Research Methods

Independent variable

The variable researcher changes

Dependant variable

The variable measured by the researcher

Hypothesis

Precise, testable statement about what the researcher thinks/expects will happen

Directional hypothesis

Has a specific outcome that will be in a certain direction

(IV) will score significantly higher on (DV) than (IV)

Non-directional hypothesis

There will be a difference but will not be in a specific direction

There will be a significant difference between (IV) and (IV) on (DV)

Null hypothesis

Nothing will happen, no difference

Experimental hypothesis

Something will happen

Covariables

Is one of 2 variables measured to see if there is a relationship between them

Operationalisation

Means clearly defining exactly how a variable is measured or manipulated in a study

Stages to writing a hypothesis

1. Choose the appropriate hypothesis (directional or non)

2. Is it an experiment or a correlational

3. Identify operationalised IV/DV

4. Follow writing frame - write it

Random Sampling

Every member of the target population has an equal chance of being selected

+: No researcher bias

-: Freak bias, unrepresentative

Volunteer Sampling

People choose themselves to take part

+: Easy

-: Miss out on a certain type of a person, volunteer bias

Opportunity Sampling

Select people who are available and willing to take part at the time

+: Quick, easy

-: Unrepresentative

Systematic Sampling

Select participants from an ordered list using a fixed interval

+: No researcher bias

-: Unrepresentative, freak bias

Stratified Sampling

The proportion of each group in the sample should match its proportion in the target population

+: Representative as it includes all groups

-: Time consuming

Independent groups

When 2 separate groups of participants experience 2 separate conditions within the experiments

All participants experience one IV only

+: Reduce demand characteristics as only take part in one condition, quick and easy compared to matched pairs, no order effects

-: Large participant variables

Repeated measures

All participants experience all conditions of the experiment

+: Removes participant variables, quicker and easier than matched pairs design

-: Order effects e.g. boredom or improving

Counter-balancing

Where participants experience conditions in different orders. Half does condition 1 first then condition 2. The other half does it the other way

Matched pairs design

Participants are paired together on a variable relevant to experiment. 1 participant from each paired allocated to each group. Participants only take part in one variable

+: Reduce participant variables, no order effects

-: Time consuming, participant variable

Method/methodology

How the research is carried out.

e.g. experiments, observations, case studies, self report (questionnaire/interview), correlations, content analysis

Laboratory experiment

An experiment carried out in a controlled environment where the researcher manipulates the IV and measures the effect on the DV

+: Easier to repeat which increases validity

-: Lacks generalisability (not like everyday life)

Field experiment

An experiment carried out in a natural/real-life setting where the researcher manipulates the IV and measures the IV and measures the effect on the DV

+: More valid, more authentic

-: Ethical issues, lose control of CVs and EVs

Quasi-experiment

An experiment where the IV is based on a pre-existing difference between participants, such as age, gender or a psychological characteristic, rather than being manipulated by the researcher

+: Controlled conditions like lab

-: Researcher cannot randomly allocate participants to conditions (may be cofounding variables)

Natural Experiment

An experiment where the IV occurs naturally through an event and is not manipulated by the researcher. The researcher measures its effect on the DV

+: High external validity

-: Rare so reduces opportunities for research, may not be randomly allocated to experimental conditions

What makes good psychological research

• Validity

• Reliability

• Representativeness/Generalisability

• Ethical Issues

• Usefulness

Reliabilty

How consistent a measuring device is

Validity

The extent to which an observed effect is genuine (truthful/accurate)

Factors affecting validity : Poor Operationalisation

Researcher has not clearly defined the variables they are studying and has not developed a valid method for measuring those variables

(using a valid method to measure a variable that doesn’t match what you want to study)

Reduce by : Ensure IV/DV detail (operationalise)

Factors affecting validity : Participant Variable

Characteristics of individual participants that might influence the outcome of the study

(Difference in participants e.g. age, gender, mood, intelligence)

Reduce by : Repeated measures

Factors affecting validity : Order Effects

In a repeated measures design a cofounding variable arising from the order in which conditions are presented

(The order of tasks affects participants response or performance)

Reduce by : counter balancing, matched pairs or independent groups

Factors affecting validity : Demand Characteristics

Behaviour changing

(Participants change behaviour)

Reduce by : Deception, field experiment

Factors affecting validity : Ecological Validity

Extent to which the tasks, setting and behaviours studied reflect those found in everyday life

(If research findings can be applied to real life)

Reduce by : Field experiment

Factors affecting validity : Social Desirability

A tendency for respondents to answer questions in such a way that presents themselves in a better light

(lie to appear socially desirable)

Reduce by : Anonymous

Factors affecting validity : Leading Questions

A question which because of the way it is phrased suggests a certain answer

(Question guides participants towards a specific response)

Reduce by : Don’t ask them

Factors affecting validity : Investigator Effect

Any effect of the investigators behaviour on the research outcome

(The researchers behaviour affects results)

Reduce by : double blind study

Factors affecting reliability : Standardisation

Using exactly the same formalized procedures and instructions for all participants in a research study so as to avoid investigator effects caused by different instructions

Factors affecting reliability : Inter-Rater Reliability

Correlating the judgements of two or more ratings of behaviour, when using a rating scale. Can happen in a questionnaire or interview when behaviour has been rated or in an observation when behaviour has been rated

Factors affecting reliability : Test Re-Test

find it out

Ethical Issues

Concerns about whether psychological research protects participants rights, privacy and wellbeing

DRIPP

Deception

Right to withdraw

Informed consent

Protection from harm

Privacy

Deception

An ethical issue where a participant isn’t told the true aims of a study and thus cannot give truly informed consent

How to deal : Debrief by telling participants true aims of the study

Right to Withdraw

Participants should have the right to withdraw from participating in a research study if they are uncomfortable with the study

How to deal : Reassure them, provide counselling

Informed Consent

Participants must be given information concerning the nature and purpose of the research and their role in it so they can make a decision on whether to participate or not

How to deal : Consent form

Protection from Harm

Participants should not be placed at any more risk than they would be in their daily lives and should be protected from physical and psychological harm

How to deal : Debrief where they tell the true aims

Privacy

A zone of inaccessibility of mind or body and the trust that this will not be invaded

How to deal : Anonymous