Week 11 - Uncertainty Management (1st Half Only) Flashcards

1
Q

What is uncertainty?

A

Things we can’t be 100% confident about

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is probabilistic determinism?

A

Establishes that there are some randomness in our findings - the relationships we’re interested in are affected by many things, additional causes

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is methodological uncertainty? and how do we manage it?

A

Related to the confidence we have that our research design and procedures allow us to answer the research question

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is external vs internal uncertainty? What are they produced by and reduced by?

A

Internal: WITHIN a particular study - what else might explain these findings

External: To what extent are these findings true BEYOND this study

Internal
Produced by: lack of control
Reduced by: experimental control

External
Produced by: sampling error and naive empiricism
Reduced by: appropriate sampling and theory development

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

How does methodological uncertainty compare to validity?

A

Validity is a quality of the study itself so does not change

BUT methodological uncertainty belongs to the consumers of research - and can thus change over time as KNOWLEDGE AND UNDERSTANDING GROWS

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is statistical uncertainty?

A

Design and data collection techniques do NOT help minimise it - this is why we do STATISTICS in order to measure the uncertainty

TWO TYPES: descriptive and inferential

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is descriptive uncertainty?

A

Descriptive: not all participants provide exactly the same response

Arises from the fact that psychologists tend to make multiple observations and these observations produce different data

Differences BETWEEN (individuals/groups)
Differences WITHIN (individuals over time)
MEASUREMENT ERROR

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is inferential uncertainty?

A

Psychologists want to make inferences about a population based on data from a sample

Affected by:
‘Signal’ - DV/IV relationship under investigation
‘Noise’ - random variances
The sample size

All contribute to calculating the p value

Higher the p value (closer to 100%) there is greater uncertainty that the effect is ‘genuine’

How well did you know this?
1
Not at all
2
3
4
5
Perfectly