IE 10 1

ENGINEERING DATA ANALYSIS

M od u l e 2 – Pa r t 3
Statistical Intervals
Contents
I. Confidence Intervals
II. Prediction Intervals
III. Tolerance Intervals
 Confidence Levels
• Confidence Level is the probability that the value of a parameter falls within
a specified range of values.
• It gives an estimated range of values which is likely to include an
unknown population parameter, the estimated range being calculated
from a given set of sample data.
 Formula: Confidence Intervals for the Mean
(𝝈 𝒊𝒔 𝑲𝒏𝒐𝒘𝒏 𝒐𝒓 𝒏 ≥ 𝟑𝟎)
• The confidence level is the percentage equivalent to the decimal value of
1 − 𝛼.

𝜎 𝜎
𝑋! − 𝑧!/# < 𝜇 < 𝑋! + 𝑧!/#
𝑛 𝑛
Example: The normal curve on the left represent a

confidence interval of 95% with 𝛼 equals to 0.05. Thus,

the area of left and right tail is equals to 0.05/2=0.025

• Example: 𝛼 = 0.05, 𝐶𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝐿𝑒𝑣𝑒𝑙 = 95%

 Maximum Error of Estimate
• The maximum error of estimate is the maximum difference between the point
estimate of a parameter and the actual value of the parameter.

𝜎
𝐸 = 𝑧!/#
𝑛
 Commonly Used Confidence Intervals
• The maximum error of estimate is the maximum difference between the point
estimate of a parameter and the actual value of the parameter.

• Commonly used are 90%, 95% (by most

researchers) and 99%.
• For our course, take note of 75%, 80%,
85%, 90%, 95% and 99%.
 Example: (𝝈 𝒊𝒔 𝑲𝒏𝒐𝒘𝒏 𝒐𝒓 𝒏 ≥ 𝟑𝟎)
• Example 1: The president of a large university wishes to estimate the average
age of the students presently enrolled. From past studies, the standard
deviation is known to be 2 years. A sample of 50 students is selected, and the
mean is found to be 23.2 years. Find the 95% confidence interval of the
population mean.
𝑥̅ = 23.3 𝑦𝑒𝑎𝑟𝑠 𝑛 = 50 𝑠𝑡𝑢𝑑𝑒𝑛𝑡𝑠
σ = 2 𝑦𝑒𝑎𝑟𝑠 𝐶𝐿 = 95% → 𝑧𝛼 = 1.96
2

2 2
23.2 − 1.96 < μ < 23.2 + 1.96
50 50

𝟐𝟐. 𝟔𝟓 < μ < 𝟐𝟑. 𝟕𝟓 𝒚𝒆𝒂𝒓𝒔

 Characteristics of a t-distribution
• The t-distribution is similar to the standard normal distribution in the following
ways:
• It is bell-shaped.
• It is symmetrical about the mean.
• The mean, median, and mode are equal to 0 and are located at the
center of the distribution.
• The curve never touches the x axis.
 Characteristics of a t-distribution
• The t distribution differs from the standard normal distribution in the following
ways:
• The variance is greater than 1.
• The t distribution is actually a family of curves based on the concept of
degrees of freedom, which is related to the sample size.
• As the sample size increases, the t distribution approaches the standard
normal distribution.
Formula: Confidence Intervals for the Mean
(𝝈 𝒊𝒔 𝒖𝒏𝒌𝒏𝒐𝒘𝒏 𝒐𝒓 𝒏 < 𝟑𝟎)

𝑠 𝑠
𝑋! − 𝑡!/# < 𝜇 < 𝑋! + 𝑡!/#
𝑛 𝑛

𝑑𝑓 𝑑𝑒𝑔𝑟𝑒𝑒𝑠 𝑜𝑓 𝑓𝑟𝑒𝑒𝑑𝑜𝑚 = 𝑛 − 1
 Example: (𝝈 𝒊𝒔 𝒖𝒏𝒌𝒏𝒐𝒘𝒏 𝒐𝒓 𝒏 < 𝟑𝟎)
• Example 1: Ten randomly selected automobiles were stopped, and the tread
depth of the right front tire was measured. The mean was 0.32 inch, and the
standard deviation was 0.08 inch. Find the 95% confidence interval of the
mean depth. Assume that the variable is approximately normally distributed.

