DOL Section 8
8. 14. Assume that data for a goodness-of-fit test has been structured into effective cells for a chi square calculation. Which of the following distributions loses the most degrees of freedom? a. Normal b. Poisson c. Binomial d. Uniform
Answer a is correct.
8.20. A dendogram, as used in cluster analysis, can be described as a: a. Classification tree b. Pareto diagram c. Decision tree d. Line diagram
Answer a is correct.
8.24.If a sample size of 16 yields an average of 12, and standard deviation of 3, estimate the 95% confidence interval for the population (assume a normal distribution). a. 10.40 <= mu <= 13.60 b. 10.45 <= mu <= 13.55 c. 10.53 <= mu <= 13.47 d. 10.77 <= mu <= 13.23
Answer a is correct.
8.28. When plotting a regression chart on graph paper, what metric is used for the horizontal scale? a. Time b. Count data c. Variable data d. Percentages
Answer a is correct.
8.3. A random sample size n is to be taken from a large population having a standard deviation of 1". The sample size is to be determined so that there will be a 0.05 risk probability of exceeding a 0.1" tolerance error in using the sample mean to estimate m. Which of the following values is nearest the required sample size? a. 385 b. 40 c. 200 d. 100
Answer a is correct.
8.34. A small change truly exists between a current process and an experimental process. However, an insufficient sample size is collected to determine this difference. What type of error would result? a. A type II error b. A 1-alpha ·decision c. A type I error d. A 1-beta decision
Answer a is correct.
8.35. Identify the subjective root cause analysis tool from the options below: a. 5 whys b. Pareto analysis c. Control charts d. Regression analysis
Answer a is correct.
8.44. What is the probability of the top event occurring in the fault-tree below, given the probability of event A is 0.9 and the probability of event B is 0.8? a. 0.72 b. 0.70 C. 0.99 d. 0.98
Answer a is correct.
8.45. The alpha critical region, to determine if a new pen lasts longer, would be placed: a. In the upper tail b. In both upper and lower tails c. In the lower tail d. In neither tail
Answer a is correct.
8.47. The probabilistic regression model for any particular observed value of Y contains a term beta 0 , which represents: a. The Y axis intercept, when X = 0 b. The Y axis intercept, when X = 1 c. The slope of the model d. The X axis intercept, when Y = 0
Answer a is correct.
8.54. From a gap analysis perspective, why does an organization need performance metrics? a. To provide information for goal achievement b. To indicate the number of and return on improvement projects c. To determine the best internal and external benchmarks d. To measure customer retention and loyalty
Answer a is correct.
8.55. Which of the following tasks is value added? a. An appropriate product development process b. Reworking parts to meet customer requirements c. MRB meetings d. Efficient material handling of customer returns
Answer a is correct.
8.56. It is desirable to reduce the variation in a process. The current variance is known to be seven. A new process yielded a standard deviation of two for twenty-five test trials. What is the calculated statistic and decision for 95% confidence ? a. 13.71, reject the null b. 13.71, fail to reject the null c. 13.85, reject the null d. 13.85, fail to reject the null
Answer a is correct.
8.1. A study was conducted on the relationship between the speed of different cars and their gasoline mileage. The correlation coefficient was found to be 0.35. Later, it was discovered that there was a defect in the speedometers and they had all been set 5 miles per hour too fast. The correlation coefficient was computed using the corrected scores. Its new value will be: a. 0.30 b. 0.35 C. 0.40 d. -0.35
Answer b is correct.
8.15. Which of the following statements is true regarding nonparametric tests? a. They have a greater efficiency than comparable parametric tests b. They can be applied to correlation studies c. They require assumptions about the shape or nature of the populations involved d. They require computations that are more difficult than corresponding parametric methods
Answer b is correct.
8.16. A two-way analysis of variance has r levels for one variable and c levels for the second variable with 2 observations per cell. The degree of freedom for interaction is: a. 2(r)(c) b. (r-1)(c-1) c. rc -1 d. 2(r-1)(c-1)
Answer b is correct.
8.17. A null hypothesis states that a process has not improved after some modifications were made. The type II error is to conclude that: a. One has failed to reject the null hypothesis when it is true b. One has failed to reject the null hypothesis when it is false c. One has rejected the null hypothesis d. One has made a correct decision with an alpha probability
Answer b is correct.
8.18. In the manufacture of airplane fuselage frame sections, thousands of rivets are used to join aluminum sheets and frames. A study of the number of oversize rivet holes and the number of minor repairs on a unit yielded a correlation coefficient of +/- 1.08 . This means that: a. The number of oversized rivet holes is a good predictor of the number of minor repairs b. A new statistician should be hired c. The number of oversized rivet holes is a poor predictor of the number of minor repairs d. A small number of minor repairs will have to be made
Answer b is correct.
