CQEprep V 2.0 - Quality Certification Training

Sample Questions, Answers and Explanations

Copyright ©1997, Datachem Software Inc., Westborough, MA

 

Question #: 1
Subject Area: General Knowledge

In a normal distribution the mean plus two standard distributions estimates the _____ ____ percentile of the distribution.

   A) 97.5
   B) 95.0
   C) Lower 90.0
   D) Middle 84.0

The correct answer is: A

The mean plus 1.96 standard deviations will estimate the point at which 97.5 % of the population will be less than. If the question were the mean minus 1.96 standard deviations, then it would be the point where 2.5 % of the population will be less than.

Back | Top


Question #: 2
Subject Area: General Knowledge

You are writing a book on TQM. You discover that the chapter you are currently working on has been significantly explained by a peer in the industry in her book. You decide that there are numerous examples that you could use in your book from her's. You should:

   A)Quote her book if you use minimal amounts of her
     information, giving her credit for the quotes.
   B)Contact her and/or her agent to discuss your
     desire to use a portion of her material in your
     book.
   C)Rewrite what she has written, changing just enough
     of the information to keep you from violating any
     copyrights.
   D)A) and B)

The correct answer is: D

If you are writing a work that is different enough to be published you should pursue your work. However, if there is information that needs to appear in you work that your peer has created, contacting her as a matter of professional courtesy is appropriate. There is a limited amount of quoting that is legitimate and legal without permission, but the overall body of knowledge in the quality arena requires your best effort and professional approach. Of course, the use of appropriate legal counsel is a must.

Back | Top


Question #: 3
Subject Area: General Knowledge

If the mean of the sample means is 7.748 and R-bar is 0.01 and the sample size is 5, what is the lower control limit for the X-bar chart?

   A) 7.738
   B) 7.585
   C) 7.690
   D) 7.255
   E) None of the above

The correct answer is: C

The formula for the LCL for a variable X-bar chart is LCL = X - A(2) * R-bar.
For a sample size of n = 5, A(2) = 0.577. Therefore the lower control limit (LCL) = 7.748 - 0.577 * 0.10 = 7.690.

Back | Top


Question #: 4
Subject Area: General Knowledge

Your company has become a VAR of some software for the documentation of quality systems. Your client in your consulting business is searching for such a product and asks your advice. You should:

   A) Tell them to buy the product you sell, but don't
      tell them that you are the distributor.  After
      all, a sale is a sale.
   B) Advise your client that you sell a product that
      does what they are looking for in the way of
      documentation, and decline to further assist them
      in their pursuit of a product.
   C) Advise your client that your company offers such a
      product, that you may have a bias, and that you
      would like them to consider your product in their
      search.
   D) None of the above.

The correct answer is: C

Your responsibility is to your client and to your own company. Your client needs to be made aware of your connection to any specific product they may be considering. Declining to offer them assistance would be doing both your client and your company a great disservice. Therefore, Answer C) is the best answer.

Back | Top

Question #: 5
Subject Area: General Knowledge

Which of the following standards is appropriate to use for the development of criteria for your company's quality systems auditors?

   A)  ISO 9001
   B)  ISO 10011-1
   C)  ISO 10011-2
   D)  None of the above

The correct answer is: C

ISO 10011-2 is titled: "Guidelines for auditing quality systems - Part 2: Qualification criteria for quality systems auditors."

Back | Top


Question #: 6
Subject Area: Measurement Systems

Primary reference standards for the plant should be maintained:

   A)  in a separate gage room
   B)  in a locked cabinet
   C)  with easy access to the quality department
   D)  all of these
   E)  none of these

The correct answer is: E 

A primary standard is in the proper care of a national bureau of standards or possibly a standards organization. It is most likely that working standards and possibly transfer standards would be maintained at the plant level. An example of a working standard is the gage block.

Back | Top


Question #: 7
Subject Area: Measurement Systems

When taking multiple measurements on the same gage block with an air gage it is noted that the results are very repeatable. This is an example of:

   A)  accuracy
   B)  precision
   C)  accuracy and precision
   D)  none of these are correct


The correct answer is: B 

In this case we are talking about the ability to repeat the same measurement reliably. This is called precision. Accuracy, on the other hand, is a measure of the ability of the instrument to record the true value.

Back | Top


Question #: 8
Subject Area: Measurement Systems

For every one turn of the thimble on a 1" micrometer the spindle advances:

   A)  .001"
   B)  .025"
   C)  .010"
   D)  .0025"

The correct answer is: B 

The micrometer screw thread has 40 threads per in., thus one turn advances the spindle 1/40 or .025".

Back | Top


Question #: 9
Subject Area: Measurement Systems

A steel 3" gage block has a coefficient of thermal expansion of 6.4 millionths of an in. per in. per degree F. If the gage block was calibrated to be exactly 3" at 20 C, and the gage block is now at 90 F, what is the actual length of the gage block at this temperature?

