3.3 - Data Handling + Analysis

• What is quantitative data?

  • data in numerical form
• Strengths of quantitative data -

  1. Reduce bias since it is objectively measured - increases scientific credibility
  2. More reliable - can be replicated
  3. Easier to analyse
• Limitations of quantitative data -

  1. reductionistic - simplifies it too much so there is a lack of meaning
  2.  It may be influenced by researcher bias or the use of inappropriate statistical techniques.
• What is qualitative data?

  • non numerical language based data
• Strengths of qualitative data -

  1. seen as rich in detail - higher in validity
• Limitations of qualitative data -

  1. Potentially biased due to interpretation
  2. challenging to summarise
  3. reduces reliability
• What is primary data?

  • data collected first hand by the researcher
• Strengths of primary data -

  1. Increased validity - research collected in designed to test variable directly
  2. increased validity as the researcher can control data collection
• Limitations of primary data -

  1. Collecting original data is time consuming and expensive
• What is secondary data?

  • data that other researchers have collected
• Strengths of secondary data -

  1. Reduces time and cost - already analysed
• Limitations of secondary data -

  1. decreases validity as data is not collected to answer research directly
  2. researcher has no role in data collection - cannot ensure it is free from bias
• What is a meta analysis?

  • when researchers draw multiple research pieces together to gather a conclusion
• Strengths of meta analysis -

  1. Large sample size so produces statistically good results
  2. Looks at the overall pattern of results so less bias or lack of control will not affect results
  3. Can be used in various contexts
• Limitations of meta analysis -

  1. Has the weakness of secondary data
  2. Unlikely to be submitted for publication
  3. Choice of which studies to include/exclude so could be bias
• What are the measures of central tendency?

  1. Mean
  2. Mode
  3. Median
• What is the mean?

  • calculates the average score of the data test
• Strengths of the mean -

  1. More sensitive as it takes all the data scores into account
  2. More likely than other measures of CT to provide a reliable result
• Limitations of mean -

  1. It includes outliers so can only be included when scores are close together
  2. The mean score may not actually be in the data ser (6.5)
• What is the mode?

  • mode calculates the most frequently occuring scores in data sets
• Evaluation of mode -

  1. Less likely to be affected by extreme scores
  2. Often useful for the analysis of qualitative data
  3. May include 2 modes (bimodal and multi modal) which blurs the meaning of the data
  4. Mode likely to be of little use as it provides an unrepresentative sample
• What is the median?

  • calculates the middle value of a data set
• Evaluation of median -

  1. Not affected by extreme scores
  2. easy to calculate
  3. impractical on large data sets
  4. does not account for extreme scores so less reliable
• What are the measures of dispersion?

  • Range
  • Standard deviation
• What is the range?

  • difference between highest and lowest scores
  • shows how consistent the scores are
• Evaluation of range -

  1. Provides broad overview of the data which can be useful for some research purposes
  2. easy to calculate
  3. provides no info on other scores besides the top and botoom
  4. unrepresentative as it varies from one sample to another
• What is standard deviation?

  • the spread of data
  • calculates how a score deviates from the mean
  • LOW SD - indicates scores are tightly clustered around the mean which indicates reliability
  • HIGH SD - scores are more spread out from the mean (low reliability)
• Evaluation of standard deviation -

  1. More sensitive than range as it uses all data sets
  2. Provides info on how scores are distributed
  3. time consuming and complicated to carry out
  4. can be skewed by extreme outliers
• How is quantitative data presented?

  1. Raw data tables
  2. Frequency tables
  3. Bar chart
  4. Pie charts
  5. Scattergrams
  6. Histogram
  7. Line Graphs
• What is a raw data table?

  • record of individual data points collected from pps
• What is a frequency table?

  • a log of the number of observations of behavioural catergories}
• What is a bar chart?

  • summarises frequency of nominal (catergorical) data
  • x axis - categorical variable
  • y axis - frequency
  • height of each bar is the frequency
  • bars DO NOT TOUCH - not continuous data
• What is a pie chart?

  • a circular graph that represents all the data
  • each wedge represents the proportion of one category of data
• What is a scattergram?

  • display relationship between 2 co variables
  • usually display correlational relationships
• What is a histogram?

  • displays frequency of continuous numerical data
  • y axis - frequency
  • x axis - continous variable
  • bars DO TOUCH
• What is a line graph?

  • allow for the display and comparison of 2 sets of continuous data on the same graph
• What is a distribution?

  • refers to the spread of the data around the mean
• What is a normal distribution?

  • symmetrical around the mean with most scores being close around it, sharing a peak in the middle where the mean value is located
  • shape is known as a 'bell curve' and most scores fall within the centre
• What is a positively skewed distribution?


  • one in which most values are found towards the left side, giving it a long tail on the right
  • MEAN - HIGHEST
  • MODE - LOWEST
  • MEDIAN - GREATER THAN MODE
• What is a negatively skewed distribution?

  • most values found towards the right side of the graph, giving it a long tail to the left
  • MODE - HIGHEST
  • MEAN - LOWEST
  • MEDIAN - HIGHER THAN MEAN