INFO 370 - L05 - October 13, 2004
Notes By: Prins, Fortier


Recording Observations (Measuring)
    > Obtrusive / Unobtrusive (Does not know you are studying them)
    > Naturalistic / Experimental
    > Participant / Non-Participant

Data Collection Methods
    > Non-Participant
        - Observation
        - Surveys
        - Interviews
        - Think-aloud
        - Journals
    > Participant
        - Ethnography
        - Focus Groups
        - Participatory action research

Method of Recording
    > Memory
    > Note-Taking
        - Use of recording sheet
    > Logs / Transcripts
    > Audio-recording
    > Video-recording

Asking Questions
    > Closed-ended
    > Open-ended

 	
Examples						
    > For each of the following variables write:
        - An open-ended question
        - A close-ended question
            * Level of expertise in Web searching
            * Perception of the accuracy of news websites
            * Attitude toward illegally sharing music files

Observation
    Examples
    > How frequently do students express frustration with Internet search results?
    > Do more students fall asleep in class when the instructor is a woman rather than man?

Coding of Text
    Definition: The process of analyzing text according to sets of categories
    Examples:
        - So, what do you think about the Internet (in an open-ended interview)
	    - Analysis of email messages between classmates

Triangulation
    > Using more than one measure of the same variable
    > Using more than one method of data collection

Level of Measurement
    > The mathematical precision with which the values of a variable can be expressed
    > It determines the teype of statistics one can use with the variable
    > Any variable is composed of 2 or more categories or attributes
        - Sex (male/female)
        - Country of Birth (USA, China, Peru)
    > Level of measurement refers to how the categories of the variable relate to one another

Nominal
    > Measuring a variable at this level involves naming the calibration units
        - (1) = Male ? Value Label
        - (2) = Female ? Value Label
        - Sample Data: 2 2 1 1 2 1 2 1

Ordinal
    > Units arranged by a logical order of rank
    > No assumption that the distances between each calibrating unit are equal
    > Age (# of years)
        - (1) 18-21
        - (2) 22-30
        - (3) 31-45
        - (4) 46-65

Interval
    > Values designate quantity at equal distances
    > No absolute zero
    > Example: Temperature

Ratio
    > Specifies an equal distance between each successive calibration
    > Zero - a pint at which the variable does not exist
        - In reality, no subject may ever be zero, and an upper limit may exist
    > Examples: Age, Height

Interval or Ration Levels
    > Precise averages can be calculated
        - What is the average sex of students at UW?
    > More powerful and sophisticated techniques of analysis are available
    > Can be converted to ordinal or nominal level but not vice versa

Grinter Reading
    > Interviewed 16 people
        - 4 UK / 12 USA
    > Exploratory -- no hypothesis
    > From Sheet He Handed Out:
        - Sex (Categorical)
        - Age (Ratio)
        - Years of IM (Ratio)
        - Residence (Categorical/Binomial)
        - Internet Access (Categorical)
        - Share or Own PC (Categorical)
        - Reported IM use/day in hours (Ordinal)
        - Reported # IM Buddies per Session (Ordinal)
    > Talked about technology choices
    > Questions of interoperability
    > Questions of peer pressure
    > QUestions of Social Congregation
    > Domestic Ecologies
    > Privacy Management
        * What is being said
        * Who is in and out of your group of friends
# END #