Answer -1 ->

In the form of a hierarchical structure, the many actions that must be carried out in order
to resolve a problem are shown as tree nodes in a tree diagram. The tree diagram
illustrates a structure that is similar to a tree. The look of a tree is created by the fact that
each node in the diagram contains a branch that may further grow into another branch. In
the realm of mathematics, tree diagrams are useful tools for visually representing and
working through problems involving probability. They are a vital part of the process of
seeking answers to questions and resolving issues. Even while tree diagrams might be
beneficial for presenting many various types of sophisticated situations, their
applicability reduces dramatically as the sample size rises. This is because tree diagrams
are best suited for demonstrating relationships between a small number of variables.

A probability tree diagram may be used to provide a graphical representation of the

numerous outcomes that might be associated with an occurrence. Everything starts out as
a single dot, and from there it expands into the area around it. On each of the tree's
branches, it is feasible to make an estimate of the likelihood that each of the potential
outcomes will come to pass.

The following are some of the features of tree diagrams –

❖ We write the probability of each branch of a tree diagram on the node that
corresponds to that branch.
❖ We write the ultimate result at the end of each branch when we're done with it.
❖ Depending on the outcomes that are most likely to occur, a node that is located at
the end of each branch may produce more branches.
❖ Keep in mind that the total probability for all of the branches leading off of each
node is 1.
Probability Tree Diagram for the Case Study -

There are three airlines that provide service to Srinagar. One of the three airlines, Amira
Airlines, is responsible for more over fifty percent of the total flights. It has been brought
to the attention of both Biyas airline, which is responsible for thirty percent of the city's
flights, and Chinar airline, which is responsible for twenty percent of the city's flights.
There is a timely arrival of flights eighty percent of the time, sixty percent of the time,
and forty percent of the time.

Probability of the flights is -

P (Amira) = 0.50
P (Biyas) = 0.30
P (Chinar) = 0.20

And the Conditional Probability is –

P (E|Amira)= 0.80
P (E|Biyas) = 0.65
P (E|Chinar) = 0.40

Airline A is responsible for fifty percent of all scheduled flights, whereas airlines B and C
are responsible for thirty and twenty percent, respectively. Their relative on-time
percentages are 80%, 65%, and 40%.
Assuming,
Airline A's planned flights are represented by Event A.
Airline B's planned flights are represented by Event B.
 Airline C's planned flights are represented by Event C.
P(A|E) = P(E|A) X P(A)
P(E|B) X P(B) + P(E|C) X P(C) + P(E|A) X P(A)

P ((A|E) = (0.80*0.50)/(0.80*0.50)+(0.65*0.30)+(0.40*0.20)= 0.59259

As a result, the flight that departed Srinagar for airline Amira is 0.5926.
= 59.26 %

The chance tree diagram is a good way to figure out how likely it is that a number of
things will happen at the same time. With the equal, you can make a graph that shows
how likely it is that a certain set of events will happen. When you use this method, it's
much easier to figure out complicated calculations with a chance factor. When dealing
with a complicated chance, it might be hard to tell whether to multiply or add the
probability. Using a tree diagram of possible options will make it easier for you to see
how the process works and decide if you need more chances or not.

Using a "possibility tree diagram" can be very helpful when trying to figure out the
chances of certain events that could go well or badly. When paired with a graphical
representation, it lets a person see how different changes can lead to many different
outcomes. If you use this strategy, you won't have to use complicated formulas to figure
out the odds. It can be hard to know whether to multiply or add the possibilities when
doing a full probability calculation. It's possible that using a probability tree diagram to
show the process will make it much easier to understand. This could help a parent who
needs to multiply or add numbers.
Answer -2 ->

Dependent Variable - The dependent variable is the one that changes as a result of the
independent variable's modification. It's the outcome you're looking for, and it's
"depending" on your independent variable.
Dependent variables are also known as –
❖ response variables (they respond to a change in another variable)
❖ Variables affecting the result (they represent the outcome you want to measure)
❖ Left-hand variables (they appear on the left-hand side of a regression equation)
You'll record the dependent variable once you've changed the independent variable. You
may use statistical analysis to assess if and to what extent your independent variable
influences the dependent variable.

Independent Variable - An independent variable is a variable that you can manipulate

or adjust in order to observe what impact it has on the experiment results. Because it's
unaffected by the other variables in the research, it's referred to as "independent."
Independent variables include, but are not limited to –
❖ Variables that help explain why something happened (they explain an event or
outcome)
❖ Variables that may be used to predict outcomes (they can be used to predict the
value of a dependent variable)
❖ Right-hand side variables (they appear on the right-hand side of a regression
equation).
If you're attempting to determine out how much a change in the independent variable
explains or predicts changes in the dependent variable, these phrases are often used in
statistics.

