Why do normal distributions matter?

All kinds of variables in natural and social

sci approximately normally distributed.
Height, Because normally distributed
variables are s

Understanding the properties of normal dist

inferential statistics to compare different gro

What are the properties of normal dist

Normal distributions have key characteri
The mean, median and mode are exactly
The distribution is symmetric about the m
The distribution can be described by two
The mean is the location parameter while

The mean determines where the peak of

Increasing the mean moves the curve right,

The standard deviation stretches or sque

results in a narrow curve, while a large stand
Empirical rule
The empirical rule, or the 68-95-99.7 rul

Around 68% of values are within 1 stand

Around 95% of values are within 2 stand
Around 99.7% of values are within 3 stan

Example: Using the empirical rule in a no

students in a new test preparation course
The data follows a normal distribution wit
Following the empirical rule:

Around 68% of scores are between 1,00

Around 95% of scores are between 850
Around 99.7% of scores are between 70
The empirical rule is a quick way to get a

If data from small samples do not closely

like the t-distribution may be more appropri
Once you identify the distribution of your va

Central limit theorem

The central limit theorem is the basis for ho
In research, to get a good idea of a populatio
A sampling distribution of the mean is the di

The central limit theorem shows the followi

Law of Large Numbers: As you increase sa

then the sample mean will approach the
pop

With multiple large samples, the sampling di

Parametric statistical tests typically assume t

but the central limit theorem means that thi

You can use parametric tests for large sampl

as other important assumptions are met. A s
For small samples, the assumption of norma
For accurate results, you have to be sure tha
ences are normally or
birth weight, reading ability, job satisfaction, or SAT
o common, many statistical tests are designed for
no

ributions means you can use

ups and make estimates about populations using sa

ributions?
stics that are easy to spot in graphs:
the same.
ean—half the values fall below the mean and h
values: the mean and the standard deviation.
 the standard deviation is the scale parameter.

the curve is centered.

while decreasing it moves the curve left.

ezes the curve. A small standard deviation

ard deviation leads to a wide curve.
e, tells you where most of your values lie in a no

ard deviation from the mean.

ard deviations from the mean.
dard deviations from the mean.

rmal distributionYou collect SAT scores from

.
h a mean score (M) of 1150 and a standard dev

0 and 1,300, 1 standard deviation above and bel

and 1,450, 2 standard deviations above and belo
0 and 1,600, 3 standard deviations above and b
n overview of your data and check for any outlie

follow this pattern, then other distributions

ate.
riable, you can apply appropriate statistical tests.

w normal distributions work in statistics.

 n mean, ideally you’d collect data from multiple ran
stribution of the means of these different samples.

ng:

mple size (or the number of samples),

ulation mean.

stribution of the mean is normally distributed, even

hat samples come from normally distributed popula

s assumption isn’t necessary to meet when you have

es from populations with any kind of distribution as l

ample size of 30 or more is generally considered larg
lity is important because the sampling distribution
of t the population is normally distributed before
you c
scores are just a few examples of such variables.
rmally distributed populations.

mples.

alf above the mean.

rmal distribution:

iation (SD) of 150.

ow the mean.
w the mean.
elow the mean.
rs or extreme values that don’t follow this patter
dom samples within the population.

if your original variable is not normally distributed.

tions,
a large enough sample.

ong
e.
the mean isn’t known.
an use parametric tests with small samples.
n.
Normal Distribution: Definition and Properti
A normal distribution is symmetrically shape
Key properties of normal distributions:
The mean, median, and mode are identical.

