Research Methods

Aim

The reason for the investigation taking place

Hypothesis

A prediction of the outcome of an experiment/study

Directional hypothesis

Predicts the effect of the independent variable on the dependent variable

Non-directional hypothesis

Doesn’t predict the direction of the difference or relationship

Independent variable

The variable that is changed

Dependent variable

The variable that is measured

Operationalise

Turning abstract concepts into something that can be measured

Extraneous variable

Any variable other than the IV that may affect the outcome of the experiment

Standardised procedures

The elements of the experimental were the same for each participant

Confounding variable

Factors other than the IV that may cause a result

Control

The strategies used to minimise the influence of extraneous variables, ensuring that changes in the DV are caused solely by the IV

External validity

The extent to which the research findings can be generalised to other situations/populations

Internal validity

An assessment of whether the observed changes in the DV can be confidently attributed to the manipulation of the IV rather than any other factors

Mundane realism

The extent to which the experimental tasks resemble real-life situations

Pilot study

A smaller scale test of the methods and procedures that are going to be used in the larger experiment

Experimental design

Repeated measures, independent groups and matched pairs

Counterbalancing

The method used during repeated measures to prevent the effects of learning affecting the final results

Order effects

When the participants responses in the conditions are affected by the order of the conditions they were exposed to

Random allocation

The allocation of participants to conditions in an experiment, randomly

Demand characteristics

Cues given to participants in an experiment that could give away the experimental hypothesis and change the way they behave

Investigator effects

When the researcher unintentionally influences the outcome of the research they are conducting

Single blind design

Where the subject doesn’t know what the IV is or what’s being changed but the experimenter does

Double blind design

When the subject and the investigator are both in the dark about what the difference in conditions is

Experimental realism

The extent to which something in an experiment can be generalised and compared to real life situations and environments

Social desirability bias

A type of response bias where subjects will give the response they think will make them look the best

Closed questions

Questions to which the answers are fixed (e.g yes/no)

Open questions

Questions to which the participants can answer however they want

Filler questions

Questions to try to stop the participant from figuring out the aim of the research

Qualitative data

Non-numeric answers, not in-depth responses

Quantitative data

Numeric answers, easier to analyse

Levels of measurement

Nominal, ordinal and interval

Nominal data

Named data that can be separated into discrete categories

Ordinal data

Data that is placed into some kind of order or scale

Interval data

Data measured in fixed units with equal distance between points on a scale

Negative skewed distribution

Mean<median<mode

Positive skewed distribution

Mode<median<mean

Skewed distribution

Similar to the normal distribution bell-shaped curve but the bulk of scores fall to one side of the median score

Intervening variable

An unforeseen variable that actually causes a change in the DV when the IV doesn’t

Meta analysis

Where researchers combine findings from multiple studies to draw a conclusion

Content analysis

A method used to understand qualitative data and turn it into quantitative data

Peer review

A quality control process used by publications to help ensure that only high-quality methodologically sound information is allowed to the public

Strengths of repeated measures

Has good internal validity by reducing the influence of participant variables such as individual differences

Limitations of repeated measures

Participants may learn or be able to practice as the measures are repeated

Strengths of independent groups

There are no order effects since the different participants are exposed to each condition

Limitations of independent groups

The difference between the experimental control groups may be different due to individual differences between participants

Strengths of matched pairs

There are no order effects and the demand from participants is lower because all participants are only tested once

Limitations of matched pairs

More time is needed to match all pairs accurately and two participants are lost instead of one if one drops out and it is difficult to match participants on every single variable so there may still be a problem with individual differences affecting the results