L1: Introduction And Examining Data Flashcards
What does a hypothesis consist of (2)?
Condition
Consequence
What is meant by a construct?
Conceptual term used to describe a phenomenon of theoretical interest.
What is an indirectly observable construct called?
Latent
Constructs must be defined in terms of… (3):
Object
Attribute
Rater entity
What is a direct causal relationship?
Linear effect
What is a mediated causal relationship?
A appears statistically to have a direct effect on B. Logically, however A influence Z and Z influences B.
When is mediation called partial?
If the effect between A and B remains significant after inclusion of the mediator.
What is a spurious relationship?
A third variable influences A as well as B.
What is a bidirectional causal relationship?
A leads to B and B leads to A, but necessarily at the same time.
What is an unanalyzed relationship?
There is a correlation between A and B.
What is meant by moderated causal relationship?
The strength and/or direction of the effect of A on B depends on the level of M.
Why do researchers explicitly model structural error?
Because they do not expect their models to perfectly explain reality.
Why use multi-item measurement (2)?
Increases validity and reliability of measures
Allows measurement assessment
What are the (2) forms of multi-item measurement?
Formative
Reflective
What is a reflective measurement model?
Direction of causality is from construct to measure and indicators are expected to be correlated.
What is a formative measurement model?
Direction of causality is from measure to construct, with no reason to expect indicators to be correlated.
In which measurement model does dropping an indicator alter the meaning of the construct?
Formative
When is a reflective measurement model used typically?
Consumer research constructs
When is a formative measurement model typically used?
Success factor research
What are the (3) characters of data?
Univariate
Bivariate
Multivariate
What are the (4) steps in assessing the type and potential impact of missing data?
Determine type of data and whether or not it can be ignored
Determine extent of missing data and decide whether variables or respondents should be deleted
Diagnose the randomness of the data
Select the imputation method for estimating missing data
What is the difference between MCAR and MAR?
MCAR means missing data is distributed randomly and can be solved without bias, whereas MAR results in a bias.
What are the (2) approaches to dealing with missing data?
Using only valid data (MAR only!)
Calculating replacement data
What is meant by outliers?
Observations with a unique combination of characteristics indicating they are distinctly different from the other observations.
Which (4) assumptions underlie most multivariate techniques?
Normality
Homoscedasticity
Linearity
Absence of correlated errors
What can a researcher do when assumptions are not met?
Apply transformations
How can a nonmetric variable be included with a set of dichtomous variables?
Dummy, but may only be included in analysis requiring only metric variables