8.19. In an experiment designed to compare two different ways of measuring a given quantity, it was desired to test the null hypothesis that the means were equal at the 0.05 level of significance. A sample of five parts was measured by method A and a sample of seven parts with method B. A t-ratio of 2.179 was obtained. One should: a. Reject the null hypothesis b. Fail to reject the null hypothesis c. Conclude that A is greater than B d. Conclude that more should be known about the sample means
Answer b is correct.
8.23. The equation below is: a. The covariance of X and Y b. The correlation coefficient of X and Y c. The coefficient of determination of X and Y d. The variance of the product of X and Y
Answer b is correct.
8.27. Tremendous advances have been made in the quality of an electronic component produced in quantities of one million units per year. Last year only six defectives were discovered. A further improvement was made. The plant manager asked the master black belt to run a 100,000 unit trial to determine with 95% confidence if the rate had been lowered by 2 DPMO. What was the master black belt's response? a. It will take too much time b. It can't be done with 100,000 units c. It will only be proven if defectives are found d. There must be a larger improvement for testing purposes
Answer b is correct.
8.29. Consider the SS and MS columns of an analysis of variance table for a single factor design. The appropriate ratio for testing the null hypothesis of no treatment effect is: a. SS treatments divided by SS residual b. MS treatments divided by MS residual c. SS treatments divided by MS residual d. MS treatments divided by SS residual
Answer b is correct.
8.30. Which of the following is considered a preventive technique? a. Rework due to poor molding b. Performing design validation c. In-process inspection by an inspector d. Re-tooling because of engineering changes
Answer b is correct.
8.31. In a t test, alpha is 0.05, therefore: a. 5% of the time one will say that there is no real difference when there is a difference b. 5% of the time one will say that there is a real difference when there is not a difference c. 95% of the time one will make an incorrect inference d. 95% of the time the null hypothesis will be correct
Answer b is correct.
8.36. Why should an experimenter plot data points and graph the least squares line if a probabilistic regression model exists? a. To visually present the relationship to others b. To check for fit; there may be a calculation error c. There's no rational reason for doing so d. To permit a projection outside of the test area
Answer b is correct.
8.37. The current process produces fifty units per shift, a new process yielded fifty-two units per shift for sixteen straight shifts, with a standard deviation of four units per shifts. What is the level of confidence that the process has changed? a. <90% b. 90-95% C. 95-99% d. >99%
Answer b is correct.
8.38. Most practitioners of regression analysis would not be surprised to find that: a. The coefficient of determination is greater than r^2 b. The r^2 value is a smaller absolute value than r c. The correlation coefficient equals r^2 d. The correlation coefficient equals the slope of the line
Answer b is correct.
8.40. Which table should be used to determine a confidence interval on the mean when a is not known and the sample size is 10? a. z b. t c. F d. X'
Answer b is correct.
8.50. What inference test compares observed and expected frequencies of test outcomes? a. F test b. Chi square test c. t test d. Paired t test
Answer b is correct.
8.52. A process FMEA is generally performed: a. Just after the design FMEA is completed b. Just before the production tooling is authorized c. Just after the design drawings are finalized d. As soon as a manufacturing defect is uncovered
Answer b is correct.
8.53. A lowered rejection rate following corrective action: a. Gives positive indication that one cause of nonconformance has been removed b. May be unrelated to the corrective action c. Indicates that the corrective action was directly related to the problem d. Has no significance
Answer b is correct.
8.58. How are the expected values in a contingency table calculated? a. Column total - row total I grand total b. (Column total) (row total) I grand total c. Column total + row total I grand total d. Row total - column total I grand total
Answer b is correct.
8.7. When constructing a power of test curve, one would not be surprised to discover that as alpha (a) increases: a. The value of mu becomes greater b. Beta decreases c. The probability of rejecting the null hypothesis decreases d. The sample size becomes larger
Answer b is correct.
8.13. Which of the following statements concerning the coefficient of simple linear correlation, r, is true? a. r = 0.00 represents the absence of a relationship b. The relationship between the two variables must be nonlinear c. r = 0.76 has the same predictive power as r = -0.76 d. r = 2.00 represents a perfect relationship
Answer c is correct.
8.2. Failure modes and effects analysis involves what activity? a. The determination of the probability of failure in a specified period of time b. The expected number of failures in a given time interval c. The study of how a product fails and what causes the failure d. A study of the probability of success in a given time period
Answer c is correct.
8.21. An assessment technique to compare a company's current performance to a desired or potential performance is called: a. Benchmarking b. SWOT analysis c. Gap analysis d. Marketplace response
Answer c is correct.
8.22. In performing an analysis of variance for a single factor experiment, a fundamental assumption which is made is that the factor: a. Means are equal b. Means are unequal c. Variances are equal d. Variances are unequal
Answer c is correct.
