Research methods

• Aim and Hypothesis

  Aim: An idea of what the study is trying to achieve

  Hypothesis: A prediction of what we expect to find

  
  

  E.g Aim: To find out if alcohol effects driving

  Hypothesis: The more alcohol in your system the worse your driving ability will be
• IV, D.V, C,V

  I.V= The variable we adjust/change

  D.V= The variable we measure

  C.V= The variable we control
• Directional and non-directional hypothesis

  Directional- specific about whether the change will be an increase or decrease (there's prior research)

  
  

  Non-directional- certain about difference but no the direction of the difference between the DV and two conditions (used when there is no prior research)

  
  

  Examples of directional:

  - there will be a significant increase in maths test outcomes when jazz music is played compared to pop music

  
  

  Examples of non-directional:

  - there will be a significant difference between the test scores when jazz music is played compared to pop music
• Null hypothesis and a Alternative/experimental hypothesis

  Null hypothesis: One variable doesnt affect the other variable.

  
  

  Alternative/experimental hypothesis: One variable does affect the other variable.
• Operationalisation of variables

  Variables in every experiment must be clearly defined, this means we must make it measurable.

  
  

  E.g Watching violent televison gives kids nightmares.

  
  

  Watching 2-4 hours of violent television can make kids wake up more times during the night.

  
  

  E.g Children who read aloud to an adult for 15 minutes a day will have higher scores on a reading test than children who do

  not read aloud to an adult.
• Field experiment

  An experiment set up in the real world, usually with participants who are not aware that they are in a study of any kind. The researcher manipulates the I.V to record the D.V

  
  

  For example: Researchers tested whether

  participants were more likely to

  obey someone's orders if they

  were dressed as a guard. A

  confederate dressed as a

  guard, milkman or casual and

  asked passers-by to pick up

  litter.

  
  

  + Participants behavior more natural

  + High external validity

  - Loss of control of extraneous variables

  - Ethical issues
• Lab experiment

  An experiment that takes place in a controlled environment where the researcher manipulates the IV and records the effect on the DV while maintaining strict control of extraneous variables.

  
  

  For example: Researchers want to

  measure the physiological

  response of participants to a

  range of stimuli, e.g. bright

  light, loud noise and

  electric shock.

  
  

  + Well controlled

  + Can be easily replicated

  + Higher internal validity (Extraneous variables controlled)

  - Artificial situation

  - Participant's may change there behavior
• Natural experiment

  An experiment where the I.V is not manipulated as the IV is not caused by the researcher as it already exists. The researcher records the effect on the DV.

  
  

  For example: Researchers are interested in how

  parenting styles influence the

  mental health of children. They take

  advantage of 2 different cultures

  that use different parenting styles

  and then measure the differences in

  the mental health of children.

  
  

  + Enables researches to study real life

  + Less ethical issues as the I.V isn't manipulated

  - May only happen rarely

  - Cannot demonstrate a casual relationship between the I.V and the D.V

  - Random allocation of participants not possible.

  - Lack of control over extraneous variables.
• Quasi-experiment

  An experiment that takes place in a lab setting however the I.V is not manipulated as they already exist. The researcher then records the D.V

  
  

  For example: Researchers want to

  compare older and younger

  participants' ability to solve

  word search puzzles.

  
  

  + Well controlled

  + Can be easily replicated

  + Higher internal validity (Extraneous variables controlled)

  + Allows comparisons between different people

  - Artificial situation

  - Participant's may change there behavior

  - Random allocation of participants not possible
• Confounding variables


  When extraneous variables do have an affect on the dv.
• Demand characteristics

  Participants changing there behaviour within the research if they know the purpose of the experiment
• Investigator effects

  Any effects of the investigators behaviour on the research outcome. This may include the design of the experiment, instructions, materials, selection of participants or interaction with participants. You could get someone else to run the experiment that does know the purpose of the research.
• 2 ways of controlling extraneous variables

  1. Standardised procedures (doing the same procedure with every participant)

  
  

  2. Randomisation (randomly allocating to avoid individual differences)
• Experimental Design

  A experiment must have at least two conditions but

  they can be arranged in a variety of ways.
• Repeated measures

  The same participants take part in both conditions.

