Logic Theory

Summary of the common Boolean Logic Gates with symbols and Truth Tables

Venn Diagrams for Logical Expression

1
 Basic Statistics – Diminishing Uncertainty

1. Collection of Data
When conducting a statistical survey, we are limited in the number of elements which we can
examine. Thus, we should take a sample which should be representative of whatever population is under
consideration. The word ‘population’ in this sense refers to the possible values of the set of variables
being examined (not the number of people).
The sample should be at random so that all members of the population have an equal chance of
being included. Indeed there are tables of random numbers which enable us to:
- Make selections of participants;
- Conduct a survey;
- Eliminate a certain amount of bias.

2. Organizing Data
The first stage in making data usable is to refine it into tabular (table) form – organized in order
and summarized.
In planning to organize the data, we need to bring out the pattern or distribution of the data. In
order to decide on what classes to use we need first to establish the scale of measurement and the range.
The scale may be continuous or discrete.
General rules for forming distributions or frequency distributions are:
- Determine the smallest (minimum) and the largest (maximum) in the raw data and thus find
the range.
- Divide the range into a convenient numbers of class intervals having the same size. If this is
not feasible, use class interval of different size or open class intervals.
- Determine the number of observations falling into each class interval – use a single stroke for
each observation and across-stroke for every fifth one (to make counting easier later). When
added, the total of the strokes in each class is its frequency. This process is known as tally.

3. Displaying the Data

3.1 Pictographs (Pitograms)
The pictograph or pictogram is often used to present
statistical data in a manner appealing to the general public.
The point of pictogram (also called ideograph or isotype
chart), is that the reader can easily identify the symbols with
the item whose frequency is shown. These symbols can be
subdivided but it is not wise to do so beyond the half-unit.

2
3.2 Pie graph (Pie charts)

Comparison Pie Chart Exploded Pie Chart

The pie chart uses a circle for the whole distribution; individual sectors represent the classes. The
size of the circle isn’t critical.
The angle at the centre of each sector is proportional to the frequency of the value that sector
represents; as the area of the sector is proportional to this angle also; it can be used to stand for the
frequency. Therefore the frequency can be identified directly with the angle at the centre of the sector or
with the sector area or with the arc length of the sector.

3.3 Bar graphs (Bar Charts)

Bar charts are an alternative method of representing data that could be shown on a pictogram or
pie chart, thus they are equally suitable for representing qualitative or quantitative data. The main
difference is the use of “bars” instead of sets of pictures or sectors of a circle.
The bars are equal width, have no significance in this case, so their area are proportional to their
lengths; thus the frequency for each is shown either by height or by area. The vertical scale indicates
frequency and is linear, so equal intervals on the scale stand for equal changes of frequency. The bar
themselves stand on a horizontal axis called baseline or datum with gaps between them, and with data
labels to show what each represents.

3.4 Histograms and Frequency Polygons

A histogram of a frequency distribution can be used to represent quantitative data only. The
histogram is rather like a bar chart to look at, though, there are no gaps between the bars, and the bars
base on a horizontal axis which has a linear scale with centres at the class marks. The range of values of

3
each class appears on the horizontal scale – so the order of
classes depends on the numerical order of the values. The
width of bars equal to the class interval sizes. The vertical axis
shows the frequency density of each class for areas of bars are
proportional to class frequencies.
A frequency polygon corresponding to the above
frequencies is a line graph of class frequency plotted against
class marks. It is superimposed on the histogram. It can be
obtained by connecting the mid-points of the tops of the bars
(rectangles) of the histogram by a series of straight lines.

3.5 Cumulative Frequency and Cumulative Frequency curve or Ogive

The total frequency of all values less than the upper class boundary of a given class interval is
called the cumulative frequency up to and including that class interval. i.e. Cumulative frequency is
defined as a running total of frequencies. The frequency of an element in a set refers to how many of that
element there are in the set. Cumulative frequency can also defined as the sum of all previous
frequencies up to the current point.
A cumulative frequency curve or Ogive is a line graph having the upper class boundries
represented on the horizontal axis and the cumulative frequencies on the vertical axis. The cumulative
frequency corresponding to each upper class boundary is marked by a point, and consecutive points are
connected by straignt line.

4. Measure of Central Tendency

4.1 The Mean or Arithmetic Mean
To find the arithmetic mean of a set of quantities we divide their total by the number of
quantities.