The distribution is symmetric around the me

It is characterized by two parameters:
Mean (μ): Determines the peak of the
curve. Standard deviation (σ): Controls the
curve’s
The empirical rule provides insights into wh
Approximately 68% of values fall within 1 sta
About 95% of values lie within 2 standard
de Nearly 99.7% of values are within 3 d
standar
Excel Functions for Normal Distributio
NORM.DIST:
Calculates the probability density functio
Syntax: NORM.DIST(x, mean,
standard_ x: Value for which you want
to find the de mean: Mean of the
distribution.
standard_dev: Standard deviation.
cumulative: Set to TRUE for CDF or
FAL
Example: NORM.DIST(5, 3, 2, TRUE)
re

NORM.INV:
Returns a normally distributed value give
Syntax: NORM.INV(probability,
mean, st probability: Desired
probability.
mean: Mean of the distribution.
standard_dev: Standard deviation.
Example: NORM.INV(0.95, 90, 10)
calcu

Example: Calculating Normal Distribu

Suppose we have exam scores normally
and a standard deviation of 10. We want
Probability Less than Some Value:
Using NORM.DIST, we can find the prob
Example: What’s the probability of scorin
NORM.DIST(85, 90, 10, TRUE) gives
the
Inverse Calculation (Finding Value Giv
Using NORM.INV, we find the score corr
Example: What score corresponds to the
NORM.INV(0.80, 90, 10) provides the
va
Remember, normal distribution is a powe
Excel simplifies these calculations, allowing y
es
d, resembling a bell curve.

an.

width.

ere most values lie in a normal distribution:

ndard deviation from the mean.
viations.
deviations.

n (PDF) or cumulative distribution function (CDF

dev, cumulative)
nsity or cumulative value.

SE for PDF.
turns the CDF value of 0.841 (area to the left of

n a probability, mean, and standard deviation.

andard_dev)

lates the value corresponding to the 95th percen

tion in Excel
distributed with a mean of 90
to find probabilities related to these scores.

ability that a score is less than a given value.

g below 85?
CDF value.
en Probability):
esponding to a given percentile.
80th percentile?
lue.
rful tool for analyzing data and making statistica
ou to explore probabilities and percentiles effortless
) for a normal distribution.
5).

tile.

l inferences.
ly!
Formula of the normal curve
Once you have the mean and standard
you can fit a normal curve to your data usin

In a probability density function, the area u

The normal distribution is a probability distr
so the total area under the curve is always
The formula for the normal probability dens
But to use it, you only need to know the po
For any value of x, you can plug in the mean
into the formula to find the probability dens

You want to know the probability that SA

On your graph of the probability density
shaded area under the curve that lies to th

You collect SAT scores from students in a ne

The data follows a normal distributio

Mean 1150
SD 150

x ValueProb (PDF) Prob(CDF)

500 0.000% 0.001%
550 0.000% 0.003%
 600 0.000% 0.012%
650 0.001% 0.043%
700 0.003% 0.135%
750 0.008% 0.383%
800 0.017% 0.982%
850 0.036% 2.275%
900 0.066% 4.779%
950 0.109% 9.121%
1000 0.161% 15.866%
1050 0.213% 25.249%
1100 0.252% 36.944%
1150 0.266% 50.000%
1200 0.252% 63.056%
1250 0.213% 74.751%
1300 0.161% 84.134%
1350 0.109% 90.879%
1400 0.066% 95.221%
1450 0.036% 97.725%
1500 0.017% 99.018%
1550 0.008% 99.617%
1600 0.003% 99.865%
1650 0.001% 99.957%
1700 0.000% 99.988%
1750 0.000% 99.997%
1800 0.000% 99.999%
Probability Density Function

Definition: The PDF, denoted

Interpretation: f(x) describe
not the probability of it lying
It's similar to the density of

The PDF of a continuous uniform dis

Cumulative Probability Distributio

Definition: The CDF, denoted by F(

Interpretation: F(x) tells you the cu
For example, if F(5) = 0.8, it means

Shape: Non-decreasing function, sta

Application: Finding probabilities of
Example: Imagine rolling a fair 6-sid

The CDF at x = 3 would be F(

deviation of a normal distribution,
g a probability density function.

nder the curve tells you probability.

ibution,
1 or 100%.
ity function looks fairly complicated.
pulation mean and standard deviation.
and standard deviation
ity of the variable taking on that value of x.