  
  

  + Cost effective

  + No individual differences/ participant variables

  - Order effects (gives them practice, makes them bored or tired, allows them to work out the goal of the study)

  
  

  Solution: Counterbalancing (ensures that each condition in a repeated measures design is tested first or second in equal amounts)
• Independent groups design

  An experimental design in which participants are each different condition and only do one condition.

  
  

  + No order effects

  - The individual characteristics affect the d.v

  
  

  (Solution: Random allocation)
• Matched pairs

  Participants are each in a different condition and only do one condition, but are matched on key characteristics.

  
  

  + no order effects

  + no demand characteristics

  - time consuming

  - Match is rarely possible

  - Not possible to control all particpant variables
• Target population and the sample


  The target population is the group of people the researcher is

  interested in studying. The sample is drawn from the target

  population.
• Random sampling

  This is a sampling technique which is defined as a sample in which every member of the population has an equal chance of being chosen.

  
  

  + Free from researcher bias

  - Difficult and time consuming

  - Sometimes a random sample may still be unrepresentative (coincidences)

  -Selected participants may refuse to take part
• Systematic sampling

  This is when every nth member of the target population is selected, for example every 5th house on a street or every 3rd pupil on a school register.

  
  

  + Avoid researcher bias

  + Usually fairly representative

  - You could get an all male/ female group if unlucky
• Stratified sampling

  Stratified sampling involves classifying the population into

  subgroups and then choosing a sample which

  consists of participants from each in the same proportions as

  they are in the population.

  
  

  + Avoids researcher bias

  + Sample is representative

  - Cannot reflect all the ways people are different
• Opportunity sampling

  Opportunity sampling is the sampling technique most used by

  psychology students. It consists of taking the sample from

  people who are available at the time the study is carried out.

  
  

  + Convenient

  + Saves the researcher time and effort

  + Less costly

  - Unrepresentative

  - Researcher bias
• Volunteer sampling

  Volunteer sampling consists of participants becoming part of a study because they volunteer when asked or in response to an advert.

  
  

  + Easy and less time consuming for the researcher

  - Volunteer bias
• DRIPPD

  Deception

  Right to withdraw

  Informed consent

  Protection from harm

  Privacy and confidentiality

  Debrief
• Informed consent

  Informed consent involves making participants aware of the aims of the research, the procedures their rights (to withdraw) and what their data will be used for. We ask this by sending a consent letter.
• Pilot study

  A pilot study is a small-scale trial run of the actual investigation. A pilot study allows the research to identify any potential issues and to modify the design or procedure, saving time and money in the long run.
• Single blind procedure

  The participant is not told the aims of the experiment or if there are any other conditions.

  This is to control demand characteristics.
• Double blind procedure

  Neither the participants nor the researcher is aware of the aims.

  This is to control both demand characteristics and investigator effects.
• Participant observation

  As the researcher, you are actively involved in the groups activities as well as making a record of what you see.
• Non participant observation

  You watch and record what is happening but are not involved in the groups activities.
• Overt observation

  The group you are observing know why you are there and

  what you are doing.
• Covert observation


  You are undercover and the group are not aware of the fact

  that you are observing them.
• Naturalistic observations

  Take place in the setting where the behaviour would normally occur.
• Controlled observations

  Watching and recording a behaviour in a structured

  environment where some variables are changed.
• Behaviour categories

  When a target behaviour is broken up into components that are observable and measurable. Often recorded in a checklist
• Inter-observer reliability

  The extent to which there is agreement between 2 or more observers.
• Hawthorne effect

  When someone changes there behaviour because they are being observed.
• Social desirability bias

  Changing your behaviour to seem more social desirable (popular).
• Event sampling

  Count the number of times a particular behaviour occurred.

  
  

  + Event sampling is useful when the target behaviour or event happens quite infrequently and could be missed if time sampling was used.

  
  

  - However, if the specified event is too complex, the observer may overlook important details if using event sampling.
• Time sampling

  Record behaviour using a pre-established time frame.

  
  

  + Time sampling is effective in reducing the number of observations that have to be made.

  
  

  - When that behaviour is sampled it might be unrepresentative of the observation as a whole.