Inferential statistics

• Probability + significance:

  Probability is the likelihood that the results are due to chance or not

  • to be more confident that the IV has effected the DV they will use P<0.01 as it is a low significance number

  In order for the results to be significant the results need to be less that P<0.05

  • if results are significant we accept the experimental hypothesis and reject the null
• Calculating the sign test:

  • look for a difference (sign of difference)
  • use a repeated measures design
  • nominal data - categories

  use the significance level of P<0.05, unless tells you otherwise + read the RULE at bottom of the table
• Type 1 error:

  This is where a psychologist wrongly accepts the experimental hypothesis + rejects the null hypothesis when they should not as the result was due to chance

  • less likely to happen if significance level is P<0.01 as there is only a 1% probability that the results are due to chance
• Type 2 error:

  This is where a psychologist wrongly rejects the experimental hypothesis + accepts the null hypothesis when they should not as the results weren't due to chance
• Choosing the right test:

  1. difference or correlation
  2. level of data (nominal/ordinal/interval)
  3. experimental design
• Statistical tests table

  
• Critical value table:

  1. whether a one-tailed or two-tailed hypothesis has been used
  2. the number of participants (N) used
  3. what level of significance is being used
  4. whether the calculated value is greater, less than or the same as the critical value (comes from the table)

  ANSWER:

  "as the calculated value of … is greater/less/equal to the critical value for a one/two tailed test for N=(praticipants). The results are therefore significant/not significant at P<0.05/P<0.01. So"