Data Collection Methods Overview

Data Collection Objectives

• Students will understand different data collection methods (self-report, tests, behavioral measures, physical measures).
• Students will learn how to use different data collection tools effectively.
• Students will be able to discuss the advantages and disadvantages of each data collection tool.
• Students will know which graph type is suitable for different datasets.

Self-Report Data

• Participants respond to researcher's questions using their own input.
• Measures how people think, feel, and act.
• Can be quantitative or qualitative.
• Examples include questionnaires, surveys, and interviews.
• Potential issues include truthfulness, accuracy of memory, and interpretation of the question itself.

Question Delivery Methods

• Self-Administered (Mail/Internet): Potential issues include interviewer bias, misinterpretation, and low response rate.
• Telephone: Potential issues include low response rate, time constraints, and socially desirable responses.
• Personal Interview: Potential issues include low response rate, time limitations, interviewer bias, and lack of anonymity.

Question Styles: Closed-Ended

• Quantitative: Participants choose from provided options.
• Example: A multiple choice or checkbox question.

Question Styles: Rating Scales

• Quantitative: Participants rate something on a numerical scale.
• Example: A Likert scale (e.g., Strongly Disagree to Strongly Agree).

Question Styles: Open-Ended

• Qualitative: Participants formulate their own responses.
• Example: An open-ended question requiring an essay response.

Question Errors

• Loaded Questions: Contain assumptions or emotionally charged language that influence the response.
• Leading Questions: Lead the participant towards a specific answer.
• Double-Barreled Questions: Ask more than one question at the same time.

Where is the Error? (Example Questions)

• Q1: "Have you stopped cheating on your exams?" - Loaded question.
• Q2: "Are you motivated to go to the gym and lose weight?" - Leading question.
• Q3: "Several experts have stated that fitness levels among Canadians are at their lowest - do you agree?" - Leading question.

Interviews

• Qualitative: Typically involve open-ended questions.
• Recording: Usually recorded and transcribed, unless not feasible or too intrusive.
• Types:
  • Informal conversational: Unguided, flexible, but difficult to summarize.
  • Semi-structured: Semi-guided, less flexible, easier to summarize.
  • Standard open-ended: Completely structured, least flexible, but easiest to summarize.

Test Data

• Instruments for assessing individual differences in various areas.
• Potential issues include the participant's state of mind on the day of the test and accurate interpretation.

Behavioral Measures

• Observation and recording of behaviors.
• Potential issues include reactivity and observer accuracy.
• Classifying the Observation:
  • Participant vs. Non-Participant: Participant directly involved in the activity or uninvolved.
  • Disguised vs. Non-Disguised: Subjects aware or unaware of the observation.
  • Direct vs. Indirect: Observation as it happens or after the fact.

Case Study (Example)

• Research Question: Investigating the rate of illegal drug use among college students.
• Setting: Researcher observes a party covertly.
• Classification of Observation: Non-participant, disguised, realism/indirect.

Physical Measures

• Measurements of bodily activity.
• Examples include equipment like scales, blood pressure cuffs, and objective tests.
• Potential issues include equipment accuracy and conductor skill (personnel administering equipment).

Data Practices

• Population: University students.
• Dependent Variable: Time spent on TikTok or Instagram.

Data Types

• Quantitative: Numerical data where a change in score represents a change in quantity (e.g., weight, age, VO2max).
• Qualitative: Categorical data where each value represents a discrete category (e.g., hair color, shoe preference, dog breed).

Organizing/Summarizing Data

• Frequency Distributions: Information on the number of observations for each variable.
• All scores are listed with a count of each score.
• Shows a data pattern.

Graphs

• Histograms: Data points are grouped into bins and bars touch each other. Good for ordinal, interval, and ratio data.
• Bar Graphs: Data points are separate bars that do not touch. Good for nominal data.
• Pie Charts: Graphical representation of the relative proportions or percentages among different categories. Good for nominal data where the proportions are important.
• Frequency Polygons: Displays data from a cumulative frequency over time using a line graph.