Research Methods

• qualititative and quantitative data are empirical data
• qualitative

  'quality'

  written

  expresses thoughts/feelings

  cannot be quantified

  eg interviews
• quantitative

  'quantity'

  numerical

  how much/how long/how many

  measured
• quantitative evaluation

  :-) easy to analyse, quick and precise

  :-( limited therefore lacks detail
• qualitative evaluation

  :-) can form further research, full scope of info

  :-( difficult to analyse, researcher bias
• primary data is gathered first hand by the researcher
• primary data evaluation

  :-) control over data, recent and current

  :-( lengthy, time consuming and expensive
• secondary data is collected by someone else
• secondary data evaluation

  :-) easy, cheap and quick

  :-( past data may not be relevant, may not be exact
• meta analysis is a statistical technique for combining findings of several studies
• independent variable is the one you change
• dependent variable is the one thats measured
• extraneous variables are anything that isn't the IV effecting the DV, become confounding variables if uncontrolled
• an aim is a clear and precise statement of the purpose of the study
• a hypothesis is a testable statement predicting the results of the research. if the results support the hypothesis its retained. if it doesn't, it's rejected
• non directional aka two tailed hypothesis

  states the iv will have an effect on the dv but doesn't predict how
• a non directional hypothesis should use the words significant difference
• directional aka one tailed hypothesis

  the iv will have an effect on the dv and what the effect is
• directional hypotheses should include a direction word eg higher or lower
• null hypotheses states there will be no significant effect of the iv on the dv
• operationalisation is defining the variables so they can be tested precisely
• the experimental methods are lab, quasi, field and natural
• laboratory experimental method

  setting: artificial

  iv: manipulated

  example: effects of alcohol on reaction time in a controlled setting

  :-) replicable, high variable control to establish C+E

  :-( low ecov, high dc's
• quasi experimental method

  setting: usually artificial

  iv: naturally occuring eg sex

  example: gender difference in time completing memory task

  :-) replicable, high variable control to establish C+E

  :-( low ecov, high dc's
• field experimental method

  setting: natural

  iv: manipulated

  example: piliavin

  :-) high ecov, low dc's

  :-( hard to replicate, low variable control
• natural experimental method

  setting: natural

  iv: natural

  example: smoking was banned from all public places for a six-month period

  :-) high ecov, low dc's

  :-( hard to replicate, low variable control
• extraneous variables

  participant variables, situational variables, experimenter effects and demand characteristics
• demand characteristics are environmental clues and cues in an investigation that cause unnatural behaviour, to please the researcher, to skew the results for funny or self consciousness
• to improve internal validity, the researcher must control extraneous variables
• minimising participant variables - repeated measures design
• minimising situational variables - controlled setting or counterbalancing (ABBA)
• minimising experimenter variables - double blind technique
• minimising demand c's - single blind technique
• Validity means accuracy; whether a study measures what it intends to measure
• internal validity - does it measure what it intends to?

  were ev's controlled?
• external validity - can the research be generalised outside of the research setting to other settings (ecological), other people (population) or other times (temporal)
• assessing validity

  face validity - 'on the face of it'

  concurrent validity - does it provide a close match to results from established test
• improving validity

  experiments - high control, standardised procedures

  questionnaires - anonymity

  observations - covert

  qualitative methods - triangulation (more than one research method)
• reliability means consistency. the results are reliable if the same results are consistently found
• just because a study is reliable it doesn't mean it's valid. a study can be reliably invalid