Extra Bits (Unit 1)

Question 1

What are the non-parametric inferential tests you need to know how to do?

Answer 1

• Binomial Sign test
• Chi-square
• Wilcoxen Signed Ranks
• Mann-Whitney U test
• Spearman’s Rho

Question 2

When would you use a Chi-square test

Answer 2

• Nominal data
• Independent measures

Question 3

When would you use a Mann-Whitney U test?

Answer 3

• Ordinal data
• Independent measures design

Question 4

When would you use a Binomial Sign test?

Answer 4

• Nominal data
• Repeated measures / matched participants design

Question 5

When would you use Spearman’s Rho Correlation Coefficient?

Answer 5

• Ordinal data
• Correlation

Question 6

What criteria need to be met to use a parametric (more powerful) inferential statistical test?

Answer 6

• The data has to be interval or ratio.
• The data has to have a curve of normal distribution.
• The variances should be similar.

Question 7

If p ≤ 0.05 which hypothesis should be accepted?

Answer 7

Alternative hypothesis

Question 8

If p ≤ 0.01 which hypothesis should be accepted?

Answer 8

Alternative hypothesis

Question 9

If p > 0.05 which hypothesis should be accepted?

Answer 9

Null hypothesis

Question 10

What is a type 1 error and when does it occur?

Answer 10

The significant level is too high and therefore the alternative hypothesis is accepted even though the behaviour shown was due to chance (false positive).

Question 11

What is a type 2 error and when does it occur?

Answer 11

The significance level is too low and therefore the alternative hypothesis is rejected even though the independent variable really is having a significant impact on the dependent variable.

Question 12

What type of distribution is represented by the graph below?

Answer 12

Negatively skewed distribution

Question 13

What type of distribution is represented by the graph below?

Answer 13

Normal distribution

Question 14

What type of distribution is represented by the graph below?

Answer 14

Positively skewed distribution

Question 15

In a normal distribution, where are the mean, median and mode?

Answer 15

All measures of central tendency are at the highest point if the curve.

Question 16

In a negatively skewed distribution, where are the mean, median and mode on a graph?

Answer 16

• The mode is at peak of the graph.
• The median and mean are less than the mode (to the left of the peak).

Question 17

In a negatively skewed distribution, where are the mean, median and mode?

Answer 17

• The mode is at peak of the graph.
• The median and mean are more than the mode (to the right of the peak).

Question 18

What does = mean?

Answer 18

Equal to

Question 19

What does < mean?

Answer 19

Less than

Question 20

What does «_space;mean?

Answer 20

Much less than

Question 21

What does > mean?

Answer 21

Greater than

Question 22

What does»_space; mean?

Answer 22

Much greater than

Question 23

What does ∝ mean?

Answer 23

Proportionality (a correlation has a linear property).

Question 24

What does ∼ mean?

Answer 24

Approximately

Question 25

What are the three methods that can be used to check the reliability of a test or study?

Answer 25

- Split-half method - Test-retest method - Inter-rater reliability

Question 26

Describe the split-half method.

Answer 26

- A way to test the internal reliability of a test. - Test one half of the questions and gain a score and then the other half of the questions to see if the same score is achieved in both halves of the test.

Question 27

Describe the test-retest method.

Answer 27

- A way to test external reliability of a questionnaire or a piece of research. - If the same results are achieved then the test shows high external reliability.

Question 28

Describe inter-rather reliability.

Answer 28

- A way to avoid observer bias. - Two observers consistently rate or observe the same behaviour and the two sets of ratings are correlated. - If a significant positive correlation is seen, inter-rather reliability had been established and the objectivity of the results confirmed.

Question 29

What are the names of the types of internal validity?

Answer 29

- Construct validity - Face validity - Concurrent validity - Criterion validity

Question 30

What are the names of the types of external validity?

Answer 30

- Population validity - Ecological validity

Question 31

Define face validity.

Answer 31

Whether a test appears (on the face of it) to be measuring what it intends to.

