Experimental Method

• What is an Experiment?

  Experimental method involves the manipulation of variables to establish cause and effects.
• What are the key features of an experiment?

  Standardised procedures and the random allocation of participants into controlled and experimental groups.
• What does Standardisation mean?


  Procedures, materials and instructions within a study are the same for ALL participants into controlled and experimental groups.
• What is the 'Aim' ?


  A broad statement based on what is going to be investigated in the study. For example: The aim of the study was to investigate how Neurozan affects performance in school.
• What is the 'Hypothesis' ?


  Its a precise, testable statement of what the researchers predict the outcome of the study will be. Its stated at the start of the study. It predicts possible cause and effects relationship between 2 variables: the independent and dependant variable.

  
  

  For example: P who are given 10 mags of Neuromind 3x a day will score more marks on a memory test out of 20 compared to those who don't take it.
• What does IV mean?

  Independant variable - What the R changes.
• What does DV mean?

  Dependant variable - What R measures.
• What only has IV and DV's?

  Experiments. Must talk about it in relation to experiments.
• What are the types of hypotheses?

  • Alternative (Experimental) Hypothesis
  • Null Hypothesis.
• What is an Alternative (Experimental) Hypothesis?


  A prediction of what the researcher thinks will happen to the DV when the IV changes.

  E.g. 'Females will drive around a 100m track at a lower average speed than males.' - However this can be directional or non-directional.
• What is a Null Hypothesis?


  States that the IV will have no effect on the DV and any observed differences will be due to chance.

  E.g. 'There will be no difference in the average driving speed around a 100m track between males and females. Any observed differences will be due to chance.'
• What must an Experimental Hypothesis include? (Framing an experimental hypothesis)

  1. All conditions of the IV operationalised.
  2. An operationalised DV.
  3. The direction (if it's a directional hypothesis), or just 'a difference' for a non-directional hypothesis.
• Framing a null hypothesis:


  'There will be no difference in [operationalised DV] between [condition 1] and [condition 2]. Any observed difference will be due to chance.
• What are the types of Alternative (Experimental) Hypothesis?

  • Non-Directional.
  • Directional.
• What is Non-Directional? 


  Predicts that there will be a difference between 2 conditions or groups of participants, without stating the direction.

  E.g. 'There will be a difference in recall of words (out of 20) between those who drink herbal tea one hour before the test and those who have no tea.'
• What is Directional?


  States the direction of the predicted difference between two conditions or two groups of participants.

  E.g. 'P's who drink herbal tea one hour before a test will recall more words out of 20 than P's who have no tea.'
• What is an Extraneous Variable? (EV)


  Other variables which must be eliminated or controlled otherwise they may affect the DV and damage the validity of results.
• Example of EV:


  If we find that learning by pictures, not words improves recall, this does not necessarily provide evidence that the IV is responsible for causing the change in the DV. It could occur by chance or some other variable might be involved.
• What are the 2 types of EV?

  • Participant variables (internal).
  • Situational variables (external).
• What are Participant variables?

  Variables to do with the P. Can include age, gender, social class, ethnicity, intelligence, personality etc.
• How can Participant variables be controlled?

  By randomly allocating participants to groups so that an differences cancel each other out with a large enough sample.
• What are Situational variables?


  variables to do with the situation which might interfere with and affect the behaviour of participants in an experiment. May include time of day, lighting, temp, material, instructions etc.
• How can Situational variables be controlled?

  By using standardised procedures and standardised instructions to ensure that all participants have exactly the same experience i.e. all take part in a study at the same time and given exactly the same instructions.
• What is a Standardised procedure?


  Keeping all aspects of in the investigation the same for all participants.
• What is a Confounding variable?

  Something found after.

  
  

  EV's that have not been controlled in participants and situational variables, may affect the results of the study and become confounding variables. In this instance, we cannot say whether any observed differences in our DV are due to change in the IV or from confdoling variable - too late.
• What is a Demand Characteristics?


  An aspect of the research situation which leads participants to guess the aim and change their behaviour accordingly, hence they do not behave natural. They can affect the DV and therefore are an example of an EV.
• What is the 'screw you' effect?


  P's will want to please R so they may act in a certain way to be helpful to the R, meaning they don't behave naturally. However, sometimes a P will deliberately act in a way that spoils the experiment.
• How can Demand characteristics be controlled?

  • Deception - this is where participants are not told the aim (are ethical issues with this).
  • Single blind method - participants are not told which conditions they are in.
• What are Investigator effects?


  Anything the R does which can affect how the P behaves and the subsequent data collected. The R may unknowingly suggest to the P's how they are expected to behave e.g. the way they ask questions or how they respond to particular participants. In addition, anything the R themselves might affect the P's responses (appearance, behaviour or accent.)

  
  

  Investigator effects may also affect the DV and therefore they are an example of an EV.
• How can Investigator effects be controlled?

  Double blind method - neither the R or the P know what the hypothesis is about o which condition they are. A R assistant is hired who conducts the investigation and collects data, without knowing the hypothesis or specifics about the study. This will make the R assistant more objective and likely to introduce investigator effects.
• What is the Reliability of an experiment?

  Refers to its consistency.
• What are the 2 types of Reliability?

  Internal and External Reliability.
• What is Internal Reliability?


  Refers to the extent the experiment was conducted consistently.

  • Did all P's have exactly the same experience?
  • Was there a standardised procedure?
  • Is the study replicable.
• What is External Reliability?


  Refers to the extent to which the study is consistent over time.

  • This is assessed by test-retest. Here, the P's are tested once, then the same P's are tested again at a later date. The 2 sets of scores are then correlated to determine the extent to which the pairs of test scores from the same persons are similar.
• What is the Validity of an experiment?


  Refers to whether a test measures what it intends to measure. A test can be reliable, but still not valid.
• What are the 2 types of Validity?

  Internal and External Validity.
• What is Internal Validity?

  Whether or not we can say fo certain hat the IV has caused the effect seen in the DV. What are the factors that can cause an experiment to lack internal validity?
• What is External Validity?


  The extent to which results can be generalised to:

  • other settings - ecological validity.
  • other people within the target pop - population validity.
  • diff time periods - temporal validity.
• What are the types of experiments?

  1. Lab experiments
  2. Field experiments
  3. Natural and Quasl experiments
• What are the key features of a Lab experiment?

  1. Conducted in tightly controlled environment
  2. Experimenter deliberately changes the IV across the conditions
  3. Experimenter measures the DV (this usually produces quantitative data)
  4. Experimenter controls the EV (e.g. participants)
  5. Procedure and instructions are standardised.