Hi guys, i was doing some finquiz mocks and found this question:
[Question and answer removed by admin]
I think this is wrong, and the correct answer should be A. As I understand type I error ir alpha, so a lower confidence interval translates into higher alpha then higher chance of type I error… What Im missing in this question?
Another question, I have Schweser, Finquiz and CFA institute mocks, and the way questions are done is very different from each other! Which one is more similar to the real exam? Another doubt is, when I enter in my candidate rosurces in the cfa site, every time I try to do a mock, the mock questions changes and when I google the questions, they were from previous years mocks… I thought there was just 1 mock, but look likes there are infinite, because it always change! Im looking the wrong test??
Let’s assume we are taking some sampling and with 0,05 error probabiltiy (95 % significance level) we risk to accept wrong null hypothesis, so Type II or beta error (I know in curriculum only Type 1 is named apha but in literature type 2 error is beta). If we extend error probabiltiy on 0,1 (90 % significance level) it is more likely that incorect null hypothesis would be accepted.
Assume 1 tailed test.
Reject Null Hy. if it is less or equal of 0,05 probability (95 % significance), if it is > 0,05, do not reject 0.
If we test on 0,1 (90 % significance level), reject Null only if is < 0,1 so the risk of accept wrong Null (Type 2) is larger.
Maybe I am wrong. Anyway since I am not brilliant in maths and inferential statistics, working hard every day to meet the CFA concept. Mathematicians are in a privileged position in this examinations. Even in accounting CFA put many mathematic approach.
FinQuiz materials are known for errors, and not good practice or mock, it will confuse you more. the same goes for their notes and formula sheet.
For the Significance level question, a reduction in C.I leads to an increase in significant level, which increases the probability of wrongfully rejecting Ho (Type 1 Error) Thus Option A is correct.
The closest to the answer for the Mosaic Theory question is option C of Non-public Immateriality, However, it is still not clear enough to be regarded as the correct answer because Mosaic theory is the combination of Material Public information with Non-Material Non-Public information.
Beta risk is the risk that the decision will be made that the part is not defective when it really is. In other words, when the decision is made that a difference does not exist when there actually is. Or when the data on a control chart indicates the process is in control but in reality the process is out of control. If the power desired is 90%, then the Beta risk is 10%. There is a 10% chance that the decision will be made that the part is not defective when in reality it is defective. "
Alpha risk is the risk of incorrectly deciding to reject the null hypothesis. If the confidence interval is 95%, then the alpha risk is 5% or 0.05. For example, there is a 5% chance that a part has been determined defective when it actually is not. One has observed or made a decision that a difference exists but there really is none. Or when the data on a control chart indicates the process is out of control but in reality the process is in control. Alpha risk is also called False Positive and Type I Error.
Confidence Level = 1 - Alpha Risk
Alpha is called the significance level of a test. The level of significance is commonly between 1% or 10% but can be any value depending on your desired level of confidence or need to reduce Type I error. Selecting 5% signifies that there is a 5% chance that the observed variation is not actually the truth.
The confidence level (1-alpha) and alpha must sum to one.
The power of a test (1-beta) and beta must sum to one.
Each one deals with a different true state of nature.
Alpha and the confidence level deal with the null being true (in reality). From this state, you can reject Ho or FTR Ho. Rejection of Ho when Ho is true is a Type I error with probability alpha. Failing to reject Ho when Ho is true is a correct decision and is denoted by the confidence level (1- alpha).
Power and beta deal with the null being false (in reality). Given that the null is false, if we accept the null, we have made a mistake, a Type II error; this occurs with probability beta. If we reject Ho, and Ho is actually false, we have made a correct decision, which has the probability (1-beta), power.
A is the correct answer. If we hold everything constant and increase alpha (decrease the confidence level), we will decrease the probability of a Type II error–B is factually incorrect. Choice C has been ruled out by our knowledge that alpha (probability of Type I error will increase). There’s no need for critical thinking in this question; it’s definitional. If alpha is the probability of a Type I error, and Confidence level (down) --> alpha (up), then P(Type I error) has gone up.
You’re right that alpha and beta are both incorrect decisions regarding different states of nature, but your understanding of the concept is mistaken. Increasing the probability of a Type I error to 0.10 from 0.05 increases the chance of a Type I error (rejecting the null when it is actually true). A Type II error is accepting (or FTR) a null that is actually false. The answer choices do not have the appropriate effect on beta, the Type II error rate. Ceteris paribus, increasing alpha will decrease beta.
You should review this concept in the text or any other statistical reference (they’re easy to mix up at first, but practice can set them straight!).
Regarding Beta or Type 2 error