statistical tests

• T-Test:

  • Compare mean values for significant difference
  • (No) significant difference between means
  • Probability that difference between the means is due to chance is equal to/less than p = 0.05 so there is a significant difference
• Spearman rank:

  • Finding whether there is a correlation between 2 values
  • (No) significant correlation (positive or negative)
  • Probability that the correlation (positive or negative) is due to chance is less than/equal to p = 0.05 so there is a significant correlation
• Chi - squared test:

  • Compare observed and expected results for significant difference
  • (No) significant difference between
  • Probability that difference between observed and expected is less than/equal to p = 0.05 so there is a significant difference
• Degrees of freedom:

  • t-test = total number of values - 2
  • Chi-squared = number of categories - 1
  • Spearman rank = number of pairs - 2
• Criteria for chi-squared test

  Data placed in discrete categories

  Large sample size

  Only raw count data allowed

  No data values equal zero