Conditional Probability and Independence nonsense in a problem The statement: Suppose that a patient tests positive for a disease affecting 1% of the population. For a patient who has the disease, there is a 95% chance of testing positive, and for a patient who doesn't has the disease, there is a 95% chance of testing negative. The patient gets a second, independent, test done, and again tests positive. Find the probability that the patient has the disease.

wijii4 2022-09-17 Answered
Conditional Probability and Independence nonsense in a problem
The statement:
Suppose that a patient tests positive for a disease affecting 1% of the population. For a patient who has the disease, there is a 95% chance of testing positive, and for a patient who doesn't has the disease, there is a 95% chance of testing negative. The patient gets a second, independent, test done, and again tests positive. Find the probability that the patient has the disease.
The problem:
I can solve this problem, but I'm unable to understand what is wrong with the following:
Let T i be the event that the patient tests positive in the i-th test, and let D be the event that the patient has the disease.
The problem says that P ( T 1 , T 2 ) = 0.95 2 0.01 + 0.05 2 0.99 = 0.0115, because the tests are independent.
By law of total probability we know that:
P ( T 1 , T 2 ) = 0.95 2 0.01 + 0.05 2 0.99 = 0.0115
Replacing, and assuming conditional independence given D, we have:
P ( T 1 , T 2 ) = 0.95 2 0.01 + 0.05 2 0.99 = 0.0115
This is the correct result, but now let's consider that:
P ( T 1 , T 2 ) = P ( T 1 ) 2
We know that P ( T 1 , T 2 ) = P ( T 1 ) 2 for all i because of symmetry, so we have P ( T 1 , T 2 ) = P ( T 1 ) 2 . Again, by law of total probability:
P ( T 1 ) = 0.95 0.01 + 0.05 0.99 0.059
P ( T 1 ) = 0.95 0.01 + 0.05 0.99 0.059
So we have:
P ( T 1 , T 2 ) = P ( T 1 ) 2 0.059 2 0.003481
The second approach is wrong, but it seems legitimate to me, and I'm unable to find what's wrong.
Thank's for your help, you make self studying easier.
You can still ask an expert for help

Expert Community at Your Service

  • Live experts 24/7
  • Questions are typically answered in as fast as 30 minutes
  • Personalized clear answers
Learn more

Solve your problem for the price of one coffee

  • Available 24/7
  • Math expert for every subject
  • Pay only if we can solve it
Ask Question

Answers (1)

Kennedi Lawson
Answered 2022-09-18 Author has 2 answers
The patient gets a second, independent, test done ...
The word "independent" as used in the question does not refer to statistical independence. It refers to the second test being done without any direct causal influence from the first test. The lack of a causal relationship between the two tests does not imply the lack of a correlation between them (in fact, the results of the two tests are quite positively correlated with each other).
Incidentally, the (fallacious) idea that correlation implies causation is equivalent (by contrapositive) to the (also fallacious)idea that a lack of causation implies a lack of correlation.
Perhaps the folks over at the English Language & Usage Stack Exchange can clarify the non-mathematical use of the word "independent" better than I can.
We know that for any two events, regardless of independence, the following is true:
P(T1∩T2)=P(T1)P(T2|T1)
Suppose, for contradiction, that T1 and T2 are statistically independent. By definition,
P(T1∩T2)=P(T1)P(T2)
In order for the first and second equations above to both be satisfied, it must be the case that
P(T2|T1)=P(T2)
This is a contradiction. If the first test is positive, the second test clearly must be more likely to also be positive. Therefore,
P(T2|T1)≠P(T2)⟹P(T1∩T2)≠P(T1)P(T2)⟹T1 and T2 are not independent
The original problem, which asks for the value of P(D|T1,T2), can be solved using Bayes' theorem, and no assumption about the statistical independence between T1 and T2 is necessary.
Not exactly what you’re looking for?
Ask My Question

Expert Community at Your Service

  • Live experts 24/7
  • Questions are typically answered in as fast as 30 minutes
  • Personalized clear answers
Learn more