Regression Analysis - Linear regression explains the link between numerical results and
explanatory factors (also known as dependent and independent variables). Many
explanatory variables need multiple linear regression, whereas one requires simple linear
regression. This word is used when forecasting many dependent variables.
Regression analysis formula -
y = mx + b
Where,
y is the regression equation's dependent variable.
m is the regression equation's slope.
x is the regression equation's dependent variable.
b= the equation's constant
Regression Analysis for the case study –

Sales of Spending in number of sales customer-

Region/ Kahwa (in advertise (in representatives satisfaction
Districts INR) INR) (person) ratings
Kupwara 55328 5512 1 1

Badgam 56251 8337 1 1

Leh-
ladakh 57126 8788 4 1
Kargil 58739 8828 5 1
Punch 66984 9050 5 2
Rajouri 70676 10150 7 2
Kathua 73206 11236 8 2
Baramul
a 80571 12538 8 3
Bandipo
re 93168 13161 8 3
Srinagar 99432 13448 9 4

SUMMARY OUTPUT

Regression
Statistics
Multiple R 0.981088188
R Square 0.962534032
Adjusted R Square 0.943801048
Standard Error 3721.75587
Observations 10

ANOVA
Significanc
df SS MS F eF
Regression 3 2135139002 7.12E+08 51.38178 0.000113
83108800.5
Residual 6 5 13851467
Total 9 2218247803

Coefficie Standard P- Lower Upper Lower Upper

nts Error t Stat value 95% 95% 95.0% 95.0%
Interce 32355.2 8538.400 3.789 0.009 11462. 53247. 11462.5 53247.9
pt 6089 022 382 08 55 97 5 7

X
Variabl 1.68683 1.500232 1.124 0.303 - 5.3577 5.35777
e1 5512 214 383 811 1.9841 71 -1.9841 1
X - -
Variabl 155.529 1061.613 0.146 0.888 - 2442.1 2442.14
e2 4991 404 5 323 2753.2 45 -2753.2 5
X 11309.3 2589.262 4.367 0.004 4973.6 17645. 4973.63 17645.0
Variabl 3441 959 781 73 36 03 6 3
e3

Regression table interpretation –

Part-1 – Summary Output – This section indicates how well the linear regression
equation you developed matches your source data.
❖ Multiple R - The linearity of a link between two variables may be quantified with
the help of the correlation coefficient. The correlation coefficient may have any
value between -1 and 1, and the absolute value of the coefficient indicates how
strong the relationship is between the two variables. The absolute value has a
direct correlation with how robust the association is –
o 1 means a strong positive relationship
o -1 means a strong negative relationship
o 0 means no relationship at all
❖ R squared - When assessing the level of quality in the fit, the coefficient of
determination is the metric that is considered. The number of points that are found
to fall on the regression line is shown below. The R2 value is derived from the
complete sum of squares, or, to be more precise, the sum of the squared
deviations from the mean of the initial data.
❖ Adjusted R square - It is equal to the square of the correlation coefficient
multiplied by the total number of variables in the model. This value, rather than R
square, should be utilised when doing an analysis of multiple regressions.
❖ Standard Error of the regression - The lower the number, the more confidence
you may be in your regression equation, another goodness-of-fit metric says about
the quality of your regression analysis. R2 measures how much of the variance in
the dependent variable can be explained by the model, while Standard Error
measures how far the data points are from the regression line on average.
❖ Observations - The amount of observations in your model is all it is.

Part-2 – ANOVA - A succession of various components, each of which exposes a

different amount of variability, are used in the construction of regression models. These
components are as follows -
❖ df is a notation that stands for the number of degrees of freedom that are
connected to the different sources of variation.
❖ The sum of all the squares equals SS. If the Residual SS is lower than the Total
SS, then your model will have a greater chance of accurately representing the
data.
❖ The abbreviation MS stands for "mean square."
❖ The F statistic, sometimes referred to as the F test, is used in the process of
determining whether or not to accept the null hypothesis. It is used to evaluate the
significance of the model in its whole.
❖ Significance The value of P for F is also F.
Part-3 – Regression Analysis Output : Coefficients - Here, you'll find a wealth of
information about each of the elements that went into your data analysis. As a result,
depending on the information you enter into the spreadsheet, the first column will display
a different value.
❖ Coefficient - Gives you the least squares estimate.
❖ Standard Error - the estimate of the standard error obtained by using the
least squares method.
❖ T Statistic - This refers to the T Statistic for comparing the alternative
hypothesis to the null hypothesis.
❖ P Value - Displays the p-value that corresponds to the hypothesis test.
❖ Lower 95% - The lower 95 percent confidence interval is the bottom border
of the confidence interval.
❖ Upper 95% - The top border of the confidence interval is denoted by the term
"upper 95 percent."
Answer -3a ->

