Week 2

• What are the three types of fit that a model can be?


  Good, moderate or poor
• What is the general linear model?


  Outcomei = model + errori
• What is deviation?


  The difference between the mean and each individual data point
• What is the sum of deviations?


  0
• What is the sum of squared errors


  The sum of the squared deviations
• Why do we use variance?


  Because the sum of squared errors is dependent on the number of items and the variance is not
• Var(x) = 


  SS/n-1
• what is the standard deviation equal to 


  The sqrt of the variance
• What do the SS, var(x) and sd all represent


  the fit of the data, the variability of the data and how well the mean represents the observed data
• Test statistic = 


  variance explained by the model / variance not explained by the model
• constructs 


  hypothetical entities created from theory and speculation/hypothetical attributes that help explain or predict behaviour in a theory
• why might operational definitions not always be accurate

  may leave out parts that are or include parts that are not related to the construct
• explain validity


  whether the test is measuring what it is supposed to measure
• what are the types of validity

  face, concurrent, predictive, construct, convergent, divergent
• what is face validity

  whether it looks like its measuring the right thing
• what is concurrent validity

  does the new measure produce similar results to the old measure
• what is predictive validity

  can it accurately predict behaviour
• what is construct validity

  does the measurement of the variable behave in the same way as the variable itself
• what is convergent validity

  if two methods are used and compared, if strong relationship exists it is valid
• what is divergent validity

  two measures used on two separate constructs

  convergent validity established within the construct

  then little or no relationship between the constructs found
• define reliability


  do the measures produce the same results if repeated
• what can reduce reliability

  • observer error - human error
  • environmental changes
  • participant changes
• what are types of measurements of reliability

  • successive measurement - test-retest
  • simultaneous measurement - inter-rater
  • internal consistency - if different components produce the same result