Probability Rules

  • Probability- the chance of an event occurring
  • Random experiment- an experiment in which the outcome is uncertain
  • Probability is a number between 0 and 1
    • Impossible event- has a probability of 0 (guaranteed not to happen)
    • Certain event- has a probability of 1 (guaranteed to happen)
    • Sum of probabilities for all possible outcomes=1
  • Subjective probability- based on personal opinion
  • Theoretical probability- based on formulas
  • Experimental probability- based on the results of a random experiment
  • Law of large numbers- if we repeat an experiment a large number of times, the results that we see experimentally should be closer to what we would expect to see theoretically
  • Sample space- collection of all possible outcomes for an experiment
  • Observation- the observed outcome of a random experiment
  • Event- a subset of the sample space, a collection of outcomes
  • Complement- the subset of all outcomes within the sample space that are not in the event A of interest
  • Intersection (A and B)- the event containing all of the elements that are common to both A and B
  • Union (A or B)- the event containing all of the elements that belong to either A only, B only, or both A and B
  • Mutually exclusive- events that have no outcomes in common
  • Correct positive- test results indicates that the condition is present, and it is
  • False positive- test results indicates that the condition is present, but it is not
  • False negative- test results indicates that the condition is not present, but it is
  • Correct negative- test results indicates that the condition is not present, and it is not
  • Sensitivity- the probability that the test will give a positive result, given that the condition tested for is present
    • P (positive result | condition is present)
  • Specificity- the probability that the test will give a negative result, given that the condition tested for is not present
    • P (negative result | condition is not present)
  • Ideally we want both the sensitivity and specificity of a test to be high