𝑥̅ = 0.32 𝑖𝑛𝑐ℎ𝑒𝑠 𝑛 = 10 𝑎𝑢𝑡𝑜𝑚𝑜𝑏𝑖𝑙𝑒𝑠

𝑠 = 0.08 𝑖𝑛𝑐ℎ𝑒𝑠 𝐶𝐿 = 95% → 𝑡𝛼 = 2.262
2

0.08 0.08
0.32 − 2.262 < μ < 0.32 + 2.262
10 10

𝟎. 𝟐𝟔𝟐𝟖 < μ < 𝟎. 𝟑𝟕𝟕𝟐 𝒊𝒏𝒄𝒉𝒆𝒔

 Example: (𝝈 𝒊𝒔 𝒖𝒏𝒌𝒏𝒐𝒘𝒏 𝒐𝒓 𝒏 < 𝟑𝟎)
• Example 2: The data represent a sample of the number of home fires started
by candles for the past several years. (Data are from the National Fire
Protection Association.) Find the 99% confidence interval for the mean
number of home fires started by candles each year.
5460, 5900, 6090, 6310, 7160, 8440, 9930

𝑥̅ = 7041.43 𝑐𝑎𝑛𝑑𝑙𝑒𝑠 𝑛 = 7 ℎ𝑜𝑚𝑒 𝑓𝑖𝑟𝑒𝑠

𝑠 = 1610.27 𝑐𝑎𝑛𝑑𝑙𝑒𝑠 𝐶𝐿 = 99% → 𝑡𝛼 = 3.707

2

1610.27 1610.27
7041.43 − 3.707 < μ < 7041.43 + 3.707
7 7

𝟒𝟕𝟖𝟓 < μ < 𝟗𝟐𝟗𝟕 𝒉𝒐𝒎𝒆 𝒇𝒊𝒓𝒆𝒔

 Confidence Intervals and Sample Size for
Proportions
• Symbols used in Proportion Notation p = population proportion
• 𝑝̂ 𝑟𝑒𝑎𝑑 “𝑝 − ℎ𝑎𝑡” = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑝𝑟𝑜𝑝𝑜𝑟𝑡𝑖𝑜𝑛

𝑋
𝑝̂ =
𝑛
𝑞_ = 1 − 𝑝̂

• Where X = the number of sample units that possess the characteristic of

interest (also known as no. of successes) and n = sample size.
 Formula for a Specific Confidence Interval for a
Proportion
• Rounding Rule for Confidence Interval for a Proportion: Round off to three
decimal places.

𝑝7𝑞7 𝑝7𝑞7
𝑝7 − 𝑧! < 𝑝 < 𝑝7 + 𝑧!/#
# 𝑛 𝑛
 Example: Confidence Intervals and Sample Size for
Proportions
• Example 1: A sample of 500 nursing applications included 60 from men. Find
the 90% confidence interval of the true proportion of men who applied to the
nursing program.

𝑛 = 500 𝑎𝑝𝑝𝑙𝑖𝑐𝑎𝑡𝑖𝑜𝑛𝑠 𝐶𝐿 = 90% → 𝑧𝛼 = 1.645

2

𝑥 = 60 𝑚𝑒𝑛 60 60
𝑝̂ = 𝑞H = 1 −
500 500

60 1 − 60 60 (1 − 60 )
60 500 500 60 500 500
− 1.645 <p< + 1.645
500 500 500 500

𝟎. 𝟎𝟗𝟔 < p < 𝟎. 𝟏𝟒𝟑𝟗 𝟗. 𝟔% < p < 𝟏𝟒. 𝟑𝟗% 𝒐𝒇 𝒎𝒆𝒏

 Example: Confidence Intervals and Sample Size for
Proportions
• Example 2: A survey of 200, 000 boat owners found that 12% of the pleasure
boats were named Serenity. Find the 95% confidence interval of the true
proportion of the boats named Serenity