T scores in your sample exceed 1380.

function, the probability is the
e right of where your SAT scores equal 1380.

w test preparation course.

n with a mean score (M) of 1150 and a standard devi

'PROB'
0.003
 0.0025

0.002

0.0015
Pr

0.001

0.0005

x Values
 (PDF):

by f(x), represents the instantaneous probability den

s the relative likelihood of the variable being exactly
within a range.
a physical object; a higher density at a point indicate

tribution between 0 and 1 is a constant function equal to 1 across th

n (CDF):

x), represents the probability that a random variable X will take on a

mulative probability up to a certain point x.
there is an 80% chance that the variable will have a value less

rts at 0 and eventually reaches 1 as x approaches positive infinity.

specific ranges (e.g., P(X ≤ 5) = F(5)).
ed die.
3) = 0.5, meaning there's a 50% chance of rolling a val
ation (SD) of 150.

Prob(CDF)
1.2
 1

0.8

0.6

0.4

0.2

0
0 200 400 600 800 1000 1200
sity of the random variable X taking on the value x.
equal to x,

s a greater chance of finding the object there.

at range, implying equal probability for any value between 0 and 1

value less than or equal to x.

than or equal to 5.

ue less than or equal to 3 (i.e., 1 or 2).

1400160018002000
.
Data of Temperature in Cel.
Mean 72.0000 72
Stdev 1 2
67.0000 0.00% 0.88%
67.5000 0.00% 1.59%
68.0000 0.01% 2.70%
68.0000 0.01% 2.70%
68.5000 0.09% 4.31%
69.0000 0.44% 6.48%
69.0000 0.44% 6.48%
69.5000 1.75% 9.13%
70.0000 5.40% 12.10%
70.0000 5.40% 12.10%
70.5000 12.95% 15.06%
71.0000 24.20% 17.60%
71.0000 24.20% 17.60%
71.5000 35.21% 19.33%
72.0000 39.89% 19.95%
72.0000 39.89% 19.95%
72.5000 35.21% 19.33%
73.0000 24.20% 17.60%
73.0000 24.20% 17.60%
73.5000 12.95% 15.06%
74.0000 5.40% 12.10%
74.0000 5.40% 12.10%
 74.5000 1.75% 9.13%
75.0000 0.44% 6.48%
75.0000 0.44% 6.48%
75.5000 0.09% 4.31%
76.0000 0.01% 2.70%
76.0000 0.01% 2.70%
76.5000 0.00% 1.59%
77.0000 0.00% 0.88%
77.0000 0.00% 0.88%

Mean 72.0000 70
Stdev 2.6 2.6
67.0000 2.41% 7.89%
67.5000 3.43% 9.66%
68.0000 4.70% 11.41%
68.0000 4.70% 11.41%
68.5000 6.20% 12.99%
69.0000 7.89% 14.25%
69.0000 7.89% 14.25%
69.5000 9.66% 15.06%
70.0000 11.41% 15.34%
70.0000 11.41% 15.34%
70.5000 12.99% 15.06%
71.0000 14.25% 14.25%
71.0000 14.25% 14.25%
71.5000 15.06% 12.99%
72.0000 15.34% 11.41%
72.0000 15.34% 11.41%
72.5000 15.06% 9.66%
73.0000 14.25% 7.89%
73.0000 14.25% 7.89%
73.5000 12.99% 6.20%
74.0000 11.41% 4.70%
74.0000 11.41% 4.70%
74.5000 9.66% 3.43%
75.0000 7.89% 2.41%
75.0000 7.89% 2.41%
75.5000 6.20% 1.64%
76.0000 4.70% 1.07%
76.0000 4.70% 1.07%
76.5000 3.43% 0.67%
77.0000 2.41% 0.41%
77.0000 2.41% 0.41%
 72
0.5 Diagrammtitel
0.000% Datenreihen1 Datenreihen2

