design issues

factors associated with good design:

• a pilot study
• reliability of results
• validity
• internal validity
• ecological validity

three experimental designs

1. independent group - testing separate groups of people, each group tested in a different ocndition (one being controlled_

+ avoids order effects

+ reduced DC

+ same test can be used

- more participants are needed than repeated measures design

- worse statistical test

- individual differences such as variation in age, sex or social background aka participant variable

2. repeated measures - testing the same group of people in different conditions, the same people are used repeatedly.

+ requires fewer participants

+ individual differences are not a confound

+ avoids the problems of participant variables

- order effects are more likely to occur

- DC

- different tests

- counterbalancing/ randomisation

3. matched pairs - testing separate groups of people - each members of once group is same sex, age or social background

+ avoids order effects

+ reduced DC

+ same test can be used

+ individual differences are reduced

- very time consuming to do

- impossible to match exactly

- more participants needed

counterbalancing - alternating the order in which participants in different conditions of an experiment to eliminate order effects

randomisation - material for each condition in an experiment is presented in a random order, preventing order effects