Research methods (P2)

Question 1

Explain how the reliability of a controlled observation can be assessed through inter-observer reliability (4 marks)

Answer 1

1) Two observers would use the same behavioural categories and discuss and agree on an interpretation of each of the social behaviours in the category system.
2) Two observers would make independent observations/tallies (of the same child at the same time/ the 5-minute sessions are filed and each observer watches and records the data for each film)
3) The two observers tally charts would be compared to check for agreement/calculate the correlation between the recordings of the two observers to determine the level of inter-observer reliability
4) Researchers generally accept +0.8 correlation coefficient as a reasonable degree of reliability

Question 2

Give one reason why collecting quantitative data could reduce the validity of this study (2 marks)

Answer 2

1) Social behaviours are complex and contextual, quantifying them will lose detail
2) A loss of detail may mean important contextual detail is missing, eg. sarcastic smile opposed to a friendly smile
3) By quantifying the social behaviours, the relative importance of the social behaviour or combination of behaviours may be lost reducing valdity.

Question 3

Describe the features of the abstract section in a scientific report (3 marks)

Answer 3

1) First section of a report
2) Brief summary of 100-300 words
3) Contains a summary of the aims, methods, results and conclusions

Question 4

Explain one way in which the researcher might deal with the deception in this study (2 marks)

Answer 4

1) At the end of the study, students should be given a full debrief, where they are made aware that the sleep data provided was manipulated.

Question 5

Describe how the researcher could have used random sampling to obtain the students for this study (3 marks)

Answer 5

1) Collect the names of all of the people in the target population (1st year students at a university)
2) put all of the students into a computer random name generator
3) select names in an unbiased manner, repeat this until desired number of participants has been obtained.

Question 6

What is a controlled observation?

Answer 6

A type of observation where participants are observed in a lab, increasing control and reliability, but decreasing ecological validity

Question 7

What is covert observation

Answer 7

A type of observation where the observer is hidden and therefore participants do not know they are being observed. While this does reduce demand characteristics, it can raise ethical issues around consent

Question 8

What is concurrent validity?

Answer 8

Occurs if a test is similar to an older test that already has well established validity

Question 9

What is counterbalancing?

Answer 9

To make half of the participant sample experience the different conditions of the experiment in one order, and the other half of the participants complete it in the opposite order

Question 10

What is falsifiability?

Answer 10

The quality of being able to be proven wrong

Question 11

What is inter-observer reliability?

Answer 11

Multiple investigators gather information separately during an observation and compare (correlate eg. Spearman’s rho) for similarity after. A correlation coefficient of +0.8 = strong reliability

Question 12

What is reliability

Answer 12

The ability for a test to be repeated and gather similar and consistent results over time

Question 13

What is a sample

Answer 13

A smaller group that aims to be representative of the entire target population

Question 14

What is test-retest reliability?

Answer 14

Completing a test multiple times and comparing the scores for similarity

Question 15

Ordinal data

Answer 15

Data that can be ordered (put on a scale)

Question 16

Nominal data

Answer 16

Categorical data eg. Boys v girls

Question 17

Interval data

Answer 17

Variables that exist on a fixed scale eg. Temperate/ time (standardized intervals)

Question 18

How can a researcher deal with the ethical issues of deception?

Answer 18

-Participants to be fully debriefed before, during and after
-Told aims of the study, how it will be carried out and any risks involved.

Question 19

When to use chi-squared test?

Answer 19

Test of difference, independent groups design, nominal data.

Question 20

Limitation of primary data?

Answer 20

Requires time and effort on the part of the researcher (to develop resources etc.) May be costly compared to secondary data which can be easily accessed.

Question 21

Evaluation of time sampling

Answer 21

-Time sampling may be easier to manage as there are likely to be many social behaviour occurring throughout the set observation time
-Time sampling is most appropriate for recording ongoing behaviours that are likely to occur in social setting eg. Conversations or playing together
-Time sampling may not be representative of social behaviours as some social behaviours that 3 year old children display may be missed, eg, a child may be playing independently when the observer is noting the behaviour, but then sharing their toys or talking to another child outside the time frame.

Question 22

When would Mann-Whitney test be used?

Answer 22

-Test of difference, independent groups design, ordinal data (ranked)

Question 23

Explain what is meant by operationalisation

Answer 23

operationalisation is the process by which a researcher defines how a concept is measured, observed or manipulated within a particular study. For example, social anxiety can be operationally defined in terms of self-rating scores, behavioural avoidance of crowded places of physical anxiety symptoms in social situations.

