Week 2 - Operationalisation of Constructs Flashcards
What are the 4 goals of science?
- Description (measurement of constructs)
- Prediction (relationship between constructs)
- Understanding (when and why does relationship exist?) - Control (can we use this to change things?)
What are the 4 criterion for scientific evidence?
- Empirical
- Objective
- Systematic
- Controlled
What are the two types of research?
- Basic vs Applied (general to specific)
- Laboratory vs Field (controlled vs naturalistic)
What is the Popperian scientific method?
- Karl Popper (1902-1994)
- FALSIFICATION IS KEY
- Observation > question > hypotheses > predictions > experiments > hypotheses either supported or rejected
What are some questionable research practices?
- P Hacking (manipulating data to ensure p is <0.05
- Harking (hypothesising after results are known)
How to write out hypotheses:
- Typically “if, then” structure
e. g., “IF participants are in a happy mood, THEN they will be more likely to help someone else” - must be precise, testable, falsifiable
What are IV’s and DV’s?
IV = the cause DV = the effect
What are the 4 elements of the experimental method?
- Manipulation of Independent Variable
- Measurement of Dependent Variable
- Random Assignment to Condition
- Control Over Extraneous Variables
How to check on manipulation:
- PILOT TESTING (seperate study created to test manipulation)
- MANIPULATION CHECKS (measurement conducted during study to check whether IV has had expected effect)
- INTERNAL ANALYSES (based on manipulation check, only use participants for whom the IV ‘had the desired effect’ - random assignment no longer involved)
What is translation validity?
“the closeness with which the study’s intended meaning of constructs matches their operationalisation”
- A type of Construct Validity?
- Hate = fMRI results; rat hunger = time since feeding
- Constructs are unmeasurable; all operationalisations may be invalid (but correlated).
How to operationalise a DV with behavioural measures:
- Measures of overt behavior (frequency, rate, speed,
duration, latency, extent, intensity etc.) - Behaviouroid measures (intentions)
- Physiological measures
- Indirect measures (reaction time, recall)
How to operationalise a DV with verbal measures:
- Questionnaires
- Interviews
- Rating Scales
What are the advantages to verbal measures?
- Easy to Use
- Face Validity
- Can look at more aspects of DV
- Subtle Distinctions can be Measured
What are the disadvantages of verbal measures?
- too indirect?
- influenced by social desirability
- participants may try to give ‘correct’ answers
- questions may be difficult to understand
- less impactful and involving for participant
Pros and cons for using your own scales?
Pros:
- often more focussed, precise for question under test
- seems relevant to participants
Cons:
- reliability, validity untested
- using existing tests helps build research literature
What is sensitivity in research?
Sensitivity relates to the test’s ability to identify positive results.
are you getting precise measurements of small difference?
What is restriction of range in research?
using dichotomous outcomes - ceiling or floor effects? floor effect (sometimes called a “basement effect”) occurs when there is some lower limit on a survey or questionnaire and a large percentage of respondents score near this lower limit. The opposite of this is known as a ceiling effect.
What is demand characteristics in research?
- reactivity, social desirability
What is internal consistency in reliability?
- the items of any scale created all measure the same thing
- assesses the correlation between multiple items in a test that are intended to measure the same construct
What is inter-rater reliability?
- if using judges/raters, are they reporting that they see the same thing?
- the extent to which two or more raters (or observers, coders, examiners) agree. It addresses the issue of consistency of the implementation of a rating system
What is construct validity?
the extent to which the measure ‘behaves’ in a way consistent with theoretical hypotheses and represents how well scores on the instrument are indicative of the theoretical construct.
What is convergent validity?
how closely the new scale is related to other variables and other measures of the same construct. Not only should the construct correlate with related variables but it should not correlate with dissimilar, unrelated ones.
What is discriminant validity?
demonstrated by evidence that measures of constructs that theoretically should not be highly related to each other are, in fact, not found to be highly correlated to each other.
What is Criterion-related validity?
indicates how well the scores or responses of a test converge with criterion variables with which the test is supposed to converge