90.00%
0.000%
80.00%
0.000% 70.00%

0.000% 60.00%

0.000% 50.00%

0.000% 40.00%

0.000% 30.00%

0.000%
20.00%

10.00%
0.027% 0.00%

0.027% -10.00%
66 68 70 72

0.886%
10.798%
10.798%
48.394%
79.788%
79.788%
48.394%
10.798%
10.798%
0.886%
0.027%
0.027%
0.000%
0.000%
0.000%
0.000%
0.000%
0.000%
0.000%
0.000%
0.000%

74
2.6 Datenreihen

0.41% 18.00%

0.67%
16.00%
1.07%
1.07% 14.00%

1.64% 12.00%

2.41%
10.00%
2.41%
3.43% 8.00%

4.70% 6.00%

4.70%
4.00%
6.20%
7.89% 2.00%

0.00%
 66 68 70
7.89%
9.66%
11.41%
11.41%
12.99%
14.25%
14.25%
15.06%
15.34%
15.34%
15.06%
14.25%
14.25%
12.99%
11.41%
11.41%
9.66%
7.89%
7.89%
l
Datenreihen3

747 67
8
Diagrammtitel
n1Datenreihen2Datenreihen3
72747678
A test is normally distributed with a m

What score would be needed to be

in What score would be needed to
be in

Mean 70
Stdev 8

(a) 85% 1.036

(b) 22% -0.77

A variable is normally distributed e

with a m
One score is randomly sampled. What
Mean 120
Stdev 5
X 127
P(x>127)

=NORM
P(X<=127) 91.9243%
 8.0757% =1-E25

Aliter
1.4 0.9192 0.080756659

population standard deviation of 𝜎=2.

Heights
State of adult women in the United
A medical researcher is planning to se

What is the standard value, or 𝑧 -

value

Mean 63.5
STDEV 2.5
x 68.5
Z value 2

An automobile manufacturer
introd A person who plans to
purchase on and found out
that the standard de Assume
that in-city mileage is app

What is the probability that

the per averages less than 20
miles per gal
What is the probability that the per
averages between 25 and 29 miles per

Given
Mean 27 StdeV
(a)
X 20
P(X<20) 0.009815329

(b) x 25
x 29
Prob ( 25<X<29) 0.495
ean of 70 and a standard deviation of 8.

the 85 percentile?
the 22 percentile?

78.291 78.29
63.822 63.82

an of 120 and a standard deviation of 5.

is the probability it is above 127?

.DIST(D22,D20,D21,TRUE)
s are normally distributed with a population mean
of
5
lect a large random sample of adult women to p
, for an adult woman who has a height of 68.5in

uces a new model that averages 27

miles pe e of these new cars wrote the
manufacturer viation is 3miles per
gallon.
roximately normally distributed.

son will purchase a car

that lon for in-city
driving?
son will purchase a car that
gallon for in-city driving?

0.25249 =NORM.DIST(E61,$D$56,$G$56,TRUE)
0.74751 =NORM.DIST(E62,$D$56,$G$56,TRUE)
=G62-G61
=63.5 inches and

articipate in a future study.

ches?

r gallon in the city

for the details of the tests,
The Z-distribution, also known as the
where the mean (average) is 0 and th
Here are some key points about the
Z

Standardization: Any normal distribu

its values into Z-scores. Z-scores tell

Z-Scores: A Z-score is a standard scor

from the mean an individual value lie
A positive Z-score means that your va
while a negative Z-score means that

