inferential testing

• what is inferential testing ?


  to be sure that what you found is not due to random error in your sampling or methodology
• what is the process of inferential testing ?

  1. gather data + put through the inferential test for z an observed or calculated value 2. for every test there is a critical values table.using information from design and hypothesis to find the appropriate critical value 3. compare your observed value with to critical value on the table to decide if your results are significant or not
• significant levels and probability ?

  to accept your results are true you have to assess the probability that they occurred by chance rather than genuine effect
• what are the probability levels ?

  standard level of probability is 5%, if it is 5% or below you accept it, if its more than 5% its too risky and you accept the null hypothesis
• how to do a sign test ?

  for each pp subtract their scores on measure 1 from measure 2, add a plus or minus sign to indicate the direction of difference ( more or less), omit data where there is no difference, count the number of the least frequent occurring signs, this is ur calculated or observed value this number is called s
• how do you use critical values?

  must know whether the hypothesis is directional or non, the number of scores (n) used to calculate s and the probability level you are aiming for
• how do you interpret the test result ?

  critical value tables
• what is the purpose of inferential test ?

  allow generalisation beyond the sample to the rest of the target population , by finding out whether the observed difference or relationship is significant or not.
• what do inferential tests and significance take into account ?

  type of hypothesis being tested ( prediction of difference or relationships between variables), the design of the study and the level of data gathered - DDD
• how is significance determined?


  by comparing the test statistic to the critical value on the tests critical value table, to calculate the probability that the results occurred by chance
• what is probability ?

  researchers set the significance level they must meet in order fir th hypothesis to be accepted. Typically this is 5% however this doesn't always mean the decision about whether the results are significant or not
• what is a type 1 error ?

  rejection of the null hypothesis when the results obtained were due to chance. more likely to happen if the significance level is set too high
• what is a type 2 error ?

  too cautious and accept the null hypthesis when the results are real, more likely if u set the significance level too low false negative