Lecture 2 Flashcards
Primary Data Collection
- Direct/Personal Interview
- Indirect/Questionnaire Method
- Focus Group
- Experiment
- Observations
Key Design Principles of a Good Questionnaire
- Keep it short and simple
- Decide on the type of questions
- Write the questions properly
- Order the questions appropriately
- Avoid questions that prompt or motivate the participant to say what you want to hear
- Write an introductory letter
- Write special instructions
- Translate the questions if necessary
- Pre-test the questions
Limitations of Experimental Method
- Ethical, legal, and moral concerns
- Unrealistic Controlled Environment
- Inability to Control Variables
Secondary Data Collection
- Published reports in newspapers and periodicals
- Financial Data in annual reports
- Records maintained by the institution
- Internal reports of the government departments
- Information from official publications
- Records of hospitals and health institutions
Types of Observational Studies
- Cross-sectional Study
- Case-control Study
- Cohort Study
Types of Experimental Studies
- Completely Randomized Design
- Matched-Pair Design
- Randomized Block Design
Steps in Designing an Experiment
- Identify the problem to be solved
- Determine the factors that affect the response variable
- Determine the number of experimental units
- Conduct the experiment
- Test the claim
A person, object, or item upon which treatment is applied
Experimental Unit
Experimental unit as a person; analogous to individual in survey
Subject
Serves as a baseline treatment for comparison to other treatments
Control Group
A controlled independent variable manipulated by the experimenter
Factor
The focus of a question in a study or experiment
Response Variable
Non-disclosure of the treatment an experimental unit is receiving
Blinding
Also called sampling error; the range in which the true value of the population is estimated to be
Level of Precision
Statistical measure of the number of times out of 100 that results can be expected to be within a specified range
Level of Confidence