Comparison of Distributions: Conver

you to calculate the probability of cer

Shape and Position: Every normal

dis been stretched or squeezed and
mo Increasing the mean moves the
curv The standard deviation
stretches or
. A small standard deviation results i

you to calculate the probability of cer

occurring and to compare different

d Z-Distribution Formula: It is

possible z=(X–μ) / σ

where X is a normal random variable

Standard Normal Distribution, is a special type of no
e standard deviation (a measure of data dispersion)
-distribution:

tion can be standardized by converting

you how many standard deviations from the mean e

e that tells you how many standard deviations away

s.
lue is greater than the mean,
your value is less than the mean

ting a normal distribution into a Z-distribution allows

tain values occurring and to compare different data

tribution is a version of the standard normal

distribu ved horizontally right or left. The mean
determines e right, while decreasing it moves the
curve left. squeezes the curve
n a narrow curve, while a large standard deviation l

tain values
ata sets.

to transform every normal random variable X into a

, μ is the mean of X, and σ is the standard deviation o

rmal distribution
is 1

ach value lies

sets1.

tion that’s
where the curve is centered.

eads to a wide curve1.

Z-score using the following formula:

2
fX
 A B C D E
1 Value at Risk - single security
2
3 Portfolio value $ 1,000,000
4 Expected volatility 30.50%
5 Time (days) 21
6 Confidence level 0.99
7 Stress event 2.33
8
9 VaR $ 204,825
The standard normal distribution, also known

Mean and Standard Deviation:

The mean of the standard normal distribution
The standard deviation is 1.

Z-Scores:
When you standardize any normal distribution
A z-score tells you how many standard deviati
Positive z-scores indicate that a value is greate
while negative z-scores indicate values below t

Comparison and Probability:

Standardizing a normal distribution allows you
Calculate the probability of specific values occ
Compare data sets with different means and s
Difference from Other Normal Distributions:

All normal distributions (including the standar

are unimodal and symmetrically distributed wi

However, a normal distribution can have any m

The standard normal distribution is a referenc

/ calculates z-score
Z. =(x-mean)/standard_deviation /
Excel Method
=STANDARDIZE(x, mean, standard_deviation) /

Mean 1150
SD 150

Converting
Z Score to
x ValueZ Score Prob
500 -4.333333333 0.003%
550 -4.000000000 0.013%
600 -3.666666667 0.048%
650 -3.333333333 0.154%
700 -3.000000000 0.443%
750 -2.666666667 1.140%
800 -2.333333333 2.622%
850 -2.000000000 5.399%
900 -1.666666667 9.948%
950 -1.333333333 16.401%
1000 -1.000000000 24.197%
1050 -0.666666667 31.945%
1100 -0.333333333 37.738%
1150 0.000000000 39.894%
1200 0.333333333 37.738%
1250 0.666666667 31.945%
1300 1.000000000 24.197%
1350 1.333333333 16.401%
1400 1.666666667 9.948%
1450 2.000000000 5.399%
1500 2.333333333 2.622%
1550 2.666666667 1.140%
1600 3.000000000 0.443%
1650 3.333333333 0.154%
1700 3.666666667 0.048%
1750 4.000000000 0.013%
1800 4.333333333 0.003%
as the z-distribution, is a special type of normal distri

is 0.

, its values are converted into z-scores. ons away from the m
he mean.

to:
urring.
tandard deviations.

d normal distribution)
th a bell-shaped curve.

ean and standard deviation.

e point where the mean is 0 and the standard deviati

/ calculates z-score

CONVERTING Z SCORE TO PROB

0.45

0.4

0.35

0.3

0.25

0.2

0.15

0.1

0.05

0
0 200 400 600 800 1000 1200 1400
bution with specific properties:
on is 1.

