Week 1: Intro & Key issues

Question 1

What are the stages of Popper’s Hypothetico-Deductive model?

Answer 1

• theory
• hypothesis
• operationalisation of concepts
• selection of participants
• survey/experimental design
• data collection
• data analysis
• findings

Question 2

What are the two sources of research ideas according to Popper (1972)?

Answer 2

• causal observation where a new phenomenon is spotted and decided to be worthy of investigation
• from previous research e.g. wanting to replicate findings, testing an idea in a new context

Question 3

What do surveys do?

Answer 3

measure variables as they naturally occur

Question 4

What do experiments do?

Answer 4

manipulate variables to isolate their effects

Question 5

What is systematic variation?

Answer 5

the variation that can be explained by the model (the statistic)

Question 6

What is the test statistic?

Answer 6

variance explained by the model divided by variance not explained by the model (effect/error)

Question 7

What is unsystematic variation?

Answer 7

the variation that cannot be explained by the model

Question 8

What is type I error?

Answer 8

• hasty rejection of the null hypothesis (a ‘false positive’)
• conclude there is an effect when there is none

Question 9

What is type II error?

Answer 9

• hasty rejection of the alternative hypothesis (a ‘false negative’)
• conclude there is no effect when there is one

Question 10

What is the typical alpha value in psychology?

Answer 10

0.05

Question 11

What is the typical beta value in psychology?

Answer 11

0.20

Question 12

What error do alpha values measure?

Answer 12

the probability of making a type I error
- measure the chance of saying there is an effect when there isn’t one

Question 13

What error do beta values measure?

Answer 13

the probability of making a type II error
- measure the chance of saying there is no effect when there is one

Question 14

What do effect sizes attempt to address and what do they measure?

Answer 14

attempt to address type I errors
- an effect can be significant but too small to be practically meaningful
- referred to as the magnitude of statistical effect found
- measures the size of relationship found

Question 16

what are the values for pearson’s r small, medium, and large effect sizes?

Answer 16

• small: 0.10
• medium: 0.30
• large: 0.50

Question 17

what are the values for Omega small, medium, and large effect sizes?

Answer 17

• small: 0.10
• medium: 0.30
• large: 0.50

Question 18

what are the values for Eta-Squared small, medium, and large effect sizes?

Answer 18

• small: 0.01
• medium: 0.059
• large: 0.138

Question 19

What error does power analysis attempt to control for?

Answer 19

Type II errors
- tells us the ‘strength’ of the statistical test to find an effect is there is one to find

Question 20

What are the 2 approaches to running a power analysis?

Answer 20

• A priori: before data collection. tells us sample size needed to find an effect if there is one
• post-hoc: power estimated after data collection and statistical analysis

Question 21

how is the mean measured?

Answer 21

add up all scores and divide by the number of scores/participants
- gives us an indication of the central tendency of a dataset

Question 22

How is the variance calculated?

Answer 22

• sum all the squared differences divided by the number of scores/participants minus one

Question 23

How is the standard deviation calculated?

Answer 23

• the square root of the sum of all the squared differences, divided by the number of scores/participants minus one.
• square root of the variance

Question 24

What are parametric statistics?

Answer 24

make assumptions about the data
- normally distributed
- homogeneity of variance
- usually only for ratio/interval data
- used for e.g. group differences in equally sized groups

Question 25

What are non-parametric statistics?

Answer 25

make no assumptions about the data - violation of normality assumptions (e.g. if data are very skewed/sparse) - used if you have ordinal data - or where small group sizes exist

Question 26

What are the 4 key principles of research integrity

Answer 26

- **honesty** in all aspects of research - **accountability** in the conduct of research - **professional courtesy and fairness** in working with others - **good stewardship** of research on behalf of others

Question 27

What is the replication crisis (Ioannidis, 2005)?

Answer 27

concerns regarding the reliability of research findings, suggesting many findings are false due to **low statistical power and bias** - when attempting to replicate 100 studies, only 36% of results could be replicated - effect sizes in replications were smaller than the original studies - more 'suprising' findings were less likely to be successfully replicated - social psychological findings were less likely to replicate than those in cognitive psychology

Question 28

What is **HARKING**?

Answer 28

hypothesising after the result is known

Question 29

What is P-hacking?

Answer 29

"p-hacking" refers to the practice of manipulating data analysis or research procedures to achieve statistically significant results (p < 0.05) where none would otherwise exist