Statistical Quality Control

Activity 1
Submitted by: Joan Grace Q. Duero
DTE 2B
Statistical Quality Control

 the use of statistical methods in the monitoring and maintaining of the quality of products and services
(Britannica, 2022)
 use of statistical tools and techniques to monitor and maintain product quality in industries such as food,
pharmaceuticals and many manufacturing environments. (Toledo, Mettler ND)
Aims and objective of SQC

 According to Datalyzer International, the aim of Statistical Process Control (SPC) is to establish a controlled
manufacturing process by the use of statistical techniques to reduce process variation.
 better quality;
 lower costs (waste, scrap, rework, claims, etc.);
 more insight into the capability of the process.

 The main objective of statistical quality control (SQC) is to achieve quality in production and service
organizations, through the use of adequate statistical techniques. 
3 categories of Statistical Quality Control

  1. Descriptive statistics: In the quality check and measure the material, the quality characteristics and the
relationships are described hence to find these it is important to know the mean, range, standard deviation
and the measurement of the distribution of data sample hence this is known as the descriptive statistics.
 2. Statistical process control - The functioning of a particular process is verified in this category whether it is
proper or not. In the process a sample is chosen and inspection on the same is done and then it is decided if
the manifested characteristics are in the pre-determined range or not and it determines if it functioning
properly or not.
 3. Acceptance sampling - This process ascertains if the entire lot is acceptable or not which is based on the
results of random inspection of the lot for the faulty products. 
Common cause variation vs. assignable cause
variation

 Common cause variation is the stuff for which you can assign a probability value. For instance, there are "predictable" failures and variance factors
associated with components and subsystems which allow one to generate fault trees for entire systems or to set error, or precision and accuracy,
limits on operation. The variation is dependent, contingent on factors inherent to the system. Suppose the cooling fan in a laptop computer fails,
causing the computer's microprocessor to overheat and "burn out"; there's a catastrophic irreversible failure of the core. That initial fan failure, if it
was caused by a mechanical failure of the rotor's bushing/bearing, a seizure and freeze-up of the rotor, may not have been predictable in the
particular instance, but over the population of all such fans, there is some frequency of failure associated with bushing/bearing failures, so a
probability of that failure occurring can be folded into a view of potential common cause failures for items using that fan as a system component.
 Special cause variation is unpredictable or off-normal. It's independent, such as a failure due to external factors, not something inherent or integral to
the system under study or operation. Suppose the owner of a laptop computer is walking along a busy urban street, right at the curb, is jostled by
some passer-by, and his or her computer falls into the street and is run over by a bus, causing irreparable damage. In the general sense, that's an
unpredictable, unforeseeable circumstance.
 Differentiating between special and common cause is important because common cause failures can be addressed reasonably and economically. For
instance, in the case of fans burning out due to bushing/bearing failure, if the failure has a serious impact, say on warranty returns, the fan design can
be improved or perhaps a better fan with the same mechanical form factor can be substituted. Special causes cannot be as easily addressed, at least
not in the ordinary processes from product conception and design through end point sales, and they're not contingent on anything in those processes.
Variation and control
 An assignable cause is a source of variation that is intermittent, not predictable. It is sometimes called
"special cause" variation. On a control chart, an assignable cause is signaled by points beyond the control
limits or nonrandom patterns within the control limits.
 Common-cause variation is the natural or expected variation in a process. Special-cause variation is
unexpected variation that results from unusual occurrences. It is important to identify and try to eliminate
special-cause variation.
 What causes the variations which you see in the control chart of a stable process?
 Control charts can be used to identify sources of variation, both common and special cause. Common
cause variation is the variation inherent in the process. Common cause variation is also known as the noise
of the process. A process with only common cause variation is highly predictable.
Control Chart

