measures of central dependency + dispersion

• central tendency:

  • descriptive statistics e.g mean, mode, median
• mean strengths:

  • most sensitive - includes all values in data set
  • more representative as a whole
• mean weaknesses:

  • easily distorted by extreme values - doesnt represent data overall
  • cannot be used with nominal data
• median strengths:

  • not affected by extreme scores
  • easy to calculate
• median weaknesses:

  • less sensitive - actual value of numbers are ignored, extreme values may be important
  • cant be used with nominal data
• mode strengths:

  • easy to calculate
  • can be used with nominal
• mode weaknesses:

  • unlikely to be unrepresentative of data - can be quite different to mean
• levels of measurement:

  • nominal = categories
  • ordinal = data is ordered, intervals between units not equal
  • interval = numerical scales of units, equal + precise intervals
• measures of dispersion:

  • spread of scores, how they vary + differ from one another e.g range, standard deviation
• range strengths:

  • easy to calculate
• range weaknesses:

  • only takes in account most extreme values - unrepresentative of data as whole
  • doesnt indicate whether most numbers are closely grouped around mean or spread out
• standard deviation:

  • most sophisticated measure, provides 1 value + tells us how far scores deviate from mean
  • larger = greater dispersion + spread of scores in data set
  • smaller = data tightly clustered around mean - responded in similar way
• standard deviation strengths:

  • more precise measure of dispersion than range - all values are in one calculation
• standard deviation weaknesses:

  • can be distorted by single extreme value