Statistical analysis

• Standard Deviation shows by how much most pieces of data vary from the mean. +/-deviations show above/below the mean. (triangular graph, pie chart & composite bar chart)
• SD: 1. Find the mean than subtract the mean from each data point

  2. Square each data point to make it positive

  3. Add all of data points2 then / by the number of data points (variant)

  4. Square root to get the standard deviation

  
• Nominal data: numbers but used in categories (e.g. types of buildings, retail 1, residential 2)
• Ordinal data: number that can be ordered (results of a bi-polar survey)
• Interval data: similar to ordinal but the gap between numbers is constant (temp)
• Ratio data: results can be analysed using a ratio (there are twice as many cars in survey 1 than 2)
• Null hypothesis: there is no statistical difference/correlation this must be accepted unless the hypothesis is accepted
• Spearmans Rank:

  • used to test if 2 sets of variables are connected
  • there must be a connection between the data loction/person
  • data must be monotonic (can draw a straight line of best fit)
  • normally must have 10 pairs of data to be statistically valid
• Spearman's Rank formula

  A) rank coefficient

  B) number

  C) sum of difference2

  
• Rank significant:

  • it is significant if R is above the critical values for n
  • most scientific papers require a 95% significance for the hypothesis to be accepted
  • there could otherwise be other factors creating the chance
• T-Test Formula

  
• Standard deviation is how spread out data is
• The student's t-test looks at the means of two sets of data and decides whether there is a significant difference between the two​. It looks at the ​degree of overlap between the two samples. It applies to data that is measured on an interval or ratio scale and for data that is normally distributed around the mean.
• The Chi-Squared test looks at the relationship between a set of data​ and a theoretical/expected set of data to decide whether the difference between the two is significantly different​. It is used to see how closely the data collected or observed by the researcher fits with the widely accepted findings.
• The Student's T test can only be used when the data in each sample can be said to be distributed normally around the mean.