descriptive statistics

• what are central tendencies

  mean, median and mode
• what is the mean and how is it calculated

  the average score within a dataset

  calculated by adding all of the scores together then dividing by the total number of scores you have
• what is a strength of finding the mean

  representative measure - it includes all values in the dataset during calculation
• what is a weakness of finding the mean

  it is easily changed by extreme scores
• what is the median and how is it calculated

  the middle score within a dataset (when scores are put in size order)

  it is calculated by ordering the data from lowest to highest and then crossing off from each side until you have just one number left - an even number of data will end up with two numbers left over at which we find the midpoint of these numbers
• what is a strength of finding the median

  it is not affected by extreme scores and it is easy to calculate
• what is a weakness of finding the mean

  not all of the scores are included in the final calculation so it is not representative of the whole dataset
• what is the mode and how do you calculate it

  the most popular score within the dataset

  calculated by identifying the most frequently occurring score in the data set.

  if there is more than one mode, our data is bi-modal
• what is a strength of finding the mode

  allows categorical data to be analysed
• what is a weakness of finding the mode

  very arbitrary measure, not very representative of the fullest dataset, it varies too much from the mean/median
• what are the measures of dispersion

  range and standard deviation
• what is the range and how do you calculate it

  the simple way of identifying the spread of scores in the dataset

  calculated by subtracting the lowest score from the highest score and often adding 1 to allow for 'margin of error'
• what is a strength of finding the range

  easy to calculate
• what is a weakness of finding the range

  only accounts for the two most extreme scores - therefore, not representative of the whole dataset
• what is standard deviation

  a value that tells us how far our schools are spread out (deviate) from the mean
• what does a larger standard deviation mean

  our data is quite spread out from the mean and suggest that not all participants behaved \ responded similarly. Could also flag up the presence of outliers
• what is a strength of calculating standard deviation

  greater precision as all scores are included in the calculation
• what is a weakness of calculation standard deviation

  can easily be affected by extreme scores and outliers
• what are three ways of presenting data

  tables, bar graphs, histograms, scattergrams
• what are tables

  Great for summarising data in a simple, understandable format. Raw scores are typically not sed but instead the measures of central tendency and dispersion that you calculate. Summary paragraphs often appear under tables in research reports to clear this up for the readers
• what are bar graphs

  Provides readers with a visual, readable version of your data. Should be used when your data is categorical (discrete). Conditions/categories should be plotted on the x-axis (IV) and frequency/numerical values on the y-axis (DV)
• what is the checklist for bar graphs

  title, X and Y axis (labelled), equal intervals, key/legend
• what are histograms

  Used when data is continuous. On the x-axis, you have your continuous numerical measure e.g. % on an exam (0-10, 11-20, etc), and frequency / numerical values on the y-axis. Cannot overlap categories and bars have to be touching
• what are scattergraphs 


  Another visual means of representing data in an accessible format for the reader. Used to analyse associations or correlations between co-variables. One of each of the co-variables is located on either the x or the y axis.
• what is distribution

  it refers to the shape that data forms when it is plotted into some kind of graphical format
• what is a normal distribution

  Symmetrical appearance of data, usually forms a bell shape know as the 'bell curve'. Most people are located at the centre of the distribution and the mean, median and mode are located at the peak. 50% are below average and 50% are above average.
• what is a skewed distribution and what are the two types

  distributions that lean more towards a specific direction

  1. positive skew
  2. negative skew
• what is a positive skew

  the data is concentrated on the left, leaving a long tail on the right.

  the mode is on the left, flooded by the median and then the mean
• what is a negative skew

  when data is concentrated to the right

  the mean is on the left, followed by the median and then the mode