(12) Statistical Testing - The Sign Test

• significant result = there is a low probability that chance factors were responsible for any observed difference, correlation or association in the variables tested
• If test is Significant :

  • null hypothesis is rejected
  • alternate hypothesis is accepted
• If out test is Not Significant :

  • null hypothesis is is accepted
  • alternate hypothesis is rejected
• a null hypothesis is a statement of no effect
• Null Hypothesis = no difference between groups
• Alternative Hypothesis = there is a difference between experimental groups
• p<0.05 strikes a balance between making a type 1 and 2 error
• p<0.05 = probability of things being due to chance has to be less than 0.05 (less dangerous/ important)
• p<0.01 = used in tests that could cause harm
• p<0.01 = is used when a new drug is being introduced
• Type I Error :

  • when the null hypothesis is rejected when it should have been accepted
  • happens when a lenient significance level is used - an error of optimism
• Type II Error :

  • when the null hypothesis is accepted when it should have been rejected
  • happens when a stringent significance level is used - error of pessimism
• Statistical Testing :

  • provides a way of determining whether a hypothesis should be accepted or rejected
  • shows whether differences or relationships between variables are statistically significant or have occurred by chance
• A Sign Test :

  • used to analyse the difference in scores between related items
  • the same participants used for both conditions - see if research uses a repeated measures design
  • data must be nominal
• in sign tests, nominal data is used - qualitative + groups variables into groups that don't overlap
• statistical testing allows psychologists to prove their results are statistically significant
• the critical value table is used when determining the significance of results after calculating the sign test
• one tailed = directional hypothesis
• two tailed = non directional hypothesis
• N = refers to the number of participants in the study
• S = the observed/ calculated value
• the S value has to be equal to or less than the critical value for a test to be significant
• To calculate the Sign Test :

  1. work out difference between two conditions (told)
  2. if score is + or - place in the end column / if no difference leave it blank/0/=
  3. count the number of + and - signs. The number that is smaller becomes the observed value (S) for the test
  4. identify critical value using critical values table. Look at whether the hypothesis is one-tailed or two-tailed. Select correct level of signnificance
  5. calculate value of N (total number of participants and if 0 changes, subtract)