Statistics

Question 1

What is an experiment?

Answer 1

The systematic procedure carried out
under controlled conditions in order to discover an
unknown effect, to test or establish a hypothesis, or to
illustrate a known effect.

Question 2

Industrial experiments involved what steps?

Answer 2

1) Hypothesis
2) Experiment
3) Analysis
4) Interpretation
5) Conclusion

Question 3

What is an error in an experiment?

Answer 3

Error refers to all unexplained variation
that is either within an experiment run or between experiment runs and associated with
level settings changing. Properly designed experiments can identify and quantify the
sources of error.

Question 4

Why is it good to have a control in an experiment?

Answer 4

Control (placebo) is a critical aspect of experimental design: good experiments are comparative!

Question 5

What is replication?

Answer 5

Replication is the basic issue behind every method we will use in order to get a handle on how precise our estimates are at the end.
With replicated measurements we can characterise the variability within measurements and compare to that between measurements.

Question 6

Why is there a need for robust sampling?

Answer 6

Because if you collect the wrong number of samples, or collect them in the wrong way, then you will not be able to undertake the analysis that you plan to, meaning your interpretation of your data is compromised from the start!

Question 7

Why should you randomise experiments?

Answer 7

Assignment of those treatments by some random process: you need to have a deliberate process to eliminate potential biases from the conclusions, and random assignment is a critical step.

Question 8

What is blocking?

Answer 8

Blocking (or stratification) is a technique to include other factors in our experiment which contribute to undesirable variation.

Question 9

Given a bivariate dataset, there is no linear relationship between X and Y when…

Answer 9

the correlation coefficient, r, approaches 0.

Question 10

Population variability refers to

Answer 10

How spread out a set of data is. Variability is measured in terms of standard errors/ deviations.

Question 11

In a designed experiment, what is the definition of “responses”?

Answer 11

The measured outcomes of an experiment

Question 12

In an experiment, what are the “uncontrollable factors”?

Answer 12

Factors that affect the results from an experiment and are difficult to be controlled.

Question 13

Why should good experiments be always comparative?

Answer 13

Because if you do not monitor the “no treatment” case by using it for comparison, you have no basis for quantifying the effect of the variables you are investigating.

Question 14

Why should you always replicate your experiments?

Answer 14

Because with replicated measurements we can characterise the variability within measurements and compare to that between measurements.

Question 15

In the design of experiments ambit, what is “randomization”?

Answer 15

Randomization is a deliberate process designed to eliminate potential biases from the conclusions.

Question 16

The basic principles of the design of experiments include

Answer 16

Replication, randomization, and stratification (or blocking).

Question 17

In metrology, what is the definition of “precision”?

Answer 17

Precision is the degree of repetitiveness of the measuring process.

Question 18

In metrology, what is the definition of static calibration?

Answer 18

If the values of the variable involved remain constant (i.e., it is not time dependent) while calibrating a given instrument, this type of calibration is known as static calibration.

Question 19

What is the definition of “random errors”?

Answer 19

Random errors provide a measure of random deviations when measurements of a physical quantity are carried out repeatedly.

Question 20

Why is something a binomial random problem?

Answer 20

• there is a fixed number of trials, with n=x
• each trial can have only two outcomes (either it contains soil residuals of dioxin or it does not)
• the probability of a having soil residuals of dioxin (i.e. the probability of success, p is the same for each trial
• the outcomes of each trial are independent of each other.

Question 21

When does confounding occur?

Answer 21

Confounding occurs when the experimental controls do not allow the experimenter to reasonably eliminate plausible alternative explanations for an observed relationship between independent and dependent variables.
Confounding factors are variables that influence both the
inputs and the outputs causing a spurious association.

Question 22

Factorial experiments

Answer 22

In a factorial experiment several independent factors are controlled and their effects are investigated at each of two or more levels.
The experimental design consists of taking an observation at each one of all possible combinations that can be formed for the different levels of the factors.
When two or more variables being studied have an interaction effect, the factorial design may be appropriate to use.
With this type of design, the results are used to estimate and compare the effects of several factors and estimate possible interaction effects.

Question 23

Factorial advantages and disadvantages:

Answer 23

• Factorial design facilitates the evaluation of interactive effects.
• All of the results are used to evaluate the effects of the factors.
• The results are applicable over a wide range of experimental conditions.
• The required sample size may be large, but this problem can be resolved by running a subset of the full factorial (this is referred to as a fractional factorial design)
• Explanation/interpretation of some interactions may be complex.

Question 24

What is blinding?

Answer 24

• Measurements made by people can be influenced by unconscious biases
• Ideally, measurements should be made without knowledge of the treatment applied

Question 25

What are internal controls?

Answer 25

It can be useful to use the subjects themselves as their own controls (e.g., consider the response after vs. before treatment)

Question 26

What is representativeness?

Answer 26

Are the subjects you are studying really representative of the population you want to study?
Ideally, your study material is a random sample from the population of interest

Question 27

What are the characteristics of a good experiment?

Answer 27

• Unbiased
• High precision
• Simple
• Able to estimate uncertainty
• Wide range of applicability

Question 28

What is engineering metrology?

Answer 28

Metrology concerns itself with the study of measurements

Measurement is an act of assigning an accurate and precise value to a physical variable

Question 29

Industrial inspection deals will

Answer 29

⊗ Ascertain that the part, material, or component conforms to the established or desired standard
⊗ Accomplish interchangeability of manufacture
⊗ Sustain customer goodwill by ensuring that no defective product reaches the customers

Question 30

What is the definition of accuracy?

Answer 30

Accuracy is the degree of agreement of the measured quantity with its true magnitude

Question 31

The difference between precision and accuracy:

Answer 31

Accuracy gives information regarding how far the measured value is with respect to the true value, whereas precision indicates quality of measurement in terms of
reproducibility, without giving any assurance that the measurement is correct

The difference between the true value and the mean value of the set of readings on the same component is termed as Error

Question 32

Output value

Answer 32

The output or terminating stage of a measurement system presents the value of the output that is analogous to the input value
the characteristics of the input signals should be
transformed with true fidelity

Question 33

Primary detector transducer

Answer 33

The main function of the primary detector–transducer stage is to sense the input signal and transform it into its analogous signal, which can be easily measured

Question 34

Fidelity and dynamic error

Answer 34

Fidelity. It is defined as the degree to which a measurement system indicates the changes in the measured quantity without any dynamic error
⊗ Dynamic error. It is also known as a measurement error. It can be defined as the difference between the true value of a physical quantity under consideration that changes with time and the value indicated by the measuring system if no static error is assumed

Question 35

What is drift?

Answer 35

-Drift can be defined as the variation caused in the output of an instrument, which is NOT caused by any change in the input

Question 36

Resolution of measuring instruments

Answer 36

Resolution is the smallest change in a physical property that an instrument can sense

Question 37

Linearity

Answer 37

⊗ Linearity is defined as the maximum deviation of the output of the measuring system from a specified straight line applied to a plot of data points on a curve of measured (output) values versus the measurand (input) values

Question 38

Hysteresis

Answer 38

When the value of the measured quantity remains the same irrespective of whether the measurements have been obtained in an ascending or a descending order a system is said to be free from hysteresis

Question 39

Random errors

Answer 39

Random errors provide a measure of random deviations when measurements of a physical quantity are carried out repeatedly

Question 40

Systematic error

Answer 40

A systematic error is a type of error that deviates by a fixed amount from the true value of measurement