In the fields of statistics and probability theory, the binomial distribution is a discrete
probability distribution that is used for situations in which there are only two probable
outcomes in an experiment: success or failure. (In English, the prefix "bi" signifies "two"
or "twice.") A toss of the coin to determine "heads" or "tails," the result of a test to
determine "pass" or "fail," the outcome of an interview to determine "yes" or "no," and
the nature of a product to determine "defective" or "non-defective" are all instances of
binomial trials. A kind of random variable distribution known as a binomial distribution
is called a binomial probability distribution.
The binomial distribution is a discrete distribution that is often used in the field of
statistics. The normal distribution, on the other hand, is a continuous distribution, in
contrast to the binomial distribution, which is discrete.
The probability distribution associated with a binomial random variable is referred to as a
binomial distribution. A random variable is a real-valued function in which the domain is
the sample space of an experiment that uses random sampling.
Statistical characteristics of the binomial distribution –
❖ There are just two unique outcomes that are even somewhat possible: truthful or
false, successful or unsuccessful, yes or no.
❖ In a certain experiment, there is a predetermined maximum number of 'n' times
repeated trials.
❖ There is no change in the likelihood of either success or failure from one try or
trial to the next.
❖ Out of 'n' separate tries, only the successful efforts are taken into account in the
calculation.
❖ Because each and every experiment is conducted on its own, the results of one
trial do not have any bearing on the results of any other trials that may occur in
the future.

Binomial Distribution Formula –

P(x) = nCx * px * (1 − p)n−x

As per the question,

n = 25
x = 15
p = 0.75
q or (1 - p) = 0.25
Putting the values in Binomial Distribution formula -
Case -1 -> Exactly 15 would agree with the claim
25
C15 * 0.7515 * 0.2510
=0.0417

As per the question,

n = 25
x = 20
p = 0.75
 q or (1 - p) = 0.25
Putting the values in Binomial Distribution formula -
Case -2 -> Exactly 20 would agree with the claim
25
C20 * 0.7520 * 0.255
=0.1645
Answer -3b ->

Z-scores are applied to the data in order to normalize the series and make it possible to
make comparisons of mortality trends across different populations or different time
periods. The z-unit score's of measurement is known as the standard deviation. It makes it
possible to examine data derived from many normal distributions at the same time.
Z-score = (x-mean of the population)/Standard deviation of the population, which, in our
context, could be approximated by S-score = (number of deaths - baseline)/Standard
deviation of the residuals (variation of the number of deaths around the baseline) on the
part of the series that was used to fit the model, with the standard unit being used as the
number of deaths.
Z-scores are computed on the detrended and de-seasonalized data using the method that
was outlined by Farrington et al. 1996. This is done after a 2/3 powers transformation has
been applied. Because of this, it is now feasible to calculate Z-scores for data series that
follow the Poisson distribution.

A z-score for an individual value can be interpreted as follows –

❖ The raw score is greater than the mean average if the z-score is positive. A z-score
of +1, for example, indicates that it is one standard deviation above the mean.
❖ The raw score is below the mean average when the z-score is negative. A z-score
of -2, for example, indicates that the data is two standard deviations below the
mean.

Formula for z-score –

z = (x – μ )/ σ
where
z stands for the Z score's value
x denotes the raw score, data point, or observation from which the Z score is to be
calculated.
μ represents the mean of the population
σ is the general representation of the Standard deviation

Putting the value in the z-score formula as per the question,

Where,
Mean (μ) = 10000
Standard Deviation (σ) = 2400

a. P (X > 12000)
z = (12000 – 10000) / 2400 = 0.833
As per z-table, the area for z = 0.833 will be 0.79767
Thus P(x>12,000) = 1 - 0.79767= 0.2033

b. P (X < 9000)
z = (9000 – 10000) / 2400 = -0.41667
As per z-table, the area for z = -0.41667 will be 0.1591
Thus P(x<9000) = 0.33846