Summary: Arm-B

Read the summary and the most important questions on ARM-B

• 1 ARM beginselen

  This is a preview. There are 11 more flashcards available for chapter 1
  Show more cards here

• What are summated scales?

  A type of assessment instrument comprising a series of statements measuring the same construct or variable to which respondents indicate their degree of agreement or disagreement

• What is the structured way to multivariate model building?

  1. Define the research problem, objectives and multivariate technique to be used 
     
  2. Develop the analysis plan
  3. Evaluate the assumptions underlying the multivariate technique 
  4. Estimate the multivariate model and assess overall model fit 
  5. Interpret the variate 
  6. Validate the multivariate model 

• What are reflective measurement models?

  The direction of causality is from the construct to measure --> high level of blood-alcohol, ability to walk in a straight line, and high level of breath alcohol. 
  

  • Indicators are expected to be correlated. 
  • Dropping an indicator of the measurement error does not alter the meaning of the construct. 
  • Takes measurement error into account at the item level. 
  • Typical for consumer research constructs (attitude and norms).  

• What are formative measurement models?

  The direction of causality is a form of measure to construct. --> consumption of beer, consumption of wine, consumption of hard liquor. 
  

  • No reason to expect indicators to be correlated. 
  • Dropping an indicator form the measurement model may alter the meaning of the construct (als je wijnconsumptie weg haalt, terwijl de person alleen maar wijn drinkt). 
  • Statistical tests of reliability and validity do not make sense. 
  • Based on multiple regression. 
  • Typical for success factor research --> How successful is an organization? 

• 2 Factor Analysis

  This is a preview. There are 7 more flashcards available for chapter 2
  Show more cards here

• What are the seven stages of factor analysis?

  1. Objectives of factor analysis
     
  2. Designing a factor analysis
  3. Assumptions of the factor analysis
  4. Deriving factors and assessing the overall fit 
  5. Interpreting the factor 
  6. Validation of the factor analysis 
  7. Additional uses of factor analysis results 

• What are the steps of stage 1 (Objective of factor analysis)?

  • Research problem 
    
  • Specifying the unit of analysis (Q-factor analysis = combines people into different groups) and (R-factor analysis = analyzes a set of variables to identify the dimensions that are latent) 
  • Data summarization (goal = defining a small number of factors that adequately represent the original set of variables) 
  • Data reduction 
  • Variable selection 

• What are the steps of stage 3 (Assumptions of factor analysis)?

  • Basic assumption: some underlying structure does exist in the set of selected variables 
    
  • Homogenous sample 
  • Observed patterns are conceptually valid and appropriate to study with factor analysis 
  • Some degree of multicollinearity is desirable 
  • Data matrix has sufficient correlations to justify the application of factor analysis 
  • No substantial number of correlations higher than 0,30
  • Partial correlation is high, indicating no underlying factor
  • Exception: High correlation as indicative of a poor correlation matrix 
  • Bartletts test of sphericity 

• What are the steps of stage 4 (Deriving factors and assessing overal fit)

  1. Variance partitioning (Verteilung) of a variable
     

  Variance = value that represents the total amount of dispersion of values for a single variable about its mean 
  

  • There are three types of variance: 
  • Common variance (that variance in a variable that is shared with all other variables, represented by derived factors) 
  • Specific variance (= unique variance) (that variance associated with only a specific variable)
  • Error variance = due to unreliability in the data-gathering process, measurement error or a random component in the measured phenomenon cannot be explained by the correlation 

  
  Component analysis or common factor analysis 

• What are the two criteria for the selection of a factor analysis?

  1. The objective of the factor analysis 
     
  2. The amount of prior knowledge about the variance in the variables 

• What are the steps of stage 5 (interpreting the factor)

  • Factor loadings are the means of interpreting the role of each variable plays in defining each factor 
    
  • Orthogonal factor rotation: axes remain at 90 degrees (Quartimax, Varimax, and Equimax) 
  • Oblique factor rotation: axes are rotated (allow correlated factors instead of maintaining independence between the rotated factors