250 likes | 950 Views
Probability. Ch 6, Principle of Biostatistics Pagano & Gauvreau Prepared by Yu-Fen Li. Operations on Events. a Venn diagram is a useful device for depicting the relationships among events. A ∪ B “A or B”. A ∩ B “both A and B”. A c or , “not A”. Probability.
E N D
Probability Ch6, Principle of Biostatistics Pagano & Gauvreau Prepared by Yu-Fen Li
Operations on Events • a Venn diagram is a useful device for depicting the relationships among events A ∪ B “A or B” A ∩ B “both A and B” Ac or , “not A”
Probability • The numerical value of a probability lies between 0 and 1. • We have The additive rule of probability
The additive rule of probability • For any two events A and B • If A and B are disjoint (mutually exclusive)
The additive rule of probability • The additive rule can be extended to the cases of three or more mutually exclusive events • If A1, A2, · · · , and An are n mutually exclusive events, then A7 A5 A3 A6 A2 A4 A8
Joint and Marginal Probabilities • Joint probability is the probability that two events will occur simultaneously. • Marginal probability is the probability of the occurrence of the single event. P(A2B1) P(A1)
Conditional Probability • We are often interested in determining the probability that an event B will occur given that we already know the outcome of another event A • The multiplicative rule of probability states that the probability that twoevents A and B will both occur is equal to the probability of A multiplied by the probability of B given that A has already occurred
Independence • Two events are said to be independent, if the outcome of oneevent has no effect on the occurrence of the other. • If A and B are independent events,
Multiplicative rule of probability • For any events A and B • If A and B are independent
‘independent’ vs ‘mutually exclusive’ • the terms ‘independent’ and ‘mutually exclusive’ do not mean the same thing. • If A and B are independent and event A occurs, the outcome of B is not affected, i.e. P(B|A) = P(B). • If A and B are mutually exclusive and event A occurs, then event B cannot occur, i.e. P(B|A) = 0.
Bayes’ Theorem • If A1, A2, · · · , and An are n mutually exclusive and exhaustive events • Bayes’ theorem states mutually exclusive exhaustive
The Law of Total Probability • P(A)=P(A1∪A2∪A3∪A4) =P(A1) + P(A2 ) + P(A3 ) + P(A4) = 1 • P(B)=P(B∩A1) + P(B∩A2) + P(B∩A3) + P(B∩A4) =P(A1)P(B|A1) + P(A2)P(B|A2) + P(A3)P(B∩A3) + P(A4)P(B|A4) B ∩ ∩B B ∩ ∩B
Examples • For example, the 163157 persons in the National Health Interview Survey of 1980-1981 (S) were subdivided into three mutually exclusive categories:
Examples of marginal probabilities • Find the marginal probabilities
Example of the additive rule of probability • If S is the event that an individual in the study is currently employed or currently unemployed or not in the labor force, i.e. S = E1∪ E2 ∪ E3. the additive rule of probability
Example of the law of total probability • H may be expressed as the union of three exclusive events: the law of total probability
Examples of conditional probabilities • Looking at each employment status subgroup separately
Example of Bayes’ theorem • What is the probability of being current employed given on having hearing impairment?
Diagnostic Tests • Bayes’ theorem is often employed in issues of diagnostic testing or screening • Sensitivity and Specificity
Positive and Negative Predictive Values (PPV and NPV) • PPV • NPV Sensitivity (SE) 1-Specificity (1-SP)
A 2 x 2 table • The diagnostic test is compared against a reference ('gold') standard, and results are tabulated in a 2 x 2 table Sensitivity = a / a+c Specificity = d / b+d Positive Predictive Value (PPV) = a / a+b ?? Negative Predictive Value (NPV) = d / c +d ?? Prevalence = a+c / (a+b+c+d) ??
Relationship of Disease Prevalence to Predictive Values • The probability that he or she has the disease depends on the prevalence of the disease in the population tested and the validity of the test (sensitivity and specificity)