AS Lessons 06 - 10

Question 1

Target population

Answer 1

The group who researchers are studying and want to generalise their results to

Question 2

Sample

Answer 2

A sample should be representative of the population from which it is drawn and should therefore have the same characteristics as the population

Question 3

Random Sampling

Answer 3

When every member of the target population has the same chances of being selected. The best way is to place all names in a hat and select the sample

Question 4

Evaluation of Random Sampling

Answer 4

+ If the target population is large and a large sample is drawn, then it is likely that the sample will be representative and therefore the results can be generalised
+ No researcher bias - the sample has been chosen by chance without any conscious choice
- Sometimes difficult to get full details of a target population (e.g. not possible to get the names of all women aged 20-30)
- Not all members of the target population who are selected are available or willing to take part, making the sample unreliable

Question 5

Systematic Sampling

Answer 5

A sampling strategy where participants are selected by taking every Nth person from a list. For example, make a list of the total population and then select every 6th person to take part

Question 6

Evaluation of Systematic Sampling

Answer 6

+ Far more simple than random sampling as it only requires a list, and then the researcher decides every Nth person. Random sampling requires more time and effort (put the names in a hat etc.)
- Process of selection can interact with a hidden periodic trait. If they do coincide, the sampling technique will no longer be random
- Not all selected participants will be available or willing to take part, making the sample unrepresentative

Question 7

Stratified Sampling

Answer 7

Involves classifying the population into categories and then randomly choosing a sample which consists of participants from each category in the same proportions that they are in the population. The population are divided into ‘strata’ in terms of characteristics (e.g. age, gender etc.). A sample is then chosen that reflects these characteristics (e.g. 51% female, 49% male)
Stratified samples ensure the sample is representative

Question 8

Evaluation of Stratified Sampling

Answer 8

+ All groups within a population are included, so the sample is representative of the population
- Can be very time consuming as the categories have to be identified and calculated. If you do not have details of all the people, you would struggle to conduct a stratified sample

Question 9

Opportunity Sampling

Answer 9

AKA convenience sampling
Involves selecting participants who are readily available and willing to take part. Psychologists may have easy access to a group of people, so it would be convenient to ask them to take part

Question 10

Evaluation of Opportunity Sampling

Answer 10

+ Easiest and most practical method of ensuring large samples especially when compared to stratified sampling, which is time consuming and expense
- High chance that the sample will not be representative of the target population. Sometimes people feel obliged to take part (especially when a friend asks them to), even if they do not want to, making it unethical

Question 11

Volunteer Sampling

Answer 11

Involves people volunteering to participate. The researcher will usually ask people to take part, possibly through advertisement (leaflets, posters, radio or TV broadcasts). These forms of communication means that people take notice of the information and then decide if they want to take part

Question 12

Evaluation of Volunteer Sampling

Answer 12

+ Saves the researcher time and effort. The researcher needs to construct an advertisement for the study, and then just needs to wait. This is better than other sampling methods where the researcher needs to ask people to take part and needs their full commitment
- A certain type of person tends to volunteer (enthusiastic, interested in the topic etc.), which means that there is a high chance of the sample being unrepresentative and it will not accurately reflect the target population (volunteer bias)

Question 13

Pilot Studies

Answer 13

An initial run-through of the procedures. It involves selecting a few people and trying the study out on them. It saves time and possibly money, by identifying flaws early on. It can help identify any ambiguities or confusion. Sometimes the task is too hard and the researcher may get a floor effect, because none of the participants can complete the task. The opposite is a ceiling effect, where the task is too easy and full marks are achieved a lot.

Question 14

Evaluation of Pilot Studies

Answer 14

+ A chance to make modifications and amendments
+ Good in the long run as it saves time and money
- Can be time consuming
- As it is small scale, the results may be unrepresentative
- The sample cannot be repeated - these people cannot take part again

Question 15

Experimental Designs

Answer 15

How participants are organised within an experiment

Question 16

Types of Experimental Designs

Answer 16

Independent groups
Repeated measures
Matched pairs

Question 17

Experimental Condition

Answer 17

Involves a group of people who are exposed to the independent variable

Question 18

Control condition

Answer 18

This group receives no treatment and are used as a base line to compare results

Question 19

Randomisation

Answer 19

The use of chance in order to control for the effects of bias when deciding the order of conditions.
Example: putting words in a random order to make sure a list of words is not too easy or too hard

Question 20

Standardisation

Answer 20

Using exactly the same formalised procedures and instructions for all participants - this improves the reliability of the study (the ability to repeat and get the same findings)

Question 21

Random allocation

Answer 21

An attempt to control for participant variables in an independent groups design which ensures that each participant has the same chance of being in one condition or the other

Question 22

Independent Groups Design

Answer 22

Different participants are used in each condition, therefore the groups are independent from one another. Participants are randomly allocated to each condition

