Statistics Mean Mode
Statistics Mean Mode
Ideas in Chapter 6:
• Normal distribution
• Compute probabilities from the normal distribution
• How to use the normal distribution to solve business problems
• (Maybe) How to use the normal probability plot to determine whether a set of data is
approximately normally distributed
• Brief look at and discussion of:
• Computing probabilities from the uniform distribution
• Computing probabilities from the exponential distribution
• Important to remember:
• What is a continuous numeric variable?
1
• Normal Probability Density Function
2
1 æ (X -µ) ö
1 - ç
2è s ø
÷
• Formula for the normal probability density function is: f(X) = e
2πs
• Where:
• e = the mathematical constant approximated by 2.71828
• π = the mathematical constant approximated by 3.14159
• μ = the population mean
• σ = the population standard deviation
• X = any value of the continuous variable Standardized Normal
• Standardized Normal
• Any normal distribution (with any mean and standard deviation combination) can be transformed
into the standardized normal distribution (Z)
($%&) $%*
• 𝑧= ≈
( +
• The standardized normal distribution (Z) has a mean of 0 and a standard deviation of 1
StandardNormal Curve
• The standard normal curve is a normal curve with:
• MEAN (µ) = 0,
• VARIANCE (σ2) = 1 and
• STANDARD DEVIATION (σ) = 1
• Denoted by N(µ , σ2) = N(0, 1)
• When calculate z-score, you are “transforming” your normal curve
into a standard normal curve
µ = 16
σ=2
µ=0
σ=1
16
0
16
• The standard Normal Z distribution always has mean = μ = 0 and standard deviation = σ = 1
• Values above the mean have positive Z-values
• Values below the mean have negative Z-values
f(X)
P (a ≤ X ≤ b )
• Finding Normal Probabilities
• Probability is measured by AREA UNDER THE CURVE = P (a < X < b )
0.5 0.5
• Normal distribution is symmetric so…
μ X
!!!!!!The!column!gives!the!value!of!Z!
to!the!second!decimal!point!
Z 0.00 0.01 0.02 …
0.0
!!!!!!The!row!shows!
the!value!of!Z!to! 0.1
. The value within the
the!first!decimal! .
. table gives the
point!
2.0 .9772 probability from Z = - ∞
up to the desired Z
value
2.0
P(Z < 2.00) = 0.9772
Standardized"Normal"Probability"" P(X"<"18.6)"
Table"(Por@on)"
="P(Z"<"0.12)"
4
But$what$if$we$want$to$know$P(X$≥$18.6)?
• μ$=$18$and$σ$=$5$
X"
18.0"
18.6" 0.5478$ 1.0$%$0.5478$=$
0.4522$
1.000$
Z"
"0"
0.12"
Z"
"0" P(X$>$18.6)$=$P(Z$>$0.12)$=$1.0$%$P(Z$≤$0.12)$
0.12" $$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$=$1.0$%$0.5478$=$0.4522$
5
• Empirical Rule
• What can we say about the distribution of values around the mean? For any normal distribution:
• What if you are given a Normal Probability, and you need to find x?
EXAMPLE: Let X represent the time it takes (in seconds) to download an image file from the internet.
Suppose X is normal with mean 18.0 and standard deviation 5.0. Find X such that 20% of download
times are less than X.
6
Excel&Can&Be&Used&To&
Find&Normal&Probabili7es&
• Find&P(X&<&9)&where&X&is&
normal&with&a&mean&of&7&
and&standard&devia7on&of&2&
6.3$Evalua*ng$Normality
• Not$all$con)nuous$distribu)ons$are$normal$
!$important$to$evaluate$how$well$data$are$
approximated$by$a$normal$distribu)on$
• Normally$distributed$data$should$approximate$the$
theore)cal$normal$distribu)on:$
• Bell:shaped$(symmetrical)$where$the$mean$is$equal$to$the$
median$
• Empirical$rule$applies$
• Interquar)le$range$~$1.33$standard$devia)ons$
34$
Comparing*data*characteris1cs*to*theore1cal*proper1es
• Construct)charts)or)graphs)
• For)small1)or)moderate1sized)data)sets,)construct))
stem1and1leaf)or)boxplot)to)check)for)symmetry)
• For)large)data)sets,)does)the)histogram)or)polygon)appear)bell1
shaped?)
• Compute)descrip=ve)summary)measures)
• Do)the)mean,)median)and)mode)have)similar)values?)
• Is)the)interquar=le)range)approximately)1.33σ?)
• Is)the)range)approximately)6σ?)
• Observe)the)distribu=on)of)the)data)set)
• Do)approximately)2/3)of)the)observa=ons)lie)within)mean)±1)
standard)devia=on?)
• Do)approximately)80%)of)the)observa=ons)lie)within)mean)
±1.28)standard)devia=ons?)
• Do)approximately)95%)of)the)observa=ons)lie)within)mean)±2)
standard)devia=ons?)
35)
7
Comparing*data*characteris1cs*to*theore1cal*proper1es
• Evaluate(normal(probability(plot(
• Is(the(normal(probability(plot(approximately(linear((i.e.(a(
straight(line)(with(posi:ve(slope?(
So#what#is#this??????#
• Construc:ng(a(Normal(Probability(Plot(
• Arrange(data(into(ordered(array(
• Find(corresponding(standardized(normal(quan:le(values((Z)(
• Plot(the(pairs(of(points(with(observed(data(values((X)(on(the(
ver:cal(axis(and(the(standardized(normal(quan:le(values((Z)(on(
the(horizontal(axis(
• Evaluate(the(plot(for(evidence(of(linearity(
36(
The$Normal$Probability$Plot$Interpreta3on
A normal probability plot for data from a normal distribution
will be approximately linear:
Left-Skewed
(b - a)2
σ=
Standard deviation: 12
where
f(X) = value of the density function at any X value
a = minimum value of X
b = maximum value of X
8
• Example: Uniform probability distribution over the
range 2 ≤ X ≤ 6:
μ=
σ=
P(3 ≤ X ≤ 5) =
• To use the normal to approximate the binomial, accuracy is improved if you use a correction for
continuity adjustment
• The closer π is to 0.5, the better the normal approximation to the binomial
• The larger the sample size n, the better the normal approximation to the binomial
•
General'Rule
•
• The$normal$distribu1on$can$be$used$to$approximate$the$
binomial$distribu1on$if:$
• $nπ$≥$5$ $and$ $n(1$–$π)$≥$5$
• Remember:$mean$and$standard$devia1on$for$binomial$
• µ = nπ"
• !=√#$(1−$) "
• If$using$normal$approxima1on,$calculate$Z$score$using$
the$formula:$
• &=((−))/! =((−#$)/√#$(1−$) $
9
42$
• EXAMPLE: If n = 1000 and π = 0.2, what is P(X ≤ 180)?
•
10