160018002000
mean 0
Sigma 1

x f(x) or P(x) Normal Dist

-5 0.000149% 0.0001487%
-4 0.013383% 0.0133830%
-3 0.443185% 0.4431848%
-2 5.399097% 5.3990967%
-1 24.197072% 24.1970725%
0 39.894228% 39.8942280%
1 24.197072% 24.1970725%
2 5.399097% 5.3990967%
3 0.443185% 0.4431848%
4 0.013383% 0.0133830%
5 0.000149% 0.0001487%
 'f(x) or P(x)'
0.45
0.4
0.35
0.3
0.25
0.2
f(x) or

0.15
0.1
0.05
0

-5 -4 -3 -2 -1 0 1
x
2345
The bivariate normal distribution is a spe
where you only have two variables (X and
Y). but capturing the potential correlation
betw

Definition: Two random variables X and

Both X and Y are individually normally di

There exists a linear relationship betwee
captured by the correlation coefficient (ρ). T

Properties:

Shape: Visualized as a 2D bell-shaped c

ρ = 0: X and Y are independent, ellipse b
-1 < ρ < 1: Positive or negative correlatio
ρ = 1 or ρ = -1: Perfect positive or negati

Bivariate Normal
Parameters: Distribution
Defined by: 2D
Mean vector (μ) with two elements: μ₁ fo
Covariance matrix (Σ) with two dimensio
Probability density function (PDF): De
Applications:

Similar to the general MVN, the bivariate

Statistics: Hypothesis testing about corr

Machine learning: Anomaly detection in
Finance: Analyzing correlations between
Natural sciences: Studying relationship
cific case of the multivariate normal distribution (
It's essentially a 2D version of the familiar bell-shap
een these two variables. Here's a breakdown of its k

Y are said to be bivariate normal if:

stributed (univariate normal). n X and Y,

his measures the strength and direction of their dep

urve (ellipse), with the shape influenced by the c

ecomes a circle.
n, stretches or shrinks the ellipse along the majo
ve correlation, ellipse collapses into a line.
r X and μ₂ for Y.
ns: σ₁₁ (variance of X), σ₂₂ (variance of Y), and σ
scribes the probability of observing specific valu
normal distribution finds applications in various

elations, regression analysis with two dependen

sensor data, Bayesian inference for classificatio
asset returns, modeling portfolio risk.
s between biological measurements, analyzing j
 MVN)
ed curve,
ey aspects:

endency.

orrelation coefficient:

r and minor axes.

₁₂ (covariance between X and Y).

es for X and Y simultaneously. It's a complicated
fields:

t variables, modeling bivariate data.

n tasks involving two features.

oint occurrences of environmental phenomena.

formula but readily available in statistical softw
are and libraries.
Suppose a bank is interested in the joi
The returns on these assets are rando
Let’s say the mean return on Asset A i
the standard deviations of their returns
The bank might be interested in questi

What is the probability that both asset

What is the probability that Asset A wil

To answer these questions, we would

the mean and dividing by the standard
Then, we would use the joint probability
d

Mean Stdev
Asset A 10% 15%
Asset B 8% 20%

Correl 0.5
X for A 10% 0 0.5
X FOR B 8% 0 0.5

Z_X = (Return on Asset A - Mean return o

Z_Y = (Return on Asset B - Mean return on

Probability = NORM.DIST(Z_X, TRUE) * (1

What is the probability that Asset A wil

X for A 10% 0 0.5

X FOR B 8% 0 0.5
nt behavior of two of its assets, Asset A and Ass
m variables that can be modeled using a bivariat
s 10%, the mean return on Asset B is 8%, and
are 15% and 20%, respectively. The correlation
ons like:

s will have returns greater than their means at

the l have a return greater than its mean but
Asset B

first standardize the returns by subtracting

deviation to get Z-scores.
ensity function of the bivariate normal distribution to

LetX be the return on Asset A and �Y be the r

Mean return on Asset A μ X ): 10%

Mean return on Asset B μ Y ): 8%
Standard deviation of returns of Asset A (σ X ): 1 Standa
Correlation coefficient between the returns of A
 25.00%

n Asset A) / Standard deviation of returns of Asset A

Asset B) / Standard deviation of returns of Asset B
- NORM.DIST(Z_Y, TRUE))

l have a return greater than its mean but Asset B

25.00%
et B.
e normal distribution.

