Basic Probability Rules - Biostatistics

1. In a clinical study, patients can have side effects from medication (20% probability), dietary factors (25% probability), or both (8% probability). What is the probability that a patient experiencing side effects from medication will also experience side effects from dietary factors?
   Answer: 0.400 This question tests conditional probability, a fundamental concept in biostatistics where you need to find the probability of one event given that another event has occurred. The key formula is $P(A|B) = \frac{P(A \cap B)}{P(B)}$, which reads as "the probability of A given B equals the probability of both A and B divided by the probability of B." Here, you're looking for the probability of dietary side effects given that medication side effects occur. Using our formula: $P(\text{dietary}|\text{medication}) = \frac{P(\text{both})}{P(\text{medication})} = \frac{0.08}{0.20} = 0.40$ Answer choice A (0.080) is simply the probability of both events occurring together, not the conditional probability you need. This is a common trap where students confuse joint probability with conditional probability. Answer choice B (0.200) represents the original probability of medication side effects, which isn't what the question asks for. This suggests misreading the question. Answer choice C (0.320) might result from incorrectly trying to subtract probabilities or misapplying probability rules. Some students might calculate $0.20 + 0.25 - 0.08 = 0.37$ and round to 0.32, but this gives the probability of experiencing either type of side effect, not the conditional probability. The correct answer is D (0.400). Study tip: Always identify what type of probability you're calculating. Conditional probability questions often use phrases like "given that" or "will also experience." Remember that conditional probability can be greater than either individual probability because you're narrowing your sample space to only cases where the given condition occurs.
2. Two independent genetic mutations occur with probabilities 0.12 and 0.08 respectively. Given that at least one mutation occurred, what is the probability that both mutations occurred?
   Answer: 0.051 When you encounter a question asking for the probability of an event "given that" another event occurred, you're dealing with conditional probability. This is a fundamental concept in biostatistics, especially when analyzing disease occurrence or genetic mutations. This problem requires using the conditional probability formula: $P(A|B) = \frac{P(A \cap B)}{P(B)}$. Here, you need to find the probability that both mutations occurred given that at least one occurred. Let's define the events: Mutation 1 occurs with $P(M_1) = 0.12$ and Mutation 2 occurs with $P(M_2) = 0.08$. Since the mutations are independent, $P(\text{both}) = 0.12 \times 0.08 = 0.0096$. The probability of at least one mutation is: $P(\text{at least one}) = 1 - P(\text{neither}) = 1 - (1-0.12)(1-0.08) = 1 - 0.88 \times 0.92 = 1 - 0.8096 = 0.1904$. Therefore: $P(\text{both}|\text{at least one}) = \frac{0.0096}{0.1904} = 0.0504 \approx 0.051$ Answer A (0.0096) is the probability of both mutations occurring without the condition - this ignores the "given that" clause. Answer B (0.048) likely results from calculation errors in the denominator. Answer D (0.200) suggests incorrectly assuming equal likelihood of the four possible outcomes. Remember: conditional probability questions always require dividing the intersection probability by the conditioning event's probability. Never ignore the "given that" information - it fundamentally changes the sample space you're working with.
3. $A$ and $B$ are independent, $P(A)=0.7$ and $P(B)=0.4$. Find the probability that exactly one occurs.
   Answer: 0.54 Exactly one occurs as A without B or B without A. With independence, multiply: 0.7 0.6 = 0.42 and 0.3 0.4 = 0.12, then add to get 0.54. The tempting 0.82 is P(A or B), which also counts the chance both happen, so it is too large for exactly one.
4. If $P(A)=0.5$ and $P(B|A)=0.3$, find the probability of A and not B.
   Answer: 0.35 Start with P(A and B) = P(B|A) P(A) = 0.3 0.5 = 0.15. Since P(A) is split into P(A and B) plus P(A and not B), subtract: 0.5 - 0.15 = 0.35. The tempting 0.15 is the probability of A and B, not A and not B.
5. In a hospital, 45% of patients are male, 60% are over age 65, and 30% are male AND over age 65. If a randomly selected patient is male, what is the probability that the patient is age 65 or younger?