𝑛 = 200, 000 𝑏𝑜𝑎𝑡 𝐶𝐿 = 95% → 𝑧𝛼 = 1.96

2

𝑝̂ = 0.12 𝑞H = 0.88

0.12 1 − 0.12 0.12 1 − 0.12

0.12 − 1.96 < p < 0.12 + 1.96
200, 000 200,
000

𝟎. 𝟏𝟏𝟖𝟔 < p < 𝟎. 𝟏𝟐𝟏𝟒 𝟏𝟏. 𝟖𝟔% < p < 𝟏𝟐. 𝟏𝟒% 𝒐𝒇 𝒕𝒉𝒆 𝒃𝒐𝒂𝒕𝒔
 Confidence Intervals for Variances and Standard
Deviations
• To calculate these confidence intervals, the chi-square (𝑥 ! ) distribution is
used.
• The chi-square distribution is similar to the t distribution in that its distribution is
a family of curves based on the number of degrees of freedom.
• A chi-square variable cannot be negative and the distributions are positively
skewed.
Confidence Intervals for Variances and Standard
Deviations

For a 95% confidence interval, we have α=0.05 which

gives 2.5% of the area at each end of the chi-square
distribution.
Example: Find the values of 𝑥 $ %&'( and 𝑥 $ )*+,(
for the confidence interval of 95% and n=6 2
𝑥𝑙𝑒𝑓𝑡 = 0.831
Degrees of freedom (d.f.) = 6 – 1 = 5 2
𝑥𝑟𝑖𝑔ℎ𝑡 = 12.833
Formula: Confidence Interval for a Variance

(𝒏 − 𝟏)𝒔𝟐 𝟐 <
(𝒏 − 𝟏)𝒔 𝟐
< 𝝈
𝑿𝟐 𝒓𝒊𝒈𝒉𝒕 𝑿𝟐 𝒍𝒆𝒇𝒕

𝑑. 𝑓. = 𝑛 − 1
Formula: Confidence Interval for a Standard
Deviation

(𝒏 − 𝟏)𝒔𝟐 (𝒏 − 𝟏)𝒔𝟐
< 𝝈 <
𝑿𝟐 𝒓𝒊𝒈𝒉𝒕 𝑿𝟐 𝒍𝒆𝒇𝒕

𝑑. 𝑓. = 𝑛 − 1
 Example: Variance

• Example 1: Find the 95% confidence interval for the variance and standard
deviation of the nicotine content of cigarettes manufactured if a sample of
20 cigarettes has a standard deviation of 1.6 milligrams.

𝑠 = 1.6 𝑚𝑔 𝑛 = 20 𝑐𝑖𝑔𝑎𝑟𝑒𝑡𝑡𝑒𝑠 (𝑑𝑓 = 19) 𝛼 = 0.05

2
𝑥𝑙𝑒𝑓𝑡 2
𝑥𝑟𝑖𝑔ℎ𝑡
= 8.907 = 32.852

(20 − 1)(1.6)2 (20 − 1)(1.6)2

< 𝜎2 <
32.852 8.907

𝟏. 𝟒𝟖 < 𝝈𝟐 < 𝟓. 𝟒𝟔 𝒎𝒈
 Example: Standard Deviation

• Example 1: Find the 95% confidence interval for the variance and standard
deviation of the nicotine content of cigarettes manufactured if a sample of
20 cigarettes has a standard deviation of 1.6 milligrams.

𝑠 = 1.6 𝑚𝑔 𝑛 = 20 𝑐𝑖𝑔𝑎𝑟𝑒𝑡𝑡𝑒𝑠 (𝑑𝑓 = 19) 𝛼 = 0.05

2
𝑥𝑙𝑒𝑓𝑡 2
𝑥𝑟𝑖𝑔ℎ𝑡
= 8.907 = 32.852

(20 − 1)(1.6)2 (20 − 1)(1.6)2

<𝜎<
32.852 8.907

𝟏. 𝟐𝟐 < 𝝈 < 𝟐. 𝟑𝟒 𝒎𝒈
 Prediction Interval of a Future Observation,
𝝈𝟐 𝒊𝒔 𝒌𝒏𝒐𝒘𝒏
In some problem situations, we may be interested in predicting a future
observation of a variable (e.g. possible value of the next observation). This is a
different problem than estimating the mean of that variable, so a confidence
interval is not appropriate.