8.25. In order to test whether the average output of one machine is the same or greater value than another machine, a sample of ten pieces was taken from each. The calculated t-value turned out to be 1.767. a. The obtained t-ratio does not fall within the critical region b. There was no significant difference between the means c. The null hypothesis was rejected d. The null hypothesis was accepted
Answer c is correct.
8.32. The risk priority number (RPN) is the measure of risk related to a particular failure mode. The ratings for each category (severity, occurrence, and detection) are on a 1 to 10 scale. If a FMEA has 10 failure modes with RPN numbers ranging from 50 to 300, an improvement team's recommended actions should focus on which of the following? a. Working on those failure modes with RPNs greater than 50 b. Using the Pareto principle to prioritize the highest RPNs c. Identifying high severity failure modes followed by high RPN numbers d. Using the Pareto principle and start with the top 20% of the failure modes
Answer c is correct.
8.39. The hybrid option on a $25,000 car costs $3,000. A gas mileage test found the hybrid averaged 39.1 mpg and the standard model averaged 34. 7 mpg and a p-value of 0.024. At a level of significance of 5%, the difference is: a. Not statistically significant, buy the standard car b. Not practically significant, buy the hybrid car c. Statistically significant, but not practically significant d. Statistically significant, one should buy the hybrid
Answer c is correct.
8.42. Given the following results obtained from a fixed factor, randomized, block design experiment, in which the production outputs of three machines A, B, and C are compared: a. 2 b. 3 c. 12 d. 14
Answer c is correct.
8.46. It is desirable to reduce the variation in a process. The current variance is known to be six. A new process yielded a standard deviation of two for twenty-five trials. What is the chi square calculated statistic ? a. 13.85 b. 15.66 C. 16.00 d. 18.24
Answer c is correct.
8.48. For a linear correlation the total sum of squares equals 1,600 and the total sum of squared errors equals 1,000. What is r2? a. 0.600 b. 0.625 C. 0.375 d. 0.750
Answer c is correct.
8.5. Identify a non-value added activity that would be considered a form of processing muda: a. Any and all forms of transportation b. An ergonomically unsound workplace c. Reshaping a product due to poor dies d. Producing more than needed by the customer
Answer c is correct.
8.51. A product was yielding 90% recovery before an improvement was made. To determine if a 2% change (in either direction) has been made at the 95% confidence level, what sample size should be taken? a. 468 b. 648 C. 864 d. 1,728
Answer c is correct.
8.59. If two sigma limits are substituted for conventional three sigma limits on a control chart, which of the following will occur? a. Alpha risk decreases b. Beta risk increases c. Alpha risk increases d. Sample size increases
Answer c is correct.
8.6. The test used for testing significance in an analysis of variance table is the: a. Z test c. F test b. t test d. Chi square test
Answer c is correct.
8.26. When a problem solving team applies the 5 whys technique, they are attempting to: a. Determine if the interviewee is telling the truth b. Understand the basics of the problem c. Eliminate areas not to investigate d. Determine the root cause of the problem
Answer d is correct.
8.41. MANOVA is used for testing many independent X variables and multiple Y dependent variables. The primary reason ii is preferred to a plain ANOVA when performing the testing is: a. The MANOVA is much faster b. The alpha value can range from 5% to 15% with MANOVA c. Only 4 or 5 dependent variables can be tested with ANOVA d. ANOVAs used across many dependent variables could increase the alpha risk
Answer d is correct.
8.49. Goodness-of-fit calculations for various distributions have many features in common. Which of the following are included? a. They all use the same DF and the same assumed distribution b. They all use the same assumed distribution and data values structured in cells c. They all use a calculated chi square test statistic and the same DF d. They use data values structured in cells and a calculated chi square test statistic
Answer d is correct.
8.57. Suppose that, given X = 35, and Z .01 = ± 2.58, one establishes confidence limits for mu of 30 and 40. This means that: a. The probability that¬µ= 35 is 0.01 b. The probability that¬µ= 35 is 0.99 c. The probability that the interval contains¬µ is 0.01 d. The probability that the interval contains¬µ is 0.99
Answer d is correct.
8.8. When finding a confidence interval for mean m, based on a sample size of n: a. Increasing n increases the interval b. Having to use S, instead of n decreases the interval c. The larger the interval, the better the estimate of µ d. Increasing n decreases the interval
Answer d is correct.
8.43. If an investigator were interested in performing a chi-square hypothesis test of the equality of measurement data, which of the following would be an option? a. Runs test b. Mood's Median test c. Mann Whitney test d. Kruskal-Wallis test
Answers a, b, and care tested from table values. The Kruskal-Wallis test can require can require a chi-square ]