   Answer: 0.333 This question tests conditional probability, a fundamental concept in biostatistics where you need to find the probability of one event given that another event has already occurred. You're looking for P(age ≤ 65 | male), which reads as "the probability a patient is 65 or younger, given that the patient is male." Using the conditional probability formula: P(A|B) = P(A ∩ B) / P(B). First, identify what you know: P(male) = 0.45, P(over 65) = 0.60, and P(male AND over 65) = 0.30. Since P(age ≤ 65) = 1 - P(over 65), you have P(age ≤ 65) = 1 - 0.60 = 0.40. To find P(male AND age ≤ 65), use: P(male AND age ≤ 65) = P(male) - P(male AND over 65) = 0.45 - 0.30 = 0.15. Therefore: P(age ≤ 65 | male) = P(male AND age ≤ 65) / P(male) = 0.15 / 0.45 = 0.333. Answer A (0.150) is the joint probability P(male AND age ≤ 65), not the conditional probability. Answer C (0.400) is P(age ≤ 65) without conditioning on being male. Answer D (0.600) is P(over 65), which is the opposite age group entirely. Remember: conditional probability narrows your sample space. Once you know the patient is male, you're only considering the 45% of patients who are male, then finding what fraction of those are 65 or younger.
6. In a clinical trial, 30% of patients have hypertension (H), 25% have diabetes (D), and 40% have either hypertension or diabetes or both. If a patient is randomly selected and found to have diabetes, what is the probability that this patient also has hypertension?
   Answer: 0.60 Using conditional probability: P(H|D) = P(H∩D)/P(D). First find P(H∩D) using P(H∪D) = P(H) + P(D) - P(H∩D): 0.40 = 0.30 + 0.25 - P(H∩D), so P(H∩D) = 0.15. Therefore P(H|D) = 0.15/0.25 = 0.60. Choice B incorrectly uses P(H∩D)/P(H). Choice C uses P(H)/P(H∪D). Choice D simply uses P(H∩D).
7. In a population study, the probability of having gene variant A is 0.25, gene variant B is 0.40, and having neither variant is 0.50. What is the probability of having both variants A and B?
   Answer: 0.15 When you encounter probability questions involving multiple conditions, think systematically about the relationships between events using the fundamental probability rules. Let's define our events: A = having gene variant A, B = having gene variant B. We know P(A) = 0.25, P(B) = 0.40, and P(neither A nor B) = 0.50. Since having "neither variant" means not having A AND not having B, we can write this as P(A' ∩ B') = 0.50. Using the complement rule, if the probability of having neither variant is 0.50, then the probability of having at least one variant is P(A ∪ B) = 1 - 0.50 = 0.50. Now apply the addition rule: P(A ∪ B) = P(A) + P(B) - P(A ∩ B). Substituting our known values: 0.50 = 0.25 + 0.40 - P(A ∩ B), which gives us P(A ∩ B) = 0.65 - 0.50 = 0.15. Choice A (0.10) likely comes from incorrectly multiplying P(A) × P(B) assuming independence, but these events aren't independent. Choice C (0.20) might result from miscalculating 1 - 0.50 - 0.25 - 0.40, incorrectly treating the probabilities as mutually exclusive. Choice D (0.25) could come from confusing P(A ∩ B) with P(A). Study tip: For overlapping probability problems, always check if the individual probabilities and intersections add up logically using the addition rule. Draw Venn diagrams when possible to visualize the relationships between events.
8. Patients get Drug A or B: $P(A)=0.3, P(B)=0.7, P(R|A)=0.8, P(R|B)=0.6$. Find $P(R)$.
   Answer: 0.66 Weight each conditional probability by the probability of receiving that drug: 0.3 times 0.8 gives 0.24, and 0.7 times 0.6 gives 0.42. Adding these gives 0.66. A tempting mistake is to pick 0.60, but that ignores the 30% of patients treated with Drug A.
9. If $P(A\cup B)=0.6, P(B)=0.3, P(A|B)=0.2$, find $P(A)$.
   Answer: 0.36 First find the intersection: P(A|B) times P(B) = 0.2 × 0.3 = 0.06. Then use the union formula: P(A∪B) = P(A) + P(B) - P(A∩B), so 0.6 = P(A) + 0.3 - 0.06, giving P(A) = 0.36. The tempting mistake is treating 0.06 as the answer, but that is only the intersection, not P(A).