Question 24

Outline how you would take a stratified sample

Answer 24

1) Identify the strata
2)Calculate the required proportion for each stratum based on the size of the target population
3)Select the sample at random from each stratum
4) To do this, you can use a random selection method eg. A computer

Question 25

Define experimental method

Answer 25

The experimental method concerns the manipulation of an independent variable to have an effect on the dependent variable which is measured and states in results (observations have no manipulation of iv)

Question 26

What is a solution to the problem of order effects caused by a repeated measures design?

Answer 26

A solution would be counterbalancing. This is when half of the participants are made to do conditions in one order and the other half in the other order-this eliminates order effects//

Question 27

Difference between aim and hypothesis

Answer 27

The aim of the study tells us what the study is investigating whereas the hypothesis is a statement that predicts the relationship between the IV and DV

Question 28

Describe the purpose of carrying out a peer review

Answer 28

-To allocate research funding to projects that is worthwhile
-To make sure that research is of a good quality and is relevant
-To be able to suggest improvements so that faulty or incorrect data is not released to the public

Question 29

Define the two types of skewed distributions

Answer 29

-Positive skew: when plotted on a graph, the data has a long tail on right, most of the scores distributed on the lower end (eg. Test was too difficult)
-Negative skew: when plotted on a graph, the data has a long tail on the left, most of the results distributed on the higher end (eg. Test was too easy, as most of the students scored very high)

Question 30

Give two strengths of conducting a content analysis

Answer 30

-It has high mundane realism and external validity as what is being studied is already out there and in the real world
-It produces a large set of both qualitative and quantitative data that is easy to analyse

Question 31

Give two limitations of a content analysis

Answer 31

-Causality cannot be established as it merely describes the data
-As it only describes the data, it cannot extract any deeper meaning or explanation for the data patterns arising from

Question 32

Describe the difference between a single-blind procedure and a double-blind procedure

Answer 32

In a double-blind procedure, neither the researcher nor the participant are aware of the aims, procedures and conditions of the study. In a single-blind procedure it’s only the participant who isn’t aware of them.

Question 33

Describe the difference between unstructured and structured observation

Answer 33

An unstructured observation consists of continuous recording, where everything the researcher sees is written down, whereas structured observation has a predetermined list of behaviours and sampling methods with which the researcher quantifies their observation (eg. Number of times a participant smiles)

Question 34

Outline three things a researcher should think about when constructing a questionnaire

Answer 34

-Clarity: the researcher should make sure that it is clear what each of the questions are asking
-Analysis: the questionnaire should be written in a way that can be easily analysed
-Sequencing questions: the researcher should think about the order of questions, maybe easy ones first then harder one last to build up the confidence of participants

Question 35

Types of observation (6)

Answer 35

-Naturalistic v controlled
-overt v covert
-Participant v non participant

Question 36

Process of a scientific study

Answer 36

1)Observation of a subject
2)Formulation of theory
3)Construction of a testable hypothesis
4)Empirical testing of the hypothesis
5)Replication and validation
6)Falisfification

Question 37

Features of science

Answer 37

-Empiral- formed from direct observation rather than reasoned argument
-Objective
-Controlled (control of extraneous variables to establish cause and effect of IV/DV)
-Replication
-Hypothesis testing
-Predictability (science must have a paradigm- shared set of beliefs) Kuhn argued psychology lacked paradigms
-Paradigm shift

Question 38

Internal reliability

Answer 38

Assesses the consistency of results across items within a test

Question 39

External reliability

Answer 39

Refers to the extent to which a measure varies from one use to another.

Question 40

Split-half method

Answer 40

-Used to assess internal reliability
-Measures the extent to which all parts of the test contribute equally to what is being measurd

Question 41

Inter-rater reliability

Answer 41

Measure of external reliability. Extent to which two or more observers are observing and recording behaviour in the same way. We can assess it by comparing the results of two researchers on the same thing and how well they correlate. We can improve inter rather reliability with training, practice in a pilot study, better operationalisation of variable and ensuring that each researcher has the same ability to see the participants.

Question 42

Test-retest reliability

Answer 42

-Measure of external reliability
-Involves presenting the same participants with the same test or questionnaire on two separate occasions and seeing whether there is a positive correlation between the two. If correlation is poor then we should alter the task until it produces higher correlation. (+.80)= high reliability

Question 43

Explain how a researcher could conduct a content analysis (2 marks)

Answer 43

-Identify/devise important categories/themes
-work through observation
-count/tally the number of occurrences of each of the categories/themes