Week 8 Self-Test Questions
The ___________ is the exact opposite of the null hypothesis and contains all of the other possibilities.
Alternative hypothesis
If the calculated power is 80%, the beta risk is ____________.
Beta risk = 20%
A manufacturer of widgets wants to see if its average widget heights are above the target of 34 inches. The best type of hypothesis test in this situation would be:
Compares one sample average to a standard, one-sample t-test
Brad is conducting a hypothesis test. He set his alpha equal to .10. QI Macros indicated that the p-value is .15. What is the result of this test?
Fail to reject the null hypothesis
True or False: It is a best practice to run the hypothesis test in QI macros and then determine the alpha risk.
False
True or False: It is appropriate to determine if the test is one- or two- tailed after running a hypothesis test in QI Macros.
False
True or False: The main effects correlation assessment is another way to show the effect of the factors on the output and compare the relative strength of the effects.
False
True or False: You want to prove that the setting does not make a difference. Therefore, you want to reject the null hypothesis.
False,
True or False: Power is defined as (1 - alpha risk).
False, 1-beta risk
True or False: Alpha risk is also referred to as a Type II error.
False, beta risk = type II error
True or False: A two-tailed test describes a hypothesis test that is concerned with one side of the frequency distribution.
False, concerned with both sides
True or False: A correlation plot shows the interaction effect of two factors on the output and compares the relative strength of the effects.
False, interaction plot
True or False: As they relate to DOEs, replicates are the values of a factor that we are interested in testing.
False, levels
True or False: The effect of one of the replicates in an experiment is called the main effect.
False, the effect of one of the factors
True or False: A replicate represents all of the runs of an experiment. Two replicates equal two factorials.
False, two replicates = two complete runs
True or False: If there is a high level of variation among DOE factors, it would be wise to have no replicates in a DOE.
False, would want many replicates to evaluate all levels
Suppose you believe that there is a statistical difference between the test scores of juniors and seniors in a high school economics class. The null hypothesis (H0) is that the mean scores of juniors (μj) is = to the mean scores of seniors (μs) (also noted as H0: μj = μs). What is the alternative hypothesis (Ha)?
Ha: μj ≠ μs - alternative hypothesis is exact opposite of the null
Suppose you are running a Black Belt project to reduce quality escapes and you suspect that there are different escape frequencies depending on the product type. There are three different types of products and the data are normal. The best type of hypothesis test to run in this situation would be ________________.
Three or more variables, ANOVA
True or False: A Type I error occurs when you incorrectly reject the null hypothesis.
True
True or False: A hypothesis test examines two opposing hypotheses about a population, which are the null hypothesis and the alternative hypothesis.
True
True or False: A one-tailed test describes a hypothesis test that is concerned with one side of the frequency distribution.
True
True or False: Alpha risk is also referred to as a Type I error.
True
True or False: An ANOVA compares three or more independent sample averages.
True
True or False: An interaction is the effect of two or more factors in conjunction with one another.
True
True or False: An interaction plot shows the interaction effect of two factors on the output and compares the relative strength of the effects.
True
True or False: If there is a high level of variation among DOE factors, it would be wise to have some replicates in a DOE.
True
True or False: In hypothesis testing, a small p-value suggests the null hypothesis is unlikely to be true.
True
True or False: It is a best practice to state the null hypothesis before running the hypothesis test in QI Macros.
True
True or False: It is appropriate to determine if the test is one- or two- tailed prior to running a hypothesis test in QI Macros.
True
True or False: Power is defined as (1 - beta risk).
True
True or False: The alternative hypothesis should be stated prior to running a hypothesis test using QI Macros.
True
True or False: The effect of one of the factors in an experiment is called the main effect.
True
True or False: You have a p-value > 0.5. Therefore, you failed to reject the null and there is no difference.
True
This error occur(s) when you incorrectly reject the null hypothesis as a result of the hypothesis test.
Type I
This error occur(s) when you incorrectly fail to reject the null hypothesis.
Type II Error
Suppose you are running a Black Belt project to reduce processing time and you suspect that there are different processing times depending on the customer type. There are four different types of customers and the data are normal. The best type of hypothesis test to run in this situation would be:
Variable data that compares more 3 or more averages: ANOVA
An experimental condition that it is characterized by the factor and levels associated with it is said to be ____________________.
a run
Which of the following is true about a type II error? a) It is a conclusion that the population has not changed when in fact it has. b) It is a conclusion that the population has changed when in fact it has not. c) The mean of population A is not equal to the mean of population B. d) Mu = 100.
a) It is a conclusion that the population has not changed when in fact it has. -getting a negative test result back, even tho the patient is positive
One of the advantages of the sample t-test is __________________. a) it can be applied to a relatively small number of cases b) Mu < 5 c) The mean of population A is not equal to the mean of population B d) Mu = 0
a) it can be applied to a relatively small number of cases
Bob walks into a meeting on a DOE that is going to be conducted. He overhears the Black Belt say that the DOE will test the temperature and sensitivity setting at high and low levels. In this situation, the temperature and the sensitivity setting likely are ______________. a) experiment variations b) factors c) exponential correlations d) replicates
b) factors
Which of the following is a valid null hypothesis? a) P > 1/8. b) The mean of population A is not equal to the mean of sample A c) Mu = 100 d) none of the above
c) Mu = 100, a null often states that there is no difference between b/w two sets of data
As they relate to DOEs, ____________ are the values of a factor that we are interested in testing. a) replicates b) factors c) levels d) noise factors
c) levels
The DOE category that is used to determine the contributions from each X and how the Xs interact with each other after the number of Xs are reduced is called ____________________.
characterizing
Significance level is also referred to as _______. a) beta risk b) p c) confidence sigma d) alpha risk
d) alpha risk (type I error)
In hypothesis testing, which of the following statements is always true? a) The P-value is greater than the significance level. b) The P-value is computed from the significance level. c) The P-value is the parameter in the null hypothesis. d) The P-value is a test statistic. e) The P-value is a probability.
e) The P-value is a probability.
The effect of two or more factors in conjunction with one another is an ____________________.
interaction
As it relates to a DOE, a __________ is a variable that is too expensive or difficult to control as part of an experiment.
noise factor
A p-value that is less than .05, indicates a ____ regression equation.
statistically significant, A low p-value (< 0.05) indicates that you can reject the null hypothesis. In other words, a predictor that has a low p-value is likely to be a meaningful addition to your model because changes in the predictor's value are related to changes in the response variable.
A teacher suspects that the mean test scores of males are different from the mean test scores of females. The best type of hypothesis test in this situation would be ___________________.
two-sample t-test