Question 32

Define concurrent validity.

Answer 32

Where a test or study measure gives the same results as another test or study that is measuring the same concept.

Question 33

Define criterion validity.

Answer 33

Refers to how much one test or measure predicts further performance on another test or measure.

Question 34

Describe the difference between representativeness and generalisability.

Answer 34

- ***Samples*** lack representativeness - If a sample is similar in make up to the target population (in terms of gender, age, ethnicity, etc…) then it can be said to be representative. - ***Results*** lack generalisability - If a sample is not representative, psychologists may be cautious before they can say that their findings can be generalised to predict the behaviour of a broader population.

Question 35

Describe the difference between demand characteristics and social desirability bias.

Answer 35

- Demand characteristics is when participants act in the way they think the researcher wants them to act after either being told or guessing the aim of the study. - Social desirability bias is when participants behave in a way that society wants or answers questions in a way that reflects society’s norms, but not necessarily accurately reflecting their true behaviour.

Question 36

Describe the difference between researcher / observer bias and researcher bias / observed effects.

Answer 36

- Researcher / observer bias can be present when collecting or analysing data. If a researcher wants to see a particular behaviour, they may ‘see it’ when it is not there. Furthermore, it is also possible for researchers to impose their bias on the interpretation of gathered data. - Researcher / observer effects is when the participant’s behaviour is influenced and changed by the researcher’s presence. The characteristics of the researcher (e.g. gender, age and race) can also affect participants’ behaviour.

Question 37

List the sections and subsections of a practical report in order.

Answer 37

- Abstract - Introduction - Method - Results - Discussion - References - Appendices

Question 38

What is included in the ‘Abstract’ section of a practical report?

Answer 38

A brief summary if the study that outlines the aim, method, participants, results and conclusions.

Question 39

What is included in the ‘Introduction’ section of a practical report?

Answer 39

- Considers the area of psychology in which the study is located and then focuses on previous research in the same area. - It will probably end with the null and alternative hypotheses.

Question 40

What is included in the ‘Method’ section of a practical report?

Answer 40

Includes all the detail necessary for someone to be able to carry out exactly the same research in the same conditions such as the sample, experimental design and procedure.

Question 41

What is included in the ‘Results’ section of a practical report?

Answer 41

- The raw data alongside verbal summaries and descriptive statistics (including measures of central tendency, measures or dispersion and graphical representations). - Inferential statistics will provide evidence for one of the two hypotheses and this will be summarised at the end of the section.

Question 42

What is included in the ‘Discussion’ section of a practical report?

Answer 42

What the study has discovered, evaluation and alternative explanations as well as suggestions for how to move the research on further.

Question 43

What is included in the ‘References’ section of a practical report?

Answer 43

All work cited must be referenced so that anyone who is reading the article will be able to locate the book or article for their own use.

Question 44

What is included in the ‘Appendices’ section of a practical report?

Answer 44

Contains materials, calculations, raw data and anything else the researcher needs to fully understand and repeat the research.

Question 45

Describe Harvard system of referencing.

Answer 45

- Author / authors (surname and followed by the initials of first names) - Year of publication of the article (in brackets) - Article title (in single quotation marks) - Journal title (in italics) - Volume of journal - Issue number of journal (in brackets) - Page range of article

Question 46

What is meant by peer review?

Answer 46

- Quality assurance checks of research carried out. - Other qualified researchers will check work before it is published to check for errors, objectivity and if valid conclusions were made. - Once published, other academics may also check and comment on the work.

Question 47

What are some strengths of peer review?

Answer 47

- Retains the credibility of new research. - Ensures validity of publifications. - Improves the reputation of psychology. - Ensures ethical guidelines are maintained.

Question 48

What are some weaknesses of peer review?

Answer 48

- Can be quite time consuming. - Reviewers may be biased. - Can’t always detect fraud or mad up data.

Question 49

List some of the nature and principles of scientific enquiry.

