ISDS Revision
ISDS Revision
ISDS | REVISION
SESSION
IN 2 SLOTS
DATE: 7 DECEMBER,THURSDAY
VENUE: ATB 306
TIME: 10 AM | 1.30 PM
IQR = Q3 - Q1
Range: 25-2 = 23
Solution
Variance is a measurement
of the spread between
numbers in a data set.
Chebyshev’s Theorem
The proportion of any
distribution that lies within k
1-(1/k^2) standard deviations of the mean
is at least 1-(1/k^2), where k is
any positive number larger than
x - ks x x + ks 1. This theorem applies to all
distribution of data.
Chebyshev’s Rule
Combination Permutation
Exercise
VARIANCE
STANDARD DEVIATION
Discrete Probability Distribution
THE RANDOM VARIABLE “X” HAS THE FOLLOWING DISCRETE PROBABILITY DISRTRIBUTION:
x 1 3 5 7 9
≥
D) P(X 7) = P(X=7) + P(X=9) = 0.2 + 0.1 = 0.3
E) P(X>2) = (VALUES OF “X” WHICH ARE GREATER THAN 2) = P(X=3) + P(X=5) + P(X=7) + P(X=9) = 0.2
+ 0.4 + 0.2 + 0.1 = 0.9
F) MEAN WILL BE EQUAL TO THE SUM OF PRODUCTS OF “X” VALUES AND THEIS PROBABILITIES:
MEAN = 1 * 0.1 + 3 * 0.2 + 5 * 0.4 + 7 * 0.2 + 9 * 0.1 = 0.1 + 0.6 +2 + 1.4 + 0.9 = 5
Discrete Probability Distribution
The age distribution for the employees of a highly successful “dot-
com” company headquartered in Atlanta is shown in teh next table.
An employee is to be randomly selected form this population
Age 20 21 22 23 24 25 26 27 28 29 30 31 32 33
Proporti
on
0.02 0.04 0.05 0.07 0.04 0.02 0.07 0.02 0.11 0.07 0.09 0.13 0.15 0.12
b) What is the probability that the randomly selected employee is over 30 years of age? Over
40 years of age? Under 30 years of age?
c) What is the probability that the randomly selected employee will be 25 or 26 years old?
Solution
Age 20 21 22 23 24 25 26 27 28 29 30 31 32 33
Proporti
on
0.02 0.04 0.05 0.07 0.04 0.02 0.07 0.02 0.11 0.07 0.09 0.13 0.15 0.12
b) What is the probability that the randomly selected employee is over 30 years of age?
For this, we will take the values of Age which are more than 30 and sum their probabilities.
P(x>30) = P(x=31) + P(x=32) + P(x=33) = 0.13 + 0.15 + 0.12 = 0.4
Age 20 21 22 23 24 25 26 27 28 29 30 31 32 33
Proporti
on
0.02 0.04 0.05 0.07 0.04 0.02 0.07 0.02 0.11 0.07 0.09 0.13 0.15 0.12
2) Probability of getting Head is 0.5 ( if it is fair coin, of course). The same with Tail ( there is
a 0.5 chance of getting it. So, here we will have p=0.5. It means that the probability of
getting success outcome in each trial is 0.5.
3) As we are tossing the coin three times, we repeating the trial three times. It means that
number of identical trials in the experiment is 3. n=3.
4) First, we are asked to find the probability of getting two heads after tossing coin three
times. Here, we want to find 2 successes (exactly 2 heads, not at least, not at most). So, x=2.
5) Now, we can put the numbers to the formula and we will get:
P(x=2) = (3!/((3-2)!*2!)) * 0.5^2 * 0.5^1 = 0.375
So, the probability of getting exactly two heads after tossing coin three times is 37.5%
Solution
When it comes to getting AT LEAST two heads, we need to consider the cases,
when x will take the values which will satisfy that it will be AT LEAST = 2.
Here, the maximum value of x is 3, because after tossing coin three times, we
can get maximum three coins. It means, that for getting at least, we can
calculate the probability of getting x=2 and x=3 and sum them.
