Statistics (1 of 
          5)
  EXAM 1 COVERS MATERIAL PRIOR TO THIS 
  CHAPTER/LECTURE
             Statistics (1 of 
             5)
    Statistical Analysis: Aims
    “Quantitative data can be collected within all “five P” data categories: 
    they  may be collected directly (e.g., as errors or preference rankings), or 
    they  may be derived from more complex data (e.g., interaction events 
    derived  from logging or eye tracking data, or features of artifacts). These 
    are the  “dependent variable” values resulting from an experiment. 
    Examples:
             Statistics (1 of 
             5)
    Statistical Analysis: Aims
    The independent variable is the set of conditions that the experimenter 
    has  defined and has control over. Examples of independent variables 
    that might  have been associated with experiments producing the 
    dependent variables  are as follows:
    The aim of the analysis is to determine what effect (if any) the values of 
    the  independent variables have had on the values of the dependent 
    variables.
    We want to find out if different values of the dependent variables can 
    be  attributed to the different values of the independent variable.
             Statistics (1 of 
             5)
    Statistical Analysis: Getting an Initial Overview of the Data
    “Note that it is useful to present and analyze “errors” (i.e., trials that 
    have  an incorrect answer) rather than “accuracy” (i.e., trials that have 
    a correct
    answer). Doing so means that a “high” measure in either type of  
    performanc
    data (high response time, high errors) implies poor performance and a 
    “low”  measure implies good performance. This consistency in 
    interpretation  makes performance bar charts easier to read and compare. 
    For example”:
             Statistics (1 of 
             5)
    Statistical Analysis: Getting an Initial Overview of the Data
    “A statistic is a number that is calculated from a set of numbers and 
    that  characterizes an aspect of that set of numbers (e.g., mean, 
    standard  deviation, sum of the squares, etc.).
    The first step in creating useful statistics is to condense the raw data 
    into a  form that is meaningful to the research question – we do this 
    using  aggregation, the process of taking a set of numbers and 
    representing it as  one summary statistic, usually by taking the:
    Mean, Median, Mode, Min, Max, Standard Deviation or Variance, 
    Range.  When would each of the above summary statistics be useful?