10. In a pharmaceutical study, drug effectiveness follows: P(effective) = 0.75, P(side effects) = 0.30, P(effective AND no side effects) = 0.60. Given that a drug causes side effects, what is the probability that it is still effective?
    Answer: 0.50 This question tests conditional probability, a fundamental concept in biostatistics where you need to find the probability of one event given that another event has occurred. The key phrase "given that a drug causes side effects" signals you need to use the conditional probability formula: $P(A|B) = \frac{P(A \cap B)}{P(B)}$. You're looking for P(effective | side effects). First, identify what you need: P(effective AND side effects) in the numerator, and P(side effects) in the denominator. You're given P(effective AND no side effects) = 0.60, but you need P(effective AND side effects). Since P(effective) = 0.75 total, and 0.60 of that is effective with no side effects, then P(effective AND side effects) = 0.75 - 0.60 = 0.15. Now apply the formula: $P(\text{effective | side effects}) = \frac{0.15}{0.30} = 0.50$ Choice A (0.15) represents P(effective AND side effects), not the conditional probability. Choice B (0.20) might result from incorrectly using P(no side effects) = 0.70 in the denominator instead of P(side effects) = 0.30. Choice D (0.75) is simply P(effective), ignoring the conditioning entirely. The correct answer is C (0.50). Study tip: When you see "given that" language, immediately think conditional probability. Always identify what goes in both the numerator (joint probability) and denominator (probability of the given condition) before calculating. Draw a probability tree or contingency table if the relationships aren't immediately clear.
11. If $P(A)=0.6$, $P(B)=0.5$, and $P(A∪B)=0.8$, find $P(A|B)$.
    Answer: 0.60 Use the addition rule to find the intersection: 0.8 = 0.6 + 0.5 minus P(A and B), so P(A and B) = 0.3. Then P(A|B) = P(A and B) divided by P(B) = 0.3 / 0.5 = 0.60. The tempting 0.30 is only the intersection, not the conditional probability.
12. A laboratory runs three independent quality control tests daily. The probability of detecting contamination when present is 0.8 for each test. If contamination is present, what is the probability that at least one test will detect it?
    Answer: 0.992 P(at least one detects) = 1 - P(none detect) = 1 - (0.2)³ = 1 - 0.008 = 0.992. Choice B incorrectly calculates 1 - (0.2)² using only two tests. Choice C uses the probability for a single test. Choice D calculates (0.8)³, the probability all three detect.
13. Three independent blood samples are tested for contamination. Each sample has a 0.15 probability of being contaminated. What is the probability that exactly two samples are contaminated?
    Answer: 0.057 When you encounter a problem about testing multiple independent samples with a fixed probability of contamination, you're dealing with a binomial probability scenario. This framework applies whenever you have a fixed number of independent trials, each with the same probability of success (or in this case, contamination). To find the probability of exactly two contaminated samples out of three, you need the binomial probability formula: $P(X = k) = \binom{n}{k} p^k (1-p)^{n-k}$, where n = 3 trials, k = 2 successes, and p = 0.15. First, calculate the binomial coefficient: $\binom{3}{2} = 3$. Then substitute: $P(X = 2) = 3 \times (0.15)^2 \times (0.85)^1 = 3 \times 0.0225 \times 0.85 = 0.057$. This confirms answer A is correct. Answer B (0.096) likely comes from incorrectly calculating $(0.15)^2 \times 0.85$ without the binomial coefficient, then doubling it. Answer C (0.225) represents a common error of simply multiplying $3 \times (0.15)^2$ without accounting for the probability that the third sample is uncontaminated. Answer D (0.450) appears to be $3 \times 0.15$, which completely ignores the binomial structure and calculates something meaningless. Remember: binomial problems require three components—the number of ways to arrange the successes, the probability of the successes occurring, and the probability of the failures occurring. Missing any component will lead you to a wrong answer choice that likely appears as a distractor.
14. In an epidemiological study, 60% of patients with symptom S have disease X, 30% have disease Y, and 10% have both diseases. A patient presents with symptom S. What is the probability that this patient has disease Y but not disease X?