between the returns is 0.5.

same time?
will not?

find the probabilities

eturn on Asset B. We are given:

5%
0%
sset A and Asset B ρ ): 0.51
will not?
μ1 0.00

𝝈1
μ2 0.00

𝝈2
1
1
⍴ 0.75

-3.0
-2.5
-2.0
-1.5
-1.0
-0.5
0.0
0.5
1.0
1.5
2.0
2.5
3.0
 -3.0 -2.5
0.000000000000 0.000000000000
0.000000000000 0.000000000014
0.000000000017 0.000000001163
0.000000001163 0.000000056015
0.000000046025 0.000001524150
0.000001028992 0.000023419756
0.000012991486 0.000203221030
0.000092626930 0.000995833345
0.000372947277 0.002755728354
0.000847987278 0.004306434737
0.001088837218 0.003800415316
0.000789529392 0.001893982553
0.000323299753 0.000533031179
 BIVARIATE Distribu

0.12

0.1

0.08

0.06

0.04

0.02

0
-3 -2.5 -2 -1.5 -1 -0.5 0 0.5 1

0-0.020.02-0.040.04-0.060.06-0.0

-2.0 -1.5
0.000000000008 0.000000000443
0.000000000843 0.000000031633
0.000000049433 0.000001274897
0.000001637001 0.000029016529
0.000030613377 0.000372947277
0.000323299753 0.002706955686
0.001928107450 0.011095492292
0.006493649116 0.025682880467
0.012350317647 0.033571644035
0.013264752835 0.024781820860
0.008045479288 0.010330599895
0.002755728354 0.002431921737
0.000533031179 0.000323299753
tion

3.0
2.0
1.0
0.0
-1.0

-2.0

1.5 2 -3.0
2.5
3

8 0.08-0.1 0.1-0.12

-1.0 -0.5 0.0

0.000000014678 0.000000294811 0.000003591536
0.000000719958 0.000009938708 0.000083215786
0.000019942749 0.000189211537 0.001088837218
0.000311957086 0.002034215731 0.008045479288
0.002755728354 0.012350317647 0.033571644035
0.013747055287 0.042343911320 0.079108841145
0.038727073380 0.081985214988 0.105271099837
0.061610027431 0.089642060967 0.079108841145
0.055350283612 0.055350283612 0.033571644035
0.028081481972 0.019300101492 0.008045479288
0.008045479288 0.003800415316 0.001088837218
0.001301713903 0.000422604630 0.000083215786
0.000118935332 0.000026538060 0.000003591536
 0.5 1.0 1.5
0.000026538060 0.000118935332 0.000323299753
0.000422604630 0.001301713903 0.002431921737
0.003800415316 0.008045479288 0.010330599895
0.019300101492 0.028081481972 0.024781820860
0.055350283612 0.055350283612 0.033571644035
0.089642060967 0.061610027431 0.025682880467
0.081985214988 0.038727073380 0.011095492292
0.042343911320 0.013747055287 0.002706955686
0.012350317647 0.002755728354 0.000372947277
0.002034215731 0.000311957086 0.000029016529
0.000189211537 0.000019942749 0.000001274897
0.000009938708 0.000000719958 0.000000031633
0.000000294811 0.000000014678 0.000000000443
 2.0 2.5
0.000533031179 0.000533031179
0.002755728354 0.001893982553
0.008045479288 0.003800415316
0.013264752835 0.004306434737
0.012350317647 0.002755728354
0.006493649116 0.000995833345
0.001928107450 0.000203221030
0.000323299753 0.000023419756
0.000030613377 0.000001524150
0.000001637001 0.000000056015
0.000000049433 0.000000001163
0.000000000843 0.000000000014
0.000000000008 0.000000000000
 3.0
0.000323299753
0.000789529392
0.001088837218
0.000847987278
0.000372947277
0.000092626930
0.000012991486
0.000001028992
0.000000046025
0.000000001163
0.000000000017
0.000000000000
0.000000000000
μ1 0