Question 23

Evaluation of Independent Groups Design

Answer 23

+ Order effects (when the sequence in which the participants take part in conditions influence their performance) will not occur as there are different participants. For example, in a memory test, participants may get better with practice.
+ The chance of demand characteristics is reduced as there are different participants for each condition. There is a lower chance of them guessing the aim
+ Participants are not lost between conditions as they only take part in one condition. In a repeated measures design, participants are used for two conditions, so there is a higher chance of participants leaving (being lost)
- More participants are needed compared to a repeated measures design.
- There is a chance that the different results gained are due to individual differences rather than manipulation of the IV, because two separate groups are used

Question 24

Repeated Measures Design

Answer 24

Each participant is tested in all conditions

Question 25

Evaluation of Repeated Measures Design

Answer 25

+ There are no individual differences, so the study is more valid as we are really only measuring the effect of the IV on the DV
+ Half as many participants are needed compared to an independent groups design
- Order effects may affect the results. One way to avoid this is counterbalancing (when half of the participants do condition A then condition B, and the other half do condition B then condition A)
- Demand characteristics are more likely - the same participants are used, so it is more likely for them to guess the aim of the study, which would affect their behaviour and the data collected

Question 26

Matched Pairs Design

Answer 26

Different participants are used in all of the conditions
Participants in the two groups are matched on characteristics important to the study (e.g. age, gender, level of education etc.). Identical twins are often used

Question 27

Evaluation of Matched Pairs Design

Answer 27

+ Less risk of order effects as participants only take part in one condition (compared to repeated measures design)
+ Individual characteristics are less likely to occur as groups have been closely matched on specific characteristics (less likely to occur compared to independent groups design)
- Twice as many participants are required compared to a repeated measures design. It can be problematic in order to locate and use enough people to take part in the study
- Matching process is incredibly difficult and time consuming. Individual differences cannot be completely controlled and removed (people may have different levels of motivation and fatigue at any given time)

Question 28

Reliability

Answer 28

Refers to the consistency of a research study especially when it is repeated again and the same results are gained on both occasions

Question 29

Two types of reliability

Answer 29

External reliability
Internal reliability

Question 30

External Reliability

Answer 30

Whether a test and the results are consistent over time
The test-retest method can be used, where a study is conducted once and then again in the future. If the results are similar, the study is said to be reliable

Question 31

Internal Reliability

Answer 31

Whether a test and the results are consistent within itself
The split-half technique can be used to assess the internal reliability of questionnaires. The questionnaire is split in half and if participants score similarly on both halves, then the questions are measuring the same factors and has internal reliability

Question 32

Validity

Answer 32

If a study is measuring what it intends to measure, when referring to the aim of the study

Question 33

Types of validity

Answer 33

External validity (ecological validity)
Participant validity
Temporal validity
Internal validity

Question 34

External Validity (Ecological Validity)

Answer 34

The extent to which the findings of a study can be generalised to other settings

Question 35

Participant Validity

Answer 35

The results from the participants can be generalised to the target population

Question 36

Temporal Validity

Answer 36

The results from the study can be generalised to people in today’s contemporary society

Question 37

Internal Validity

Answer 37

When the outcome of the study is a direct results of the manipulation of the IV on the DV, and has not been affected by EV

Question 38

Categories of extraneous variables

Answer 38

Participant variables
Situational variables
Experimenter variables

Question 39

Participant Variables

Answer 39

Characteristics of the participants that may affect the DV (e.g. intelligence, age, gender, personality etc.). Matched pairs and repeated measures design can help to avoid this. However, repeated measures can lead to order effects, so counterbalancing is needed. Random allocation of participants should also ensure the groups are not biased

Question 40

Situational Variables

Answer 40

Factors in the environment where the experiment is conducted that could affect the DV (e.g. temperature, time of day, lighting). A way to resolve this is to use standardisation (making sure that all the conditions, materials and instructions are the same for all participants)

Question 41

Experimenter Variables

Answer 41

Factors to do with the experimenter that can affect the DV (e.g. personality, appearance, conduct). Standardised instructions should ensure that the experimenter acts in a similar way with all participants (follows a script, same manner and tone)

Question 42

Investigator Effects

Answer 42

Examples: observer bias, interviewer effects
Investigator characteristics (e.g. age, gender, ethnicity) may influence the results and behaviour of the participants
If investigators know the hypothesis, they may also inadvertently be biased in their interpretation of the results.
Investigator effects can be overcome by the double blind effect, when neither the participants or the investigator know the aim of the study and hopefully, the results will be more valid

Question 43

Demand Characteristics

Answer 43

Participants may guess the main aim of the research and what is expected from them. They might try to please the experimenter by giving the results they think are wanted. Or participants might try to annoy the researcher by giving incorrect results, or acting unnaturally.
It can be overcome by the single blind technique, which involves making sure participants do not know the aim, so hopefully this will not influence their behaviour - this is more difficult to accomplish in a repeated measures design

Question 44

Ethical guidelines

Answer 44

• Introduction
• General
• Fully informed consent
• Deception
• Debriefing
• Right to withdraw
• Confidentiality
• Protection of participants from psychological harm
• Observational Research
• Giving advice

Question 45

Ethics Committee

Answer 45

Made up of psychologists, staff, members of the public, and people from other disciplines and subject areas. Their job is to approve research proposals, after examining whether there are any ethical problems and whether they have been properly resolved

Question 46

Informed Consent

Answer 46

Whenever possible, investigators should inform participants of the objectives of investigations and gain their consent to take part.
The participants need to be informed about what will be required of them, the purpose of the research, their rights (to withdraw etc.).