    Answer: 0.200 When you encounter probability questions involving overlapping conditions in epidemiology, you need to carefully distinguish between joint probabilities and conditional probabilities, then use set theory principles to find specific combinations. Given that a patient has symptom S, you know: 60% have disease X, 30% have disease Y, and 10% have both diseases. To find the probability of having disease Y but not disease X, you need to subtract the overlap from the total probability of disease Y. The probability of having Y but not X equals P(Y) - P(both X and Y) = 0.30 - 0.10 = 0.20. Looking at the wrong answers: Choice A (0.500) likely comes from incorrectly calculating the complement of having both diseases (1.00 - 0.50), but this ignores the specific question about disease Y. Choice B (0.300) is the trap of using the total probability of disease Y without accounting for the overlap with disease X. Choice C (0.100) represents the probability of having both diseases, which is the opposite of what the question asks. The correct answer is D (0.200). Study tip: For overlapping probability problems, always draw a Venn diagram or use the principle that P(A but not B) = P(A) - P(A and B). Watch for questions that give you marginal probabilities and joint probabilities—the key is identifying what specific combination they're asking for and whether you need to add or subtract the overlap.
15. In a medical database, 35% of patients have condition X, 28% have condition Y, and 12% have both conditions. If a patient does not have condition X, what is the probability that they have condition Y?
    Answer: 0.246 When you encounter conditional probability questions in biostatistics, you're dealing with how one event's probability changes when you know another event has or hasn't occurred. The key formula is $P(A|B) = \frac{P(A \cap B)}{P(B)}$. Here, you need $P(Y|\text{not }X)$. First, identify what you know: 35% have condition X, so 65% don't have X. Since 12% have both conditions and 35% have X total, then 35% - 12% = 23% have only X. This means 28% - 12% = 16% have only Y. Among the 65% without condition X, 16% have condition Y. Therefore: $P(Y|\text{not }X) = \frac{16\%}{65\%} = \frac{0.16}{0.65} = 0.246$. Answer A (0.123) likely comes from incorrectly using the intersection probability (12%) divided by something inappropriate. Answer B (0.160) might result from confusing the conditional relationship or using 16% directly without proper conditioning. Answer D (0.280) represents the unconditional probability of having condition Y, ignoring the given information that the patient doesn't have condition X. The correct answer is C (0.246). Remember this pattern: conditional probability questions require you to restrict your sample space to only those cases where the condition is met. Always double-check that your denominator reflects the appropriate subset of the population, not the entire original sample. Drawing a 2×2 table or Venn diagram can help visualize these relationships clearly.
16. If A and B are independent, $P(A)=0.6, P(A\cup B)=0.8$, find $P(B|A)$.
    Answer: 0.500 For independent events, P(A and B) = P(A)P(B), so P(A or B) = P(A) + P(B) - P(A)P(B). Plug in 0.6 + P(B) - 0.6P(B) = 0.8, giving P(B) = 0.5. Independence means P(B|A) = P(B), so the answer is 0.500. The tempting wrong value 0.300 is P(A and B), not the conditional probability; remember to divide by P(A).
17. Test +: 90% if diseased, 5% if healthy; prevalence 1%. Find $P(D|+)$.
    Answer: 0.154 Out of 1000 people, 10 have disease and 990 are healthy. Of the 10 diseased, 90% test positive: 9. Of the 990 healthy, 5% test positive: 49.5. Total positive tests are 58.5, so the chance a positive test is truly diseased is 9 divided by 58.5, which equals 0.154. The tempting wrong answer 0.009 is the joint probability of being diseased and testing positive, not the conditional probability given a positive test.
18. In a genetics study, three independent genes each have a 0.4 probability of mutation. What is the probability that exactly two of the three genes will mutate?