You might be interested in

asked 2022-09-20
What can we conclude from correlation?I just got my statistics test back and I am totally confused about one of the questions!
A study was done that took a simple random sample of 40 people and measured whether the subjects were right-handed or left-handed, as well as their ages. The study showed that the proportion of left-handed people and the ages had a strong negative correlation. What can we conclude? Explain your answer.
I know that we can't conclude that getting older causes people to become right-handed. Something else might be causing it, not the age. If two things are correlated, we can only conclude association, not causation. So I wrote:
We can conclude that many people become right-handed as they grow older, but we cannot tell why.
asked 2022-08-23
Determining correlation given 2 other correlation
Hi I'm given a rather ambigious question on correlations. My question is how do we determine the correlation between 2 varibles given their correlation with other variables?
Correlation between chocolate consumption per capita and number of Nobel laureates per 10 million persons for a broader list of 90 countries = 0.45
Perfect positive association bewteen chocolate consumption and chili consumption per capita (correlation = 1)
Correlation between chili consumption per capita and nobel laureates per 10 million persons: ?
1) > 0.45
2) = 0.45
3) < 0.45
4) cannot determine
asked 2022-07-20
Correlation of Rolling Two Dice
If A is a random variable responsible for calculating the sum of two independent rolls of a die, and B is the result of calculating the value of first roll minus the value second roll, is is true that A and B have a c o v ( A , B ) 0? In other words, is it true that they are correlated?
I've come to the conclusion that they must be correlated because they are not independent, that is, the event of A can have an impact on event B, but I remain stuck due to the fact that causation does not necessarily imply correlation.
I know that independence −> uncorrelation, but that the opposite isn't true.
asked 2022-07-23
Probability (independent?) events
Hi everyone I have a question about the following problem:
Events for a family: A 1 = ski, A 2 == does not ski, B 1 = has children but none in 8-16, B 2 = has some children in 8-16, and B 3 = has no children. Also, P ( A 1 ) = 0.4, P ( B 2 ) = 0.35, P ( B 1 ) = 0.25 and P ( A 1 B 1 ) = 0.075, P ( A 1 B 2 ) = 0.245. Find P ( A 1 B 1 ) = 0.075.
Here is my solution:
Since P(A1 and B1) = 0.075, P(A2 and B1) = 0.25-0.075= 0.175. Also since P(A1 and B2) = 0.245, P(A2 and B2) = 0.35 - 0.245 = 0.105. From this we can find P(A2 and B3) which is 0.6-0.175-0.105 = 0.32. But when I use the formula for independent events formula P ( A 2 B 3 ) = P ( A 2 ) P ( B 3 ) I get 0.24. Does this mean that the events are not independent? If so, how are these events not independent?
asked 2022-07-18
Correlation: Concept to FormulaIn digital signal processing, we calculate the correlation between two discrete signals by multiplying corresponding samples of the two signals and then adding the products. Where does this process/formula for correlation come from?
I understand the concept of correlation (similarity) between two signals. But I fail to understand how it translates to the formula that it does.
All the texts I have seen so far start with this formula and explain cross correlation, auto correlation, etc. None of them attempt to explain how the formula was derived in the first place.
asked 2022-08-18
Statistics:How to prove that one variable's change is influenced by another variable,that is to say ,they are related?
I major in Bioinformatics. Now,I am in a problem: we all know that temperature changes during a year , I find that a disease incidence is really high when temperature is relatively high , while it becomes really low when the temperature is relatively low , that is to say ,they are related. So ,I want to find out a way to prove that they are related ,not just intuitively feel that they are related. So, any suggestions?
asked 2022-07-16
PCA vs Correlation
What is the relationship between (first) principal component(s) and the correlation matrix or the average correlation of the data. For example, in an empirical application I observe that the average correlation is almost the same as the ratio of the variance of the first principal component (first eigenvalue) to the total variance (sum of all eigenvalues).
Is there a mathematical relationship?

New questions