Types of data

• Primary data

  • Data collected from first-hand experience
  • For testing specific hypotheses
  • Design study -> get approval -> carry out study -> analyse findings -> draw conclusions
  • Any experiment carried out by researcher = primary data
• Primary data strengths:

  • Close focus = more control over data -> fits aims + hypotheses better
  • Investigator bias can be avoided because researcher builds study around hypothesis
• Primary data weaknesses:

  • Close focus = time consuming = expensive + difficult to obtain/analyse
  • Designing study = time consuming
  • Researcher close to study = potential investigator bias
• Secondary data

  • Data collected for another purpose in different form/collected by different researcher for same purpose
  • e.g. government statistics
• Secondary data strengths:

  • Readily available = easy to access
  • Cheaper + more time efficient
  • Data may have been statistically tested to support accuracy/reliability
• Secondary data weaknesses:

  • Potential investigator bias unavoidable as someone else conducted the research
  • Original researchers may not have taken the same care in preventing investigator bias
  • Research built around specific hypothesis = may not fit around new hypothesis
• Meta-analysis

  • Primary data from other studies combined + re-analysed -> draws on as many prior studies as possible to base conclusions off of regarding new hypothesis
  • Produces quantitative data
• Meta-analysis strengths:

  • Makes it easy to identify trends in research that are not always easy to point out
  • Time efficient = inexpensive (data is readily available)
  • Huge sample size
• Meta-analysis weaknesses:

  • Primary research has to be of good quality as chosen secondary data relies on it
  • Doesn't take into account potential investigator bias
• Quantitative data

  
  

  • Numerical data obtained from counting variables
  • Experimental + observational methods can provide quantitative data
• Quantitative data strengths:

  • Variables operationalised well = objective + reliable data
  • Can be put into graphs to spot trends (can be used in meta-analysis)
  • Data obtained easier to replicate
• Quantitative data weaknesses:

  • Doesn't give origin of original data
  • Trends' contexts not explained
  • Superficial insight
• Qualitative data

  • Non-numerical data (detailed)
  • Obtained from subjective studies, e.g. self-report methods, case studies
  • Insight into meaning behind quantitative data
• Qualitative data strengths:

  • Provides origins of data, e.g. motivation + intent
  • Richer insight into data itself
• Qualitative data weaknesses:

  • Subjective -> can't see patterns in data
  • Not replicable = can't be generalised