existing Theories

  • Formulation of Hypothesis or Research Question (Focus of this week)

  • Operationalisation: includes methods, concepts, measuring concepts and sampling

  • Conducting the Research

  • Processing of Results and Analysis of Data

  • Presenting or Publication of Results

Recap: Review of Literature and Existing Theories

• The first stage of the research process is conducting a literature review.

• Purpose:

  • Provides insight into relevant theories, concepts, measurements, and methods used/developed by prior researchers.

  • It is a critical discussion of existing work on the topic, not merely a summary.

  • Facilitates linking one's own research questions, findings, and discussion to existing literature.

  • Demonstrates the credibility and contribution of the research.

• Ethical Considerations:

  • Avoid plagiarising others' work (intellectual property) by proper referencing and using software like Turnitin.

• Sources:

  • Different types of sources can be consulted: primary and/or secondary.

• Theoretical Framework:

  • The final part of a literature review involves identifying one or more theories to use as a framework for understanding relevant concepts.

Formulation of Hypothesis OR Research Question

• At this stage, the researcher must formulate either a hypothesis or a research question.

• The choice between a hypothesis and a research question typically depends on the type of research being conducted.

  • Hypothesis: Usually associated with experimental research (e.g., psychologists, criminologists).

  • Research Question: Usually associated with non-experimental research (e.g., sociologists, criminologists, historians).

• Important Note: Disciplines do not exclusively use one or the other; the choice is dictated by the nature of the research (experimental vs. non-experimental).

What are they…?

Hypothesis

• A testable statement containing an informed prediction, typically derived from a literature review.

• This prediction is tested using scientific methods.

• Example: "Brand X will have more chocolate chips per cookie than Brand Y."

• Developed after examining existing literature.

• The research's intention is to support or refute this hypothesis.

• Characteristics of a Good Hypothesis (and Research Question):

  • Clear and easy to understand.

  • Specific, with a definite focus.

  • Answerable (data collection must be possible).

  • Substantively relevant to the area of study.

• Used primarily in experimental research.

• Definition (Bryman, 2012, p.712): "An informed speculation, which is set up to be tested, about the possible relationship between two or more variables."

Research Question

• Not all social science research starts with a hypothesis.

• Some research begins simply with a research question.

• A research question is a question that the research intends to address.

• The research doesn't necessarily need to answer the question specifically but should explore it, providing detailed and analytical justifications of how and why it is or isn't answered.

• Example: "How do students use the communal areas of the college?"

• Characteristics of a Good Research Question:

  • Clear and easy to understand.

  • Specific, with a definite focus.

  • Answerable (it must be possible to collect the necessary data).

  • Substantively relevant to the area of study.

• Used primarily in non-experimental research.

Variables in Hypotheses

• Hypotheses should contain at least two variables.

• A variable is simply something that can take on different values or attributes; it is something that varies.

Independent Variable (IV)

• Definition: The variable that the researcher manipulates or changes to observe whether it has an effect on something else.

• Often referred to as the 'cause' in a cause-and-effect relationship.

• Example: In the hypothesis "background noise will have an effect on short-term memory performance," the IV is background noise.

• Conditions: The IV can have two or more conditions (specific manipulations of the IV).

  • Condition 1: No loud music (control group).

  • Condition 2: Loud rock music (experimental group).

Dependent Variable (DV)

• Definition: The variable that is being measured by the researcher.

• This is the 'effect' in a cause-and-effect relationship; it changes as a result of the researcher manipulating the IV.

• Example: In "background noise will have an effect on short-term memory performance," the DV is short-term memory performance. This is the effect being measured across different conditions of background noise.

Another Example: Gender and Puzzle Completion

• Scenario: A researcher wants to find out whether males complete a puzzle faster than females.

• Hypothesis: "Females will complete puzzles faster than males."

• Independent Variable (IV): Gender (male/female) - this is the manipulated 'cause'.

• Dependent Variable (DV): Time taken to complete the puzzle (where the effect of the change can be measured).

Null Hypothesis

• A hypothesis is refutable, meaning it is capable of being proven wrong.

• For this reason, a Null Hypothesis ($H_0$) is included in experimental research.

• Definition: A prediction that the results obtained in the experiment will be due to chance or to some other factor not covered by the experimental hypothesis.

  • It states that the IV will have no effect on the DV, and any observed change will be due to random factors or chance.

• Purpose: Used for statistical purposes to evaluate the results.

• Significance Level:

  • The probability of the null hypothesis being correct is known as the significance level.

  • In psychology, a common significance level sought is <0.05 (or $5\%$).

  • This means researchers aim to be more than $95\%$ sure that the results did not occur through chance.

  • Decision Rule:

    • For results equal to or less than $0.05$, the null hypothesis is rejected (there is less than $5\%$ probability that the results were a fluke).

    • The experimental hypothesis ($H_1$) is then accepted (there is at least a $95\%$ probability that the manipulation of the IV brought about the change in the DV).

Other Variables

Extraneous Variable

• Definition: Any variable, other than the IV, that may affect the DV.

• Researcher's Role: The researcher should try to eliminate these as much as possible because they can obscure or mask the true effect of the IV on the DV.

• Example: In the memory task with background noise, roadwork noise occurring throughout both conditions could be an extraneous variable affecting the results.

Confounding Variable

• Definition: Again, a variable other than the IV that may affect the DV.

• Distinction from Extraneous: Its effect is more systematic than extraneous variables, meaning it will only affect one condition of the IV.

• Example: Roadwork noise only heard during one condition (e.g., loud music condition) of the IV would make it a confounding variable.

One-Tailed or Two-Tailed Hypotheses

One-Tailed Hypothesis (Directional Hypothesis)

• Definition: Predicts the specific direction of the effect on the DV.

• Example: "A loud noise will reduce participants’ ability to learn information."

• Another Example: "Social pressure will increase levels of conformity."

Two-Tailed Hypothesis (Non-Directional Hypothesis)

• Definition: Predicts that changes to the IV will have an effect on the DV, but does not predict a specific direction of that effect.

• Example: "A loud noise will have an effect on participants’ ability to learn information."

• Another Example: "Social pressure will have an effect on levels of conformity."

Recap: Formulation of Hypothesis or Research Question

• After conducting a literature review, researchers need to develop either a research question or a hypothesis.

• Research Question: Used in non-experimental research; it is a question that can be answered by conducting research.

• Hypothesis: Used in experimental research; it predicts that the manipulation of the Independent Variable (IV) will have an effect on the Dependent Variable (DV).

  • Independent Variable (IV): The variable being manipulated by the researcher (the 'cause').

  • Dependent Variable (DV): The variable that changes as a result of the researcher manipulating the IV (the 'effect').

• Types of Experimental Hypotheses:

  • One-Tailed: Predicts the direction of the effect on the DV (e.g., "social pressure will increase levels of conformity").

  • Two-Tailed: Predicts an effect on the DV but does not specify a direction (e.g., "social pressure will have an effect on levels of conformity").

• Null Hypothesis: Predicts that any results obtained will be due to chance or other factors not covered by the experimental hypothesis, implying no effect of the IV on the DV.

Common Errors to Avoid

• When explaining the "Formulation of Hypothesis or Research Question" stage, remember to explain both concepts to the reader.

• Differentiate between who is more likely to formulate a hypothesis (experimental researchers, e.g., psychologists) and who is more likely to formulate a research question (non-experimental researchers, e.g., sociologists).

Reading and Further Research

• The information provided in the slides is insufficient for assessments.

• Students must expand on the content with additional research.

• Several sources are available on Teams to assist with further reading.