ASSIGNMENT ON STATISTICAL PROCESS CONTROL Prod

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 4

ASSIGNMENT ON STATISTICAL PROCESS CONTROL

A. To calculate 𝐶𝑝𝑘, we first need to calculate the process capability index (Cpk). Cpk measures how
well the process meets the specifications, taking into account both the variability of the process
and the distance between the target and the specification limits.

Cpk is calculated using the following formula:

Cpk = min[(USL - mean)/3σ, (mean - LSL)/3σ]

Where USL is the upper specification limit (3.15), LSL is the lower specification limit (2.85), mean
is the average amount of formula placed in the bottles (3.042), and σ is the standard deviation of the
amounts (0.034).

Cpk = min[(3.15 - 3.042)/3(0.034), (3.042 - 2.85)/3(0.034)]

Cpk = min[2.96, 2.82]

Cpk = 2.82

The value of 𝐶𝑝𝑘 is 2.82.

B. To determine the proportion of bottles that meet the specifications, we need to calculate the
proportion of bottles that fall within the specification limits. We can use the normal distribution
to estimate this proportion, since we have a large sample size (n = 200) and the central limit
theorem applies.

The standard error of the mean is calculated as:

SE = σ/√n = 0.034/√200 = 0.0024

We can use the z-score formula to calculate the proportion of bottles that fall within the
specification limits:

z = (USL - mean)/SE = (3.15 - 3.042)/0.0024 = 36.67

z = (mean - LSL)/SE = (3.042 - 2.85)/0.0024 = 79.17

The proportion of bottles that fall within the specification limits is approximately the area under
the standard normal curve between these two z-scores. We can use a table or a calculator to find this
area, or we can use a software like R or Python.

Using R, we can calculate this proportion as follows:

pnorm(79.17) - pnorm(36.67)

[1] 1.006882e-12
2. To construct a p-chart, we need to calculate the proportion of unsatisfied patients for each day and
then calculate the overall proportion of unsatisfied patients. We can then use the overall proportion and
the sample sizes to calculate the control limits.

The proportion of unsatisfied patients for each day is:

Day 1: p₁ = 24/100 = 0.24

Day 2: p₂ = 22/100 = 0.22

Day 3: p₃ = 8/100 = 0.08

Day 4: p₄ = 15/100 = 0.15

Day 5: p₅ = 10/100 = 0.1

Day 6: p₆ = 26/100 = 0.26

Day 7: p₇ = 17/100 = 0.17

The overall proportion of unsatisfied patients is:

p̂ = (24 + 22 + 8 + 15 + 10 + 26 + 17)/(100 + 100 + 100 + 100 + 100 + 100 + 100) = 0.163

The sample standard deviation of p is:

s p = sqrt[(p̂ (1-p̂ ))/n] = sqrt[(0.163(1-0.163))/100] = 0.0394

To calculate the control limits, we use the following formula:

UCL = p̂ + 3s_p

LCL = p̂ - 3s_p

UCL = 0.163 + 3(0.0394) = 0.2812

LCL = 0.163 - 3(0.0394) = 0.0448


A. The formula for calculating the standard deviation of the sample mean, 𝜎𝑋̅, is:

𝜎𝑋̅ = 𝜎 / sqrt(n)

where 𝜎 is the population standard deviation and n is the sample size. In this case, 𝜎 = 1.36 and n = 5, so:

𝜎𝑋̅ = 1.36 / sqrt(5) = 0.608

Therefore, 𝜎𝑋̅ is approximately equal to 0.608.

b. The control limits for the mean chart can be calculated using the following formulas:

Upper control limit (UCL) = 𝑋̅ + 𝑧(𝜎𝑋̅)

Lower control limit (LCL) = 𝑋̅ - 𝑧(𝜎𝑋̅)

where 𝑋̅ is the sample mean, 𝑧 is the number of standard deviations from the mean, and 𝜎𝑋̅ is
the standard deviation of the sample mean. In this case, 𝑧 = 3 and 𝜎𝑋̅ = 0.608 (from part a). We also
need to calculate the overall sample mean, which is:

𝑋̅ =
(1+2+3+4+5+6+7+8+9+10+9+9+9+10+10+10+11+10+8+12+10+11+10+11+9+8+10+8+12+9+11+10+10+1
1+12+8+10+12+8+12+10+9+10+10+9+9+8+9+12) / (10*5) = 9.96

Plugging in these values, we get:

UCL = 9.96 + 3(0.608) = 12.78

LCL = 9.96 - 3(0.608) = 7.14

Therefore, the control limits for the mean chart are 7.14 and 12.78.

C. Process that is considered to be in control measures an ingredient in ounces. Below are the last 10
samples (each of size 𝑛 = 5 ) taken. The population process standard deviation, 𝜎, is 1.36.

Samples

1 2 3 4 5 6 7 8 9 10

10 9 13 10 12 10 10 13 8 10

9 9 9 10 10 10 11 10 8 12

10 11 10 11 9 8 10 8 12 9

9 11 10 10 11 12 8 10 12 8

12 10 9 10 10 9 9 8 9 12

As we can see from the chart, one point (sample 3) falls above the upper control limit, and
another point (sample 5) falls below the lower control limit. This indicates that the process may not be in
control, as these points suggest that there are some sources of variation that are causing the process to
produce results outside of the expected range. To confirm whether the process is out of control, we
would need to investigate these out-of-control points further and determine the root cause of the
variation. It's possible that these points are due to common causes of variation that can be addressed by
making minor adjustments to the process, or they could be due to special causes of variation that
require more significant changes to the process. Without further investigation, it's difficult to say for
certain whether the process is in or out of control.

You might also like