   A)  3.0004224
   B)  3.0013440
   C)  3.0042240
   D)  the actual length does not change
   E)  none of these is correct
   

The correct answer is: A 

In order to determine the new length at a higher temperature than calibration, you would multiply the coefficient of expansion x the gage block length x the temperature change and add this to the original length. In this problem you must first convert the calibration temp. from degrees C to degrees F. The calculation would be 3 + 3 x 6.4 x 10^-6 x (90 - 68). This shows the importance of a reference temperature when taking measurements.

Back | Top


Question #: 10
Subject Area: Measurement Systems

If you are using gage blocks as a reference and measuring an aluminum part at a higher temperature than the standard calibration temperature of 20C (68F), the part would measure longer than it actually is at 20C (68F) because:

   A) the coefficient of thermal expansion for aluminum
      is less than that of steel
   B) the coefficient of thermal expansion is greater
      for aluminum than steel
   C) it makes no difference what the coefficient of
      thermal expansion is if the material and gage
      blocks are at the same temperature
   D) none of these is correct


The correct answer is: B 

Since the aluminum expands more rapidly than steel, the part will actually be relatively longer than it was at 68F and it will measure longer.

Back | Top


Question #: 11
Subject Area: Product, Process and Mat.

*Shewhart X-bar control charts are designed with which one of the following objectives?

   A)  Reduce sample size.
   B)  Fix risk of accepting poor product.
   C)  Decide when to hunt for causes of variation.
   D)  Establish an acceptable quality level.

The correct answer is: C

After control limits are calculated, it is possible, using Shewhart's chart, to distinguish between common cause and special cause variation. With points falling outside the control limits or the presence of abnormal, unnatural patterns within the control limits, special cause variation is indicated. At this point, in most cases, the assignable cause is determined and an appropriate adjustment is made.

Back | Top


Question #: 12
Subject Area: Product, Process and Mat.

*In which one of the following is the use of an X-bar and R chart liable to be helpful as a tool to control a process?

   A) The machine capability is wider than the
      specification.
   B) The machine capability is equal to the
      specification.
   C) The machine capability is somewhat smaller than
      the specification.
   D) The machine capability is very small compared to
      the specification.

The correct answer is: C

Monitoring process variation in order to be able to respond to special causes is very critical when machine capability is only slightly smaller than specification. Response must be made on a real-time basis with little or no delay. When a high capability exists the X-bar and R chart is not the appropriate tool to use. When machine capability is wider or equal to specifications action must be taken on the process.

Back | Top


Question #: 13
Subject Area: Product, Process and Mat.

*If a process is out of control, the theoretical probability that four consecutive points on an X-bar chart will fall on the same side of the mean is:

   A) Unknown.
   B) (1/2)^4
   C) 2 x (1/2)^4
   D) 1/2 x (1/2)^4

The correct answer is: A 

A process that is out of control may have points on both sides of the mean, with no consecutive points on the same side of the mean. The theoretical probability of four points falling on one side of the mean in a consecutive pattern, with the given information, is unknown.

Back | Top


Question #: 14
Subject Area: Statistical Principles

The "t" distribution should be used for interval estimates when:

   A) The sample size is 30 or less
   B) The population distribution is not normal
   C) The population standard deviation is not
      known
   D) A) and B)
   E) A) and C)
         

The correct answer is: E 

Both conditions A) and C) are necessary. The normal distribution is used if the population standard deviation is known.

Back | Top


Question #: 15
Subject Area: Statistical Principles

The Poisson distribution can probably be used as a good approximation of the binomial distribution if:

   A) p > .15
   B) The number of trials is less than 10
   C) Both A) and B) are satisfied
   D) None of the above
The correct answer is: D 

In general p should be < .1 and the number of trials 15 or more. Some statisticians may argue that p should be < .05 with at least 20 trials.  While there is no agreement on the exact p and n values, p should be "small" and n "large".

Back | Top


Question #: 16
Subject Area: Statistical Principles

All but one of the following statements about linear regression analysis are true. Select the untrue statement.

   A) linear regression analysis is used to describe
      an association between two variables
   B) the linear regression equation is frequently
      useful for extrapolating data
   C) if the slope of the linear regression is
      negative the relationship is inverse
   D) customarily the independent variable is plotted
      on the x axis and the dependent variable is
      plotted on the y axis


The correct answer is: B 

It is dangerous to extrapolate from a regression equation. One should not make predictions outside the range of the given data. However this may be common practice due to the ease of doing so and the impression that time and money may be saved by avoiding additional testing.

