Research Methods

• independant variable

  thing you change
• dependant variable

  thing you measure
• operationalised 


  to be clear + precise
• reliable 


  results can be repeated
• valid 


  results are true
• null hypothesis

  there will be no difference in the results
• directional hypothesis 


  they state the specific direction, the research expects the result eg higher,lower
• non-directional hypothesis 


  these state that there will be a difference but doesn't state the direction
• Extraneous variable

  something you are not investigating but could affect the results
• confounding variable 


  affects the dependant variable and is related to the independant variable
• internal validity 


  control + realism
• external 


  generalising the results to other people + situations
• population validity

  can it be generalised to all people
• ecological validity 


  can it be generalised to other environments
• temporal validity

  generalised to people of today - hisotrical
• demand characteristics

  the pp can guess the aim of the study
• investigators effects

  any effects of the investigators behaviour that could affect the outcome
• randomisation

  using chance wherever possible to reduce the researchers influence
• standardisation

  all pp should be subjected to the same environment, instructions + experience
• laboratory experiment

  highly controlled experiment
• field experiment

  familiar setting
• natural experiment

  change to the iv has naturally happened
• quasi experiment 


  iv is naturally occurring
• laboratory strengths + weaknesses

  strengths - highly controlled, easily replicable

  weaknesses - lacks mundane realism, higher risk of demand characteristics
• field strengths + weaknesses

  strengths - high in mundane realism, high ecological validity

  weaknesses - reduces internal validity, more time consuming + expensive
• quasi strengths + weaknesses

  strengths - allows comparison between types of people

  weaknesses - pp might be aware they are being studied, reducing internal validity
• independant groups

  separate groups of pp experience different conditions of the iv
• repeated measures

  when all the pp are tested under all the conditions of the iv, these results are then compared
• matched pairs

  pp are paired together on a variable to variables relevant to the experiment eg gender, IQ
• counterbalancing

  half take part in one condition other 1/2 in the other condition then swap
• single blind procedure

  either the experimenter or pp doesn't know which is which
• double bind procedure

  both the experimenter + pp don't know which is which
• pilot study

  small scale trial run of the actual investigation, allows the researcher to identify the possible issues and modify them before the actual procedure
• central tendency

  mode, mean + median
• dispersion

  range, standard deviation
• standard deviation 


  a measure of the variability of a set of scores or values within a group
• s value

  less frequent
• n value

  number of scores excluding the 0
• unstructured observations

  records all behaviours but has no system
• structured observations


  uses the systems to organise observations