P(x=2) = 0.375, P(x=3) = 0.125, P (x>=2) = P(x=2) + P(x=3) = 0.375 + 0.125 = 0.5
Probability of getting at least two heads after tossing coin three times is 0.5
Binomial Distribution
Suppose a student is preparing for a multiple-choice test with 8
questions. Each question has 4 possible answers, and only one is
correct. The student hasn't studied and decides to guess the
answers.Passing the test requires answering at least 6 questions
correctly.
In Table, according to n=8, p=0.25, x=6, x=7, x=8, we find that Probabilities of
P(x=6) = 0.004, P(x=7) = 0, P(x=8) = 0. After adding them, we will get that
Probability of getting at least 6 correct answers is 0.4%
Poisson Distribution
1) The experiment consists of counting the number of times
a certain event occurs during a given unit of time or in a
given area or volume (or weigh, distance, or any other unit
of measurement
After solving the following problem, we will get the solution for the
first question, which is 0.1404.
So the probability that exactly 3 customers will arrive in the next
hour is 14.04%
Solution
What is the probability that no customers will arrive in
the next hour?
λ = 4.5 fatalities per month. First question asks to find out P(x=0),
Using the Poisson Distribution Table, we get that P(x=0) = 0.0111, 1.11%
Solution
What is the probability that one fatality will occur during a year?
As λ=4.5 fatalities per month, and we asked to find one fatality per a year, we
need to convert λ to fatalities per year. For this we can just use the following
cross product method:
However, in the Poission Table, there are no values of x for such a big lambda
like 54. So we will solve it using formula, and we will get:
We will get very small number of P(x=1) ~ 2 * 10^-22, which shows the
probability of getting one fatality during a year
Solution
Find E(x) and the standard deviation of “x”.
P(z<0.85)=0.80
There is no tears
in SOBE school
Hypothesis
Testing
Assumptions about population parameter
Hypothesis
Hypothesis testing is a statistical method used to
determine if there is enough evidence in a sample data to
draw conclusions about a population parameter.
Examples
02 04
01 03
Setting Calculating Formulating Making
Hypothesis test statistic decision rule decision
Problem
Petrol station reports that it serves to on average 600 cars per
day. You stayed there for 100 days and found out that on average
610 cars visited petrol station with standard deviation of 40 cars.
Left-sided: µ≥600
01 µ<600
Left-sided: =2.5
03
0.05
=1.645
Formulating
decision rule Right-sided: =2.5
0.05
=1.645
Two-sided: 2.5>1.96
There is sufficient evidence to
>z 0.025 claim average number of
clients is not 600
Type II error (false-negative): failing to reject a null hypothesis that is actually false
in the population
Decision rule: Reject Ho if p-value < alpha
p-value = P(z > 2.5) = P(z < -2.5) = 0.0062 < alpha = 0.05
NBA
Many basketball fans think that Michael Jordan has worse scoring
records of 3-Point Field Goal performance compared to Stephen
Curry. As of now, Curry has scored 3481 out of 8140 3-Point Field
shots. Jordan’s success rate was 32.7%. Let’s test whether Curry’s
performance in 3-Point Field shooting is statistically better than
that of Jordan or just based on good luck/chance. Calculate the
test statistic, significance level = 10%
0.327
0.327
p=3481/8140=42.8
0.428 - 0.327
zstat = =19.42
√0.327*(1 - 0.327)/8140
zcritic=1.28 Reject H0
There is way too much evidence that Curry is better than Jordan
in 3-point field shooting
You conducted a survey to find out how many
hours your groupmates studied ISDS a week. Your
results are the following: 25 students on average
studied 10 hours a week with standard deviation
of 2 hours. Your friend also conducted survey and
his results: 20 students studied on average 9 hours
a week with standard deviation of 3. Is there
enough evidence to claim your group studied on
average more hours than your friend’s group?
Significance level = 1%
H0: µ1< µ2 10 - 9 1
Ha: µ > µ zstat = = =1.2804
1 2 √ 4/25+9/20 √0.61
Fcritic
= 6.85. (from F table)