Experimental Research Design

Experimental Research Design

• An experimental research design involves manipulating one or more independent variables and measuring their effect on one or more dependent variables.
• This type of design is the most effective method for testing a hypothesis, as it allows for the investigation of causal relationships between variables.
• Three basic principles of experimental design are:
  • The principle of replication: repeating the experiment multiple times to increase statistical accuracy.
  • The principle of randomization: randomizing the assignment of subjects to treatment groups to eliminate bias.
  • The principle of local control: ensuring that controls are part of the test factors.

Analytical Research Design

• An analytical research design aims to understand phenomena by discovering and measuring causal relationships among them.

Research Design

• A research design is a plan that outlines the specifics of a research project, including what, where, when, how much, and by what means.
• It includes a plan for the time and cost budgets, as most studies are conducted under these constraints.

Types of Research Designs

• Exploratory research designs:
  • Also known as formulative research studies.
  • Aim to understand a problem for more precise investigation or to develop working hypotheses.
  • Emphasize the discovery of ideas and insights.
  • Methods include:
    • Literature survey
    • Experience survey
    • Analysis of "insight-stimulating" examples
• Descriptive and diagnostic research designs:
  • Descriptive research studies describe the characteristics of a particular individual or group.
  • Diagnostic research studies determine the frequency with which something occurs or its association with something else.
• Hypothesis-testing research designs:
  • Also known as experimental studies.
  • Test hypotheses of causal relationships between variables.
  • Require procedures that reduce bias, increase reliability, and permit drawing inferences about causality.

Indirect Approach

• An indirect approach disguises the true purpose of the project.
• Projective techniques are unstructured, indirect forms of questioning that encourage respondents to project their underlying motivations, beliefs, attitudes, or feelings.

Quantitative Research Design

• A quantitative research design seeks to quantify data and applies statistical analysis.
• Involves generating data in quantitative form, which can be subjected to rigorous quantitative analysis in a formal and rigid fashion.
• Aims to:
  • Describe variables
  • Examine relationships among variables
  • Determine cause-and-effect interactions between variables

Experiment vs Survey

• An experiment is an investigation in which a factor or variable under test is isolated and its effect(s) measured.
• A survey is a method of securing information concerning a phenomenon under study from all or a selected number of respondents.

Data Collection Methods

• Primary data: collected afresh and for the first time.
• Secondary data: collected by someone else and already passed through statistical process.
• Methods of collecting primary data:
  • Observation
  • Interview method
  • Through questionnaires
  • Through schedules

Data Collection through Questionnaires

• A popular method of data collection, particularly in large-scale inquiries.
• Questionnaires are sent to respondents with a request to answer the questions and return the questionnaire.
• Types of questionnaires:
  • Structured questionnaires: have definite, concrete, and pre-determined questions.
  • Unstructured questionnaires: have a general guide on the type of information to be obtained, but exact question formulation is left to the interviewer.
• Characteristics of structured questionnaires:
  • Standardized questions
  • Closed or open-ended questions
  • Limited space for respondents' comments
• Characteristics of unstructured questionnaires:
  • General guide on the type of information to be obtained
  • Exact question formulation is left to the interviewer
  • Replies are taken down in the respondent's own words.