research methods

• Reliability:

  measure of consistency

  every time you measure something (IQ) you should get the same measurements every time

  if something changes it does not mean that the instrument tool is broken it means something has changed
• Ways of testing reliability:

  TEST- RETEST

  • involves administering the same test or questionnaire to the same person on several different occasions
  • if the test or questionnaire was reliable then the sedulity obtained should be the same or similar each time they administer it
  • There must be sufficient time between the test and retest that the pp cannot remember their answers but cannot be too long that their answer, opinion has changed
  • two tests should be correlated using spearmans test
  • if the correlation turns out to be significant then the reliability of the measuring tool is assumed good
• Ways of testing reliability:

  inter-observere reliablity:

  • when observing behaviour, one observers interpretations may difffer widely from the other researcher. This subjectively means there isn't consistency in the data gathered
  • pilot studies need to be carried out so that different observed can agree what each behaviour looks like and therefore record behaviour with consistency
  • observers need to watch the same event or sequence of events but record their data independently
  • data between the two researchers should be corrlated
• Extraneous variables


  Many variables are easy to control such as age, lightening in a lab these are known as nuisance variables as they do not vary systematically with the IV.
• Confounding variables

  change systematically with the IV.

  end up with an intended IV
• demand characteristics

  pp reactivity is a significant extraneous variable which is very hard to control

  • Pp try to guess the aim of the study and certain clues may help them interpret what is going on.

  These cues or clues may help are the demand characteristics of the experimental situation and may help a pp to second guess the researchers aim and instructions of the study

  These clues may tell them how to behave they may try to behave in a way to please the researcher known as the Please-U effect or they may purposefully under perform to sabotage the result of the study the screw-U effect
• Investigator effects:

  any unwanted influence of the investigator on the research outcome.

  Coolican (2006) says these can include any expectancy effects and any unconscious cues