𝟏 𝟏
0 − 𝒛𝜶/𝟐 𝝈
𝒙 𝟏+ 0 + 𝒛𝜶/𝟐 𝝈
< 𝒙𝟎 < 𝒙 𝟏+
𝒏 𝒏
 Example: Prediction Interval of a Future
Observation, 𝝈𝟐 𝒊𝒔 𝒌𝒏𝒐𝒘𝒏
• Example 1: Due to the decrease in interest rates, the First Citizens Bank
received a lot of mortgage applications. A recent sample of 50 mortgage
loans resulted in an average loan amount of $257,300. Assume a population
standard deviation of $25,000. For the next customer who fills out a mortgage
application, find a 95% prediction interval for the loan amount.

𝑥̅ = $257, 300 𝑛 = 50 𝑚𝑜𝑟𝑡𝑔𝑎𝑔𝑒 𝑙𝑜𝑎𝑛𝑠

σ = $25, 000 𝐶𝐿 = 95% → 𝑧𝛼 = 1.96

2

1 1
257, 300 − 1.96 25, 000 1 + 50 < 𝑥𝑜 < 257, 300 + 1.96 25, 000 1 + 50

$𝟐𝟎𝟕, 𝟖𝟏𝟐. 𝟒𝟑 < 𝒙𝒐 < $𝟑𝟎𝟔, 𝟕𝟖𝟕. 𝟓𝟕

 Prediction Interval of a Future Observation,
𝝈𝟐 𝒊𝒔 𝒖𝒏𝒌𝒏𝒐𝒘𝒏
In some problem situations, we may be interested in predicting a future
observation of a variable. This is a different problem than estimating the mean
of that variable, so a confidence interval is not appropriate.

𝟏 𝟏
0 − 𝒕𝜶/𝟐 𝒔
𝒙 𝟏+ 0 + 𝒕𝜶/𝟐 𝒔
< 𝒙𝟎 < 𝒙 𝟏+
𝒏 𝒏

𝑑𝑓 𝑑𝑒𝑔𝑟𝑒𝑒𝑠 𝑜𝑓 𝑓𝑟𝑒𝑒𝑑𝑜𝑚 = 𝑛 − 1
 Example: Prediction Interval of a Future
Observation, 𝝈𝟐 𝒊𝒔 𝒖𝒏𝒌𝒏𝒐𝒘𝒏
• Example 1: A meat inspector has randomly selected 30 packs of 95% lean
beef. The sample resulted in a mean of 96.2% with a sample standard
deviation of 0.8%. Find a 99% prediction interval for the leanness of a new
pack. Assume normality.

𝑥̅ = 96.2% 𝑛 = 30 𝑝𝑎𝑐𝑘𝑠 𝑜𝑓 95% 𝑙𝑒𝑎𝑛 𝑏𝑒𝑒𝑓 (𝑑𝑓 = 29)

σ = 8% 𝐶𝐿 = 99% → 𝑡𝛼 = 2.756
2

1 1
0.962 − 2.756 0.008 1 + 30 < 𝑥𝑜 < 0.962 + 2.756 0.0008 1 + 30

𝟗𝟑. 𝟗𝟔% < 𝒙𝒐 < 𝟗𝟖. 𝟒𝟒%

 Tolerance Intervals

• For instance, if process specifications are important, the manager of the

process is concerned about long-range performance, not the next
observation.

! − 𝒌𝒔, 𝒙
𝒙 ! + 𝒌𝒔
• where k is a tolerance interval factor
 Example: Tolerance Intervals

• Consider previous example but n = 20 packs. With the information given, find
a tolerance interval that gives two-sided 95% bounds on 90% of the
distribution of packages of 95% lean beef. Assume the data came from an
approximately normal distribution.

𝑥̅ = 96.2% 𝑛 = 20 𝑝𝑎𝑐𝑘𝑠
𝑠 = 8% 𝑘 = 2.310

0.962 ± (2.310)(0.008)

(𝟗𝟒. 𝟑𝟓𝟐%, 𝟗𝟖. 𝟎𝟒𝟖%)

Factors for Tolerance Intervals
References
Montgomery, D. & Runger, C. (2011). Applied Statistics and
Probability for Engineers Fifth Edition. John Wiley and
Sons, Inc.