Back | Top


Question #: 17
Subject Area: Statistical Principles

For mutually exclusive events the probability of A or B happening is equal to:

   A) P(A) + P(B)
   B) P(A) + P(B) - P(AB)
   C) P(A) + P(B/A)
   D) P(A) X P(B)
   
   
The correct answer is: A 

The formula for mutually exclusive events which determines the probability of either one event or another happening is P(A or B) = P(A) + P(B). Mutually exclusive events cannot occur at the same time.

Back | Top


Question #: 18
Subject Area: Statistical Principles

If we use a Venn Diagram to represent non mutually exclusive events A and B:

   A) two separate diagrams must be used
   B) the events can be represented by non overlaping
      circles inside a rectangle
   C) the events can be represented by circles that
      overlap inside the rectangle
   D) the Venn Diagram cannot be used for this situation

The correct answer is: C

A single rectangle can be used and since the events are not mutually exclusive they must be represented by overlapping circles.

Back | Top


Question #: 19
Subject Area: Statistical Principles

When calculating permutations the order (arrangement) of r objects selected from n objects:

   A) does not matter
   B) is a minor consideration
   C) does matter
   D) relates to the number of combinations

The correct answer is: C 

Order (the exact order in which they occur) matters when considering permutations. Order does not matter when considering combinations.

Back | Top


Question #: 20
Subject Area: Statistical Principles

The probability that a casting machine will produce an overweight part is .02. If we randomly sample 20 pieces out of 500 produced, using the Poisson distribution approximate the probability of getting exactly 3 bad pieces is:

   A) .00065
   B) .00715
   C) .10770
   D) .07150


The correct answer is: B 

The number 500 is irrelevant to this problem. Using n = 20, p = .02 and X = 3, the Poisson formula can easily be used to solve this problem. Solving this problem using the binomial distribution formula gives a probability value of .00647.

Back | Top


Question #: 21
Subject Area: Statistical Principles

The coefficient of variation of a population is equal to:

   A) the population variance divided by the
      population mean
   B) the average squared distance between the
      mean and each data point in the population
   C) 100 times the population standard deviation
      divided by the mean
   D) the average distance of the data point from
      the mean

The correct answer is: C 

The coefficient of variation is the standard deviation expressed as a percentage of the mean. This is a relative measure of dispersion which allows us to more readily compare two distributions.

Back | Top


Question #: 22
Subject Area: Statistical Principles

For a two tailed "t" distribution problem with a 90 percent confidence interval the t value is 1.729. The number of data points in the sample under question is:

   A) 19
   B) 20
   C) 18
   D) none of these

The correct answer is: B 

The degrees of freedom for this t value is 19. Since the d.o.f. is one less than the sample size, the number of data points in the sample would be 20.

Back | Top


Question #: 23
Subject Area: Statistical Principles

Given a finite population, when computing the standard error of the mean, a finite population multiplier is necessary:

   A) When the sample is small relative to the 
      population size, n < 5% of the population
      size N for example
   B) When the sample is taken without replacement
      and the sample size is large relative to the
      population size
   C) Whenever the population is finite and the 
      sample is small relative to the population
      size
   D) None of the above
 
 The correct answer is: B 

A finite population multiplier is used when the sample size is large relative to the finite population, i.e., n > 5% or when sampling without replacement. It is not used for sampling with replacement even if the population is finite.

Back | Top


Question #: 24
Subject Area: Statistical Principles

The frequency distribution that probably best describes the distribution of time to failure for a complex system of non redundant components subject to random failures is:

   A) the normal distribution
   B) the binomial distribution
   C) the Poisson distribution
   D) the exponential distribution

The correct answer is: D 

This is an example of a continuous distribution, therefore Answers B) and C) are not appropriate since they are discrete distributions. It is generally recognized that the failure distribution for the type of system described in this question is the exponential distribution.

Back | Top


Question #: 25
Subject Area: Statistical Principles

A chrome plating process is subject to 2 types of blemishes. For the sake of simplicity we will call them blemish type A and blemish type B. These defects can occur either alone or together. The historical rate of occurrence of blemish type A is .0769 and blemish type B is .2500. They are known to occur together at the rate of .0192. What is the probability, when sampling a batch of parts produced from this method, of getting either blemish A or blemish B?

   A)  .3268
   B)  .1731
   C)  .3077
   D)  none of these answers are correct


The correct answer is: C 

This an example of events that are not mutually exclusive. The formula to use for this situation is:
P(A or B) = P(A) + P(B) - (AB).
Thus, P(A or B) = .0769 + .2500 - .0192 = .3077

Back | Top


Question #: 26
Subject Area: Statistical Principles

The mean ultimate tensile strength for a certain type of aluminum casting is known to be 18,000 psi with a standard deviation of 950 psi. A new lot of castings is checked by taking a sample of 50 test bars with a resulting mean tensile strength of 16,750 psi. It is desired to determine if the mean tensile strength of these castings is less than 18,000 psi. The correct type of hypothesis test to use for this situation would be:

   A) two tailed test
   B) right tailed test
   C) left tailed test
   D) none of these

The correct answer is: C

The null hypothesis would be that the tensile strength does equal 18,000 psi and the alternative hypothesis would be that the tensile strength is less than 18,000 psi. Thus, we would be looking for a sample mean significantly below the desired population mean. We would check to make sure the sample mean is above the acceptance limit for the chosen level of significance.