 The control chart is a graph used to study how a process changes over time. Data are plotted in time order. A
control chart always has a central line for the average, an upper line for the upper control limit, and a lower
line for the lower control limit. These lines are determined from historical data. By comparing current data to
these lines, you can draw conclusions about whether the process variation is consistent (in control) or is
unpredictable (out of control, affected by special causes of variation). This versatile 
data collection and analysis tool can be used by a variety of industries and is considered one of the 
seven basic quality tools.
 Control charts for variable data are used in pairs. The top chart monitors the average, or the centering of the
distribution of data from the process. The bottom chart monitors the range, or the width of the distribution. If
your data were shots in target practice, the average is where the shots are clustering, and the range is how
tightly they are clustered. Control charts for attribute data are used singly.
 X-Bar & R Charts – These variable charts utilize the X-Bar or the Mean to determine subgroups. The R or
Range plots the subgroups based on upper and lower control limits. X-Bar & R Charts are the most widely
utilized charts in project management, however, are only successful if 5 or less subgroups are analyzed.
 Both X-bar and R-chart provide you with visual snapshots of data that are assumed to be normally
distributed. The X-bar helps to monitor the average or the mean of the process and how this changed over
time. The R-chart shows the sample range, which represents the difference between the highest and lowest
value in each sample. Both X-bar and R-chart display control limits. Manufacturers must pay attention and
study any points outside the control limits as these indicate out-of-control processes and can help locate the
origins of the process variables. 
 Manufacturers typically use the X-bar and R-chart pair to visualize continuous data collected at regular
intervals in sample subgroups. The size of the subgroups is also very important, it needs to be between 2 and
10. If your sample size is 1 or more than 10, you need to select different control charts.  
 Manufacturers typically use the X-bar and R-chart pair to visualize continuous data. The X-bar helps to
monitor the average or the mean of the process and how this changed over time. The R-chart shows the
sample range, which represents the difference between the highest and lowest value in each sample. While
they are different, the X-bar and R-chart are used in conjunction with one another.
P-chart and C-chart

 p Control Charts – This attribute-type chart is effective when elements are not equal. A p Control Chart
might be used to determine how many accidents occur each day at a chosen intersection.
 c Control Charts – Another attribute-type control chart, the c Control Chart explores elements that are
nonconforming. A c Control Chart might be used to explore mass-production of one similar product where
the elements per unit do not conform to the norm.
 A p-chart is an attributes control chart used with data collected in subgroups of varying sizes. Because the
subgroup size can vary, it shows a proportion on nonconforming items rather than the actual count. P-charts
show how the process changes over time. The process attribute (or characteristic) is always described in a
yes/no, pass/fail, go/no go form. For example, use a p-chart to plot the proportion of incomplete insurance
claim forms received weekly. The subgroup would vary, depending on the total number of claims each week.
P-charts are used to determine if the process is stable and predictable, as well as to monitor the effects of
process improvement theories. 
Process capability

 Process capability is defined as a statistical measure of the inherent process variability of a given
characteristic. You can use a process-capability study to assess the ability of a process to meet specifications.
 During a quality improvement initiative, such as Six Sigma, a capability estimate is typically obtained at the
start and end of the study to reflect the level of improvement that occurred.
 Several capability estimates are in widespread use, including:
 Potential capability (Cp) and actual capability during production (Cpk) are process capability estimates.
Cp and Cpk show how capable a process is of meeting its specification limits, used with continuous data.
They are valuable tools for evaluating initial and ongoing capability of parts and processes.
 "Sigma" is a capability estimate typically used with attribute data (i.e., with defect rates).
 Acceptance sampling uses statistical sampling to determine whether to accept or reject a production lot of
material. It has been a common quality control technique used in industry. It is usually done as products
leaves the factory, or in some cases even within the factory. Most often a producer supplies a consumer a
number of items and a decision to accept or reject the items is made by determining the number of defective
items in a sample from the lot. The lot is accepted if the number of defects falls below where the acceptance
number or otherwise the lot is rejected.[1]
 In general, acceptance sampling is employed when one or several of the following hold: [2]
 testing is destructive;
 the cost of 100% inspection is very high; and
 100% inspection takes too long.
 In statistics, a variables sampling plan is an acceptance sampling technique. Plans for variables are
intended for quality characteristics that are measured on a continuous scale. This plan requires the
knowledge of the statistical model (e.g. normal distribution).
 The purpose of a plan for variables is to assess whether the process is operating far enough from the
specification limit. Plans for variables may produce a similar OC curve to attribute plans with significantly
less sample size.
References

 Britannica, T. Editors of Encyclopaedia (2022, February 14). statistical quality control. Encyclopedia
Britannica. https://www.britannica.com/topic/statistical-quality-control
 Gomes M.I. (2011) Statistical Quality Control. In: Lovric M. (eds) International Encyclopedia of Statistical
Science. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04898-2_551