Answer 49

- The study of cause and effect - Falsification - Replicability - Objectivity - Induction - Deduction - Hypothesis testing - Manipulation of variables - Controls - Standardisation - Quantifiable measures

Question 50

Define the study of cause and effect.

Answer 50

When research can (to any significance level) show that one factor actually causes a change in behaviour (effect).

Question 51

Define falsification.

Answer 51

The ability, in principle, to prove a claim wrong.

Question 52

Define replicability.

Answer 52

To be able to repeat and therefore support or refute the findings from another piece of research.

Question 53

Define objectivity.

Answer 53

When a claim is a matter of fact, rather than opinion.

Question 54

Define induction and provide an example.

Answer 54

Empirical research is carried out and *then* a theory is developed to make sense of the findings. [Piliav**in** is **in**duction as he collected data on helping behaviour in the New York subway and *then* developed the arousal-cost-reward model to explain this.]

Question 55

Define deduction and provide an example.

Answer 55

A theory is developed and *then* empirical research is carried out to see if the theory is correct. [Ban**du**ra is de**du**ction as he developed social learning theory and *then* conducted his ‘bobo doll’ study to see if the evidence backed up his theory.]

Question 56

Define hypothesis testing.

Answer 56

Once a theory has been identified based on observations, then in scientific enquiry a hypothesis is formulated and this can be tested in empirical research.

Question 57

Define the manipulation of variables.

Answer 57

The independent variable must be manipulated, so that we can see the results if it is or isn’t present.

Question 58

Define controls.

Answer 58

Things imposed on experiments to ensure that results are due to the independent variable, rather than extraneous variables.

Question 59

Define standardisation.

Answer 59

The test conditions are kept the same for all participants.

Question 60

Define quantifiable measures.

Answer 60

Quantitative data, which is observable and objective, should be used to identify the impact of the independent variable.

Question 61

What are the strengths of collecting nominal data? *[Why is it better than ordinal and interval?]*

Answer 61

- Quick and easy to obtain as it is just a headcount. - Can be displayed in lie charts which can be easily made sense of.

Question 62

What are the weaknesses of collecting nominal data? *[Why is it worse than ordinal and interval?]*

Answer 62

- Can only analyse the mode of data and can’t calculate the mean or median. - Can’t analyse measures of dispersion. - Less precise as data is group into categories (we don’t know how individual participants are scored).

Question 63

What are the weaknesses of collecting nominal data? *[Why is it worse than ordinal and interval?]*

Answer 63

- Can only analyse the mode of data and can’t calculate the mean or median. - Can’t analyse measures of dispersion. - Less precise as data is group into categories (we don’t know how individual participants are scored).

Question 64

What are the strengths of collecting ordinal data? *[Why is it better than nominal?]*

Answer 64

- Can calculate the mean, median and mode as well as measures of dispersion. - Can calculate individual scores of participants and see how they differ.

Question 65

What are the weaknesses of collecting ordinal data? *[Why is it worse than nominal and why is it worse than interval?]*

Answer 65

- Worse that interval: - Ordinal data can be subjective (as people may interpret rating scales differently). - Although we can work out the rank order of particonats, we don’t always know the exact difference between individual scores. - Worse than nominal: - More time consuming and comped to analyse.

Question 66

What are the strengths of collecting interval data? *[Why is it better than nominal and why is it better than ordinal?]*

Answer 66

- Better than nominal: - Can calculate mean, median and mode as measures of central tendency as well as measures of dispersion. - Can calculate individual scores of participants and see how they differ. - Better than ordinal: - Scores can be compared directly as precise values are recorded. - The scores are more consistent as the same universal scale is used.

Question 67

What are the weaknesses of collecting interval data? *[Why is it worse than ordinal and why is it worse than nominal?]*

Answer 67

- Worse than ordinal: - Can only be used with concepts that are measurable through universal scales (can’t be used with attitudes, opinions, etc…). - Worse than nominal: - More time consuming and complex to analyse.