Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
13 Cards in this Set
- Front
- Back
|
What are the two regions of the sampling distribution of a test statistic? |
Region of rejection and nonrejection |
|
|
Define: critical value (hypothesis testing) |
The value which divides the region of rejection and nonrejection |
|
|
Define: null hypothesis. How is it symbolized? What is the opposite? |
The statement which proves that a claim is true. "H(0):" Alternative Hypothesis: "H(1):" |
|
|
Define: Type I error (hypothesis). How is it symbolized? |
A "false alarm", when one falsely rejects the null hypothesis when it is true. Its symbol is a, alpha. |
|
|
Define: Type II error (hypothesis). How is it symbolized? |
A "missed opportunity to take corrective action", when one does not reject a false null hypothesis. Its symbol is b, beta. |
|
|
Define: level of significance |
The risk of committing a Type I error (a). |
|
|
Define: B risk (beta). How is it calculated? |
The risk of committing a Type II error. It calculates the difference between the hypothesis and actual values of the population parameter. |
|
|
Define: confidence coefficient. How is it calculated? |
The complement of Type I Error. It is probability of accepting H(0) when it should not be rejected and is true. "1 - a". |
|
|
Define: power of a statistical test. How is it calculated? |
The complement of a Type II error. It is probability of rejecting H(0) when it should be rejected and is false. "1 - b". |
|
|
How does one reduce b, beta? Why? |
Increase the sample size, n. This is because a large sample size enables the detection of the smallest difference between the hypothesis and the population values. |
|
|
Define: p-value. |
The probability of getting a test statistic equal to or more than the sample result, given that H(0) is true. Intuitively, it is the probability that H(0) is true. |
|
|
Using the p-value, what are the situations to accept or reject H(0)? |
When p >= a, do not reject H(0). When p <= a, reject H(0). |
|
|
What are the assumptions for using t-distribution for hypothesis testing? |
Normally distributed and population standard deviation is unknown. |