𝝈1
μ2 0

𝝈2
1
1
⍴ -0.9

-3.0
-2.5
-2.0
-1.5
-1.0
-0.5
0.0
0.5
1.0
1.5
2.0
2.5
3.0
 -3.0 -2.5
0.000000004811 0.000000005057
0.000000449284 0.000000740744
0.000011256572 0.000029106226
0.000075657400 0.000306805887
0.000136413258 0.000867563702
0.000065981418 0.000658110698
0.000008561436 0.000133923386
0.000000298010 0.000007310949
0.000000002783 0.000000107066
0.000000000007 0.000000000421
0.000000000000 0.000000000000
0.000000000000 0.000000000000
0.000000000000 0.000000000000
 BIVARIATE Distribu

0.07

0.06

0.05

0.04

0.03

0.02

0.01

-3 -2.5 -2 -1.5 -1 -0.5 0 0.5

-2.0 -
0-0.010.01-0.020.02-0.030.03-0.040

0.000000003225 0.000000001247
0.000000740744 0.000000449284
0.000045647649 0.000043421387
0.000754620713 0.001125761817
0.003346562373 0.007829774122
0.003981337716 0.014608709213
0.001270629706 0.007311969107
0.000108784967 0.000981785793
0.000002498496 0.000035363809
0.000000015394 0.000000341713
0.000000000025 0.000000000886
0.000000000000 0.000000000001
0.000000000000 0.000000000000
ution

3.0
2.0
1.0
0.0
-1.0

-2.0
1 -3.0
1.5
2.5
2
3

-1.0
.04-0.05 0.05-0.06 0.06-0.07 -0.5 0.0
0.000000000293 0.000000000042 0.000000000004
0.000000165282 0.000000036879 0.000000004991
0.000025051961 0.000008766627 0.000001860699
0.001018631416 0.000559036774 0.000186087177
0.011110978369 0.009563307708 0.004992484401
0.032512280266 0.043886987872 0.035931626631
0.025521279878 0.054028549925 0.069374031330
0.005374243782 0.017843117726 0.035931626631
0.000303593289 0.001580804132 0.004992484401
0.000004600731 0.000037570353 0.000186087177
0.000000018703 0.000000239537 0.000001860699
0.000000000020 0.000000000410 0.000000004991
0.000000000000 0.000000000000 0.000000000004
 0.5 1.0 1.5
0.000000000000 0.000000000000 0.000000000000
0.000000000410 0.000000000020 0.000000000001
0.000000239537 0.000000018703 0.000000000886
0.000037570353 0.000004600731 0.000000341713
0.001580804132 0.000303593289 0.000035363809
0.017843117726 0.005374243782 0.000981785793
0.054028549925 0.025521279878 0.007311969107
0.043886987872 0.032512280266 0.014608709213
0.009563307708 0.011110978369 0.007829774122
0.000559036774 0.001018631416 0.001125761817
0.000008766627 0.000025051961 0.000043421387
0.000000036879 0.000000165282 0.000000449284
0.000000000042 0.000000000293 0.000000001247
 2.0 2.5
0.000000000000 0.000000000000
0.000000000000 0.000000000000
0.000000000025 0.000000000000
0.000000015394 0.000000000421
0.000002498496 0.000000107066
0.000108784967 0.000007310949
0.001270629706 0.000133923386
0.003981337716 0.000658110698
0.003346562373 0.000867563702
0.000754620713 0.000306805887
0.000045647649 0.000029106226
0.000000740744 0.000000740744
0.000000003225 0.000000005057
 3.0
0.000000000000
0.000000000000
0.000000000000
0.000000000007
0.000000002783
0.000000298010
0.000008561436
0.000065981418
0.000136413258
0.000075657400
0.000011256572
0.000000449284
0.000000004811