Back | Top


Question #: 27
Subject Area: Quality Practices & App.

*Lots of 75 parts each are inspected to an AQL of 0.25% using normal inspection, single sampling. The sample size for MIL-STD-105D, Level II is:

   A) 13
   B) 32
   C) 50
   D) 75


The correct answer is: C 

The use of the tables is explained in the standard. It may be useful to obtain a copy of the standard to bring to the exam far enough in advance to familiarize yourself with its use. In this case the sample size code letter is E. Make sure you use the table for single sampling, normal inspection. You would accept on 0 defecetives and reject on 1.

Back | Top


Question #: 28
Subject Area: Quality Practices & App.

*The laboratory has notified the Quality Engineer of an incoming product which has changed from acceptable to marginal over a period of six months.  Which of the following actions should be taken?

   I. Notify the laboratory to check their
      analysis and send a sample to an outside
      laboratory to verify the results
  II. Notify the supplier of your observations 
      and concern about the acceptability of his
      product
 III. Notify receiving to reject the product 
      based on the product's trend toward
      unacceptability

A)  I. and II.
B)  I. and III.
C)  II. and III.
D)  I., II., and III.
                    
The correct answer is: A 

It is not correct to reject, based on a trend, as a first action. Both I. and II. would help to find out what is true about the state of the product and are therefore appropriate responses.

Back | Top


Question #: 29
Subject Area: Quality Practices & App.

*A certain part is produced in lot quantities of 1,000. Prior history shows that 90% of the production lots are 1% defective or better, but the remaining 10% range between 5% and 10% defective. A defective part costs $5 to repair at this point, but the same defect will average $80 if allowed to be installed in the next higher assembly. Inspection at the part level costs $1.50 per part, and rejected lots will be sorted at your expense. What inspection plan would you specify for this part?

   A) 100% inspection
   B) No inspection
   C) n = 32, A = 1, R = 2 (single-sampling)
   D) n = 50, A = 0, R = 1 (single-sampling)
   E) n = 5,  A = 1, R = 2 (single-sampling)

The correct answer is: C 

The general approach is to minimize the cost per lot. 100% inspection + repair costs is over $1500. No inspection would involve spending $80 per unit defective in repair costs. Assume .01 x 900 + .075 x 100 = 16.5 repairable units per lot for a cost of $1320. The next step is to calculate the costs of each inspection plan. In this case Answer C) results in the lowest cost. The calculations for these costs are rather involved and includes determining probabilities using the binomial distribution. See "Juran's Quality Control Handbook" published by McGraw Hill for a thorough explanation of this question.

Back | Top


Question #: 30
Subject Area: Systems and Reliabilty

The lifetime of a special type of electronic device is a random variable with a mean life of 200 hours and is subject to an exponential distribution. What is the probability the device will last at least 100 hours?

   A) .607
   B) .393
   C) .334
   D) none of these is correct

The correct answer is: A

Lasting at least 100 hours is interpreted as lasting 100 hours or more.  Either using the exponential distribution formula or a table, the area under the curve to the right of the value 100 hours is .607.  The formula for the exponential distribution is e^(-x/µ).  Substituting 100 for x and 200 for æ gives e^(-100/200) and thus e^(-1/2) or .607.

Back | Top


Question #: 31
Subject Area: Systems and Reliabilty

Design reviews for modern complex products are made with the following concepts in mind, except (choose the one that doesn't apply):

   A) they should be mandatory
   B) the design review can be informal but must include
      complete documentation of the proceedings
   C) independent, competent and experienced specialists
      should be present
   D) design reviews should cover quality matters as
      well as reliability, maintainability, safety,
      appearance, packaging, weight, etc.

The correct answer is: B 

The design review must be formal and scheduled like any other important meeting in the company. The other answers given above are all excellent guidelines for setting a design review policy.

Back | Top


Question #: 32
Subject Area: Systems and Reliabilty

A system with parallel redundancy and two redundant elements has a reliability factor of .975 for each element. The overall reliability of the system is:

   A)  .9506
   B)  .9994
   C)  .9750
   D)  .9999


The correct answer is: B 

The overall system reliability for parallel redundancy where each element has an identical reliability factor is calculated by the following formula:
   P[s] = 1-(1-P[1])^n
where n = the number of identical redundant elements.

Back | Top


End of CQEprep Sample Questions