Question 47

Three types of informed consent

Answer 47

Presumptive consent
Prior general consent
Retrospective consent

Question 48

Presumptive Consent

Answer 48

Consent gathered from people from a similar background to the participant. If they agree, it is assumed that the actual participants will also be willing to take part in the study

Question 49

Prior General Consent

Answer 49

Involves participants agreeing to be deceived without knowing how or when it will happen. If they agree, you can conduct the study knowing that you have gained their informed consent prior to the study. However, if they know they will be deceived at some in the future, they might show demand characteristics or change their behaviour

Question 50

Retrospective Consent

Answer 50

Involves asking participants after they have done the study. It could lead to their data being destroyed

Question 51

Protection from Harm

Answer 51

Investigators have a responsibility to protect participants from physical and psychological harm. The risk of harm should be no greater than in ordinary life. The study must be stopped if the investigator suspects a participant may be harmed. Participants need to leave the study the same way they entered it

Question 52

Right to Withdraw

Answer 52

At the start, all participants must be made aware that they can leave the study at any time, without having to offer explanations. It might be difficult to implement in covert observations. Participants should be made aware that they can withdraw their data at any point.

Question 53

Confidentiality

Answer 53

Data is confidential and should not be disclosed to anyone unless it has been agreed. Numbers and letters should be used instead of names if the study is published.
Confidentiality means that the data can be traced back to a name (but it should not be shared with others), but anonymity means that data cannot be traced back to a name as a name has not been provided

Question 54

Deception

Answer 54

The withholding of information or misleading participants is unacceptable.
Intentional deception over the purpose and general nature of investigators should be avoided whenever possible. Participants should not be misled without scientific or medical justification. Sometimes deception is necessary, and this is when an ethics committee approves it (with a cost benefit analysis)

Question 55

Overcoming deception through debriefing

Answer 55

What occurred in a study needs to be explained after the study. Participants also need to be told why deception was necessary. During a debriefing session, participants need to be made aware that they have the right to withdraw and to confidentiality. It also needs to allow the participant to ask questions

Question 56

Peer Review

Answer 56

The university sends out a psychologist’s completed work to other psychologists in the same field (usually experts), so that the work can be independently scrutinised. If the work is of high standard and quality, high in validity, significant and original, the work is considered for publishing, in a psychological journal etc.
The peer reviewers report on the quality of the research. Their views are considered by a research panel. The double blind peer review process occurs - the psychologists doing the review are anonymous (so the researcher does not know) and the peer reviewer does not know whose work it is
If the research does not meet high standards, the research will not be published. It could be sent back to the researcher who can correct and modify their work.

Question 57

Advantages of double blind peer review

Answer 57

No chance of bias
The reviewer would be extremely honest as they do not know the researcher

Question 58

Academic journals

Answer 58

Some are more prestigious than others.
They are expensive to buy, and many universities only buy a few a year, or subscribe to the journals online. This means the general public will not have access to the journals or the published research.

Question 59

Open Access - Online Peer Reviews

Answer 59

Some research might not be published in print but might go on through a different process called ‘open access’.
This is a process where new knowledge can be viewed online by the scientific community and the general public. The work deemed to be of good quality can be trusted and will be accepted and published. Work rated as poor quality will not be accepted and published. Readers decide whether the work is valid or not and they leave comments, however there is a possibility of people stealing your work, it could be biased, and non-psychologists may judge even if they do not understand

Question 60

Why is it important to publish research?

Answer 60

• The work can appear in international journals, meaning the research can be shared across the world
• The work can be debated and new ideas can develop from it, which could help establish new theories/research
• The scientific community will have confidence that the work is of a good quality due to peer review
• It can increase the reputation of the researcher and offer them the chance to gain funding
• The institutions (university) also look good. Many universities receive government grants for their research so the university will get more money

Question 61

Three main functions of peer review

Answer 61

• Allocation  of research funding (peer review is required to ensure the research is likely to be worthwhile)
• Publication of research in academic journals (peer review prevents the publication of irrelevant findings, unwarranted claims etc. It also improves the quality of research published, and increases the probability of weakness is being identified before publication)
• Assessing the research rating of university departments (peer review assessed the quality, so departments can be given a rating to reflect the standard of the research)