    Answer: 0.288 When you encounter a genetics problem involving independent events with specific probabilities, you're dealing with a binomial probability situation. Here, you need to find the probability of exactly 2 successes (mutations) out of 3 independent trials, where each trial has a 0.4 probability of success. Use the binomial probability formula: $P(X = k) = \binom{n}{k} \times p^k \times (1-p)^{n-k}$ Where n = 3 genes, k = 2 mutations, and p = 0.4. First, calculate the binomial coefficient: $\binom{3}{2} = \frac{3!}{2!(3-2)!} = 3$ Then: $P(X = 2) = 3 \times (0.4)^2 \times (0.6)^1 = 3 \times 0.16 \times 0.6 = 0.288$ Answer B (0.288) is correct. Answer A (0.384) represents a common error where students multiply 3 × 0.4 × 0.32, forgetting that the non-mutating gene has probability 0.6, not 0.8. Answer C (0.480) might result from incorrectly calculating 3 × 0.4 × 0.4 without considering the third gene at all. Answer D (0.064) equals (0.4)³, which would be the probability that all three genes mutate, not exactly two. Remember that in binomial problems, you must account for all possible outcomes. The binomial coefficient tells you how many ways the event can occur, and you must include both the probability of success and failure in your calculation. Always verify that probabilities of complementary events sum appropriately.
19. A clinical trial has three treatment arms with success rates of 0.7, 0.6, and 0.5 respectively. Patients are randomly assigned with probabilities 0.4, 0.35, and 0.25 to each arm. If a randomly selected patient from the trial was successful, what is the probability they were in the first treatment arm?
    Answer: 0.455 This question tests Bayes' theorem, which helps you find the probability of a cause given an observed effect. When you see a problem asking "given that an outcome occurred, what's the probability it came from a specific source," think Bayes' theorem. You need to find P(Treatment 1 | Success). Using Bayes' theorem: P(Treatment 1 | Success) = P(Success | Treatment 1) × P(Treatment 1) / P(Success). First, calculate the total probability of success across all arms: P(Success) = (0.7)(0.4) + (0.6)(0.35) + (0.5)(0.25) = 0.28 + 0.21 + 0.125 = 0.615 Now apply Bayes' theorem: P(Treatment 1 | Success) = (0.7 × 0.4) / 0.615 = 0.28 / 0.615 ≈ 0.455 Looking at the wrong answers: A) 0.400 is simply the initial assignment probability to Treatment 1, ignoring that we now have additional information about success. B) 0.700 is the success rate of Treatment 1, but this doesn't account for the relative likelihood of being in that arm. D) 0.280 is the numerator (0.7 × 0.4) without dividing by the total probability of success. The key insight is that successful patients are more likely to have come from higher-performing treatment arms. Even though Treatment 1 only gets 40% of patients initially, its high success rate makes it disproportionately represented among successful outcomes. Study tip: In Bayes' problems, always calculate the total probability of the observed outcome first, then apply the formula. The answer will typically differ from simple assignment probabilities because new information changes the likelihood.
20. A pharmaceutical company tests drug efficacy using two methods independently. Method 1 correctly identifies effective drugs 92% of the time. Method 2 correctly identifies effective drugs 88% of the time. What is the probability that both methods fail to identify an effective drug?
    Answer: 0.0096 When you encounter questions about multiple diagnostic tests or methods working independently, you're dealing with probability calculations involving independent events. The key insight is recognizing what "both methods fail" means and how to calculate it. To find the probability that both methods fail to identify an effective drug, you need the failure rate for each method. Method 1 succeeds 92% of the time, so it fails 8% of the time (1 - 0.92 = 0.08). Method 2 succeeds 88% of the time, so it fails 12% of the time (1 - 0.88 = 0.12). Since the methods work independently, you multiply their individual failure probabilities: $P(\text{both fail}) = 0.08 \times 0.12 = 0.0096$ Looking at the wrong answers: Choice B (0.0400) represents a common error where students might incorrectly add the failure rates (0.08 + 0.12 = 0.20) then try some manipulation. Choice C (0.0800) is simply the failure rate of Method 1 alone, suggesting the student ignored Method 2 entirely. Choice D (0.1600) might result from incorrectly squaring one of the success rates or making an arithmetic error in the multiplication. The correct answer is A (0.0096). Remember this pattern: for independent events, multiply probabilities. When calculating failure rates, always subtract the success rate from 1 first. This type of question frequently appears in biostatistics because diagnostic testing often involves multiple independent methods, and understanding combined failure rates is crucial for clinical decision-making.

Start this quiz