RMA: WEEK 3

Question 1

What is an experiment?

Answer 1

• where one or more variables are manipulated
• determine the effect of this manipulation of another variable (on the DV)
• tests cause and effect relationships between variables (e.g: does coffee improve driving)

Question 2

Alternative/experimental hypothesis

Answer 2

• Prediction where treatment leads to an effect > there will be a change
• e.g:‘Learning with background music does lead to lower marks

Question 3

Null hypothesis

Answer 3

• Treatment does not lead to an effect or change

- e.g: ‘Learning with background music does NOT leads to lower marks.’

Question 4

What does the IV do to the DV?

Answer 4

• Manipulating the independent variable changes the value of the dependent variable.

Question 5

Nuisance variable

Answer 5

• any variable which may affect the DV which you are not manipulating > these ruin the validity of results
• (e.g: does background music (IV) affect test results (DV) > nuisance variables like time of testing + place affect marks)

Question 6

How to resolve problems cause by nuisance variables

Answer 6

• Turn the nuisance v into a control variable > something to control for both groups by ensuring all tests are constant & standardised (e.g: same music, same time same place)
• If nuisance variables vary across conditions, they may become confounding variables (unique to the person) > e.g: amount of revision they did

Question 7

Groups of participants in an experiment

Answer 7

• Experimental group: Group receiving the important level of the independent variable. > experiences change > e.g., students listening to music as they study.
• Control group: Group that serves as the untreated comparison group. > Group receives comparison level of the independent variable. > e.g., students not listening to music as they study.

Question 8

Testing more than one IV

Answer 8

• Some situations require more than one IV to be tested (e.g: men + women may react differently to a particular change so include it in one exp rather than many) > this may be a nuisance variable otherwise (if only men are tested for example so make it an IV)
• Is better than doing several exp for multiple IVs independently as it is more efficient, better control of nuisance v + results tend to be more representative of behaviour

Question 9

Example of testing more than one IV

Answer 9

• Does special diet and/or exercise reduce cholesterol?
• IV’s: diet (special diet vs. normal diet) & exercise (exercise vs. no exercise)
• DV:Level of cholesterol in blood.
• IV’s tested separately = 1 exp looks at special diet affect on cholesterol + 1 exp looks at exercise affect on cholesterol
• Testing IV’s together: Diet + exercise interact to make bigger decrease in cholesterol (no interaction = variables have individual impacts)

Question 10

Testing more than one DV

Answer 10

• DV measures behaviour in question
• Measuring more than 1 DV is usually more informative (e.g: time taken to write essay vs essay mark)
• Although these variables may not measure the same thing > speed-accuracy trade off (e.g: the faster you write, mark goes down or slower you write, the mark goes up)

Question 11

Advantages of experiments

Answer 11

• Relative strong test of causality (e.g., what leads to what).
• Possibility of a variety of manipulative controls

Question 12

Disadvantage of experiments

Answer 12

• Unnatural setting and tasks.
• Reactivity (also in non-experimental research).
• Some phenomena cannot be studied under controlled conditions (e.g., social interactions).
• Ethical limitations (e.g., lying to participants, electric shocks etc…).