Sign test

• What factors are needed for the sign test to be used?

  • We need to be looking for a difference rather than an association.
  • We need to have used a repeated measures design.
  • We need data that is organised into categories (nominal data).
• Null hypothesis

  • States there is no differences/association in the population.
• Alternative hypothesis

  States there is a difference/association in the population.
• What is the accepted level of probability in psychology?

  0.05
• What is an accepted level of probability?

  The level at which researcher decides finding are significant so will reject the null hypothesis.
• What values are used to decide is results are significant?

  • When a statistical test has been calculated the psychologist is left with a value (calculated value).
  • This needs to be compared with the critical value to decide whether results are significant or not.
• What factors are needed to compare the critical value and calculated value?

  • Significance level (0.05)
  • Number of participants in investigation (N value or degrees of freedom)
  • Whether the hypothesis is directional (one-tailed) or non-directional (two-tailed)
• What does the calculated value have to be in the sign test to be significant?

  For the sign test the calculated value has to be equal to or lower than the critical value for results to be significant.
• Explain the steps of the sign test

  1. Convert data to nominal data (work out the sign of difference).
  2. Add up signs (pluses or minuses)
  3. Take the less frequent sign, this is called S.
  4. Compare calculated value with critical value (need to determine what hypothesis is used, level of significance and N (number of participants).