Descriptive Research

1
Descriptive Research

• Jesse Fletcher
• CSC426 Values in Computer Technology

2
Agenda

• Descriptive Research Designs
• Using Checklists and Rating Scales
• Practical Application
• Interpreting Data in Descriptive Research
• Some Final Suggestions

3
Descriptive Research Designs
Approaches that yield quantitative
information that can be summarized through
statistical analyses.
4
Observation Studies

• Focus on a particular aspect of behavior
• Behavior must be qualified
• Considerable Advanced Planning
• Meticulous Attention to Detail
• Time Consuming
• Find Help

5
Observation Studies - Cont

• Strategies
• Precise Behavior Definition
• Divide Time by Segments
• Rating Scales
• Multiple Raters
• Training for the Raters

6
Correlational Research
Examines the extent to which differences in
one characteristic are related to the differences
in one or more other characteristics
7
Correlational Research

• What is a Correlational?
• Can Scatterplots Help?
• What is the Line of Regression?
• How Does Correlation Coefficient Help?
• Beware Faulty Logic!!!

8
Developmental Designs
How does a particular characteristic change as
people grow old?
9
Developmental Designs

• Cross-Sectional Study
• Different Age Groups Sampled
• Disadvantages
• Environmental Conditions
• Correlations Between Age Groups Invalid

10
Developmental Designs - Cont

• Longitudinal Study
• Single Group Over Time
• Disadvantages
• Time
• Practice

11
Survey Research
Acquiring information about one or more groups by
asking questions and tabulating the answers
12
Survey Research

• Summarize Responses
• Draw Inferences
• Capture Fleeting Moment In Time
• Self-Report Data - Data May be False

13
Survey Research - Cont

• Face-To-Face and Telephone Interviews
• Likeable and Friendly Interviewers
• Interviewers May Clarify Ambiguous Answers
• Structured
• Higher Response Rate
• Semi-Structured
• Less Time Consuming and Cheaper

14
Survey Research - Cont

• Questionnaires
• Cheaper, Large Collections, Anonymous
• Disadvantages
• Low Return Rate
• Sample Could Be Impacted
• Questions Are Fixed - Must Be Right First Time

15
Using Checklists/Rating Scales

• Checklists
• List of behaviors, characteristics, etc that
  researcher is investigating
• Rating Scales
• Used to evaluate behavior, attitude, etc

16
Practical Application

• Planning and Conducting Interviews
• Review Guidelines for Qualitative Research
  Interviews
• Ensure Questions Can Be Quantified, But
• Pilot-Test The Questions
• Single Ideal
• Controversial Questions?
• Clarifying Questions

17
Practical Application - Cont

• Constructing/Administering a Questionnaire
• Short, simple, clear, unambiguous language
• Avoid Unwarranted Assumptions
• Consistency
• How Will I Code Answers
• Respondents Task Should Be Simple
• Clear Instructions

18
Practical Application - Cont

• Constructing/Administering a Questionnaire
• Rational For Unclear Items
• Attractive and Professional Looking
• Pilot Test
• Double Check That Your Needs Are Met

19
Practical Application - Cont

• Maximizing Return Rates for Questionnaires
• Rates Average Less Than 50
• Timing
• Good First Impression
• Motivate Potential Respondents
• Self-Addressed Stamped Envelope
• Offer the Results
• Be Persistent, Gently!

20
Practical Application - Cont

• Computerizing Data Collection
• Directly Enter Data During Observations
• Use Computer As Tape Recorder
• Peripheral Devices
• Questionnaires on Computer
• Automated Monitoring of Data
• Use Internet for Data Collection

21
Practical Application - Cont

• Choosing A Sample
• Segment Represents Population
• Sampling Designs
• Probability Sampling
• Nonprobability Sampling

22
Practical Application - Cont

• Probability Sampling
• Simple Random Sampling
• Stratified Random Sampling
• Proportional Random Sampling
• Cluster Sampling
• Systematic Sampling

23
Practical Application - Cont

• Nonpropability Sampling
• Convenience Sampling
• Quota Sampling
• Purposive Sampling

24
Practical Application - Cont

• Sampling of Large Populations
• Sample Must Represent Population
• Quality In Assists Quality Out
• Quality of Sample Critical

25
Practical Application - Cont

• Sufficient Sample Sizes
• Text Book Lists Some General Rules
• Be Safe, Find a Statistics Book
• Bias in Sampling
• Has the Randomness Been Disturbed?
• Acknowledge Bias When Present
• Complete Population Analysis

26
Interpreting Data

• Data By Itself is of Little or No Value
• Do Not Lose Site of the Problem
• Extract Meaning

27
Sage Advise

• There are three kinds of lies lies, damned lies
  and statistics. - Twain attributed this to B.
  Disraeli
• It has long recognized by public men of all kinds
  ... that statistics come under the head of lying,
  and that no lie is so false or inconclusive as
  that which is based on statistics. - H. Belloc
• Figures don't lie, but liars figure. - Samuel
  Clemens (alias Mark Twain)
• If your experiment needs statistics, you ought to
  have done a better experiment - Ernest Rutherford

28
Q A