4
4.1.1 The Mean of Ungrouped data
For a set of 𝑁 numbers, 𝑥1 , 𝑥2 , …, 𝑥𝑁 , the mean (or arithmetic mean), denoted by 𝑥̅ , is defined
as
𝑥1 + 𝑥2 + … + 𝑥𝑁 ∑𝑁
𝑖=1 𝑥𝑖
𝑥̅ = =
𝑁 𝑁

4.1.2 The Mean of Frequency Distribution (Grouped data)

If the data are presented in a frequency table (i.e. grouped data), the mean is almost the same by
definition.
If the numbers 𝑥1 , 𝑥2 , …, 𝑥𝑁 , occur , 𝑓1 , 𝑓2 , …, 𝑓𝑁 times respectively, the mean is given by
𝑥1 𝑓1 + 𝑥2 𝑓2 + … + 𝑥𝑁 𝑓𝑁 ∑𝑁
𝑖=1 𝑥𝑖 𝑓𝑖 ∑ 𝑓𝑥
𝑥̅ = = 𝑁 =
𝑓1 + 𝑓2 + … + 𝑓𝑁 ∑𝑖=1 𝑓𝑖 ∑𝑓
We can reduce the amount of tedious arithmetic by using an assumed mean, denoted by 𝑥0 .
∑ 𝑓𝑑
Mean = 𝑥̅ = 𝑥0 +
∑𝑓
𝒙𝒊 𝒇𝒊 𝒅𝒊 = 𝒙 𝒊 − 𝒙 𝟎 𝑓𝑖 𝑑𝑖
𝑥1 𝑓1 𝑑1 𝑓1 𝑑1
𝑥2 𝑓2 𝑑2 𝑓2 𝑑2
⋮ ⋮ ⋮ ⋮
𝑥𝑁 𝑓𝑁 𝑑𝑁 𝑓𝑁 𝑑𝑁

∑𝑓 ∑ 𝑓𝑑

4.2 The Median

The median of a set of 𝑁 numbers arranged in order of ascending or descending at magnitude, is
the middle number of the set if 𝑁 is odd, or the mean of the two middle numbers if 𝑁 is even.

4.3 The Mode

The mode is often referred to as the typical average and the name given to the element which
occurs as the most common value in the list, i.e the “most popular” one.

4.4 The Geometric Mean

For a set of 𝑁 nonnegative numbers, 𝑥1 , 𝑥2 , …, 𝑥𝑁 , the geometric mean, denoted by G.M., is
defined as
G.M = 𝑁√𝑥1 ∙ 𝑥2 ∙ … ∙ 𝑥𝑁

4.5 The Harmonic Mean

For a set of 𝑁 numbers, 𝑥1 , 𝑥2 , …, 𝑥𝑁 , the harmonic mean is defined as
𝑁 𝑁
ℎ = =
1 1 1 1
+ + …+ ∑𝑁𝑖=1 𝑥
𝑥1 𝑥2 𝑥𝑁 𝑖

5
5. Measures of Spread or Dispersion
5.1 The Range
The range is by far the simplest measure of spread.
For a set of numbers of any distribution, the range is the difference between the largest and
smallest data value in the set.
For a frequency table, the range is the difference between the upper boundary of the highest
class and the lower boundary of the lowest class.

5.2 Inter-Quartile Range

For a set of 𝑁 numbers, 𝑥1 , 𝑥2 , …, 𝑥𝑁 , arranged in increasing order of magnitude, the lower
1 3 1 3
quartile and the upper quartile are defined as the (𝑁 + 1)th and (𝑁 + 1)th values (or the 𝑁 and 𝑁
4 4 4 4
values when the number of data items, 𝑁, is large) respectively.

5.3 Mean Deviation

Theorem. The sum of the deviations of a set of variates from their mean is equal to zero.
Although this expression from above theorem is of no value in measuring the dispersion, it
furnishes a useful device for checking the accuracy of a calculated mean. Since for purpose of describing
the dispersion, it is immaterial whether a variate is at certain distance above or below the mean, the sign
of the deviation can be ignored.
For a set of 𝑁 numbers, 𝑥1 , 𝑥2 , …, 𝑥𝑁 , whose mean is 𝑥̅ , the mean deviation is defined as
∑𝑁 𝑖=1|𝑥𝑖 − 𝑥̅ |
Mean deviation =
𝑁
If 𝑥1 , 𝑥2 , …, 𝑥𝑘 , occur with frequencies 𝑓1 , 𝑓2 , …, 𝑓𝑘 respectively, the mean deviation can be
written as
∑𝑘𝑖=1 𝑓𝑖 |𝑥𝑖 − 𝑥̅ |
Mean deviation =
𝑁
𝑘
where N = ∑𝑖=1 𝑓𝑖

5.4 The Variance and Standard Deviation

A good measure of spread will:
(i) Take every data value into account;
(ii) Weight data values according to frequency.
The standard deviation fits those criteria and overcomes the problems of both range and inter-
quartile range.
The average of the squared deviation from the mean called the variance, is used as a measure of
dispersion.
For a set of 𝑁 numbers, 𝑥1 , 𝑥2 , …, 𝑥𝑁 , whose mean is 𝑥̅ , the variance, denoted by 𝜎 2 (read sigma
square),
∑𝑁𝑖=1(𝑥𝑖 − 𝑥̅ )
2
𝜎2 =
𝑁
The variance is expressed in units which are the squares of the original units. For many purpose,
it is desirable that a measure of dispersion may be expressed in the same units as the original variates

6
and their mean. Such a measure of dispersion is the standard deviation, which is obtained by taking the
square root of the variance.
The standard deviation is then the square root of the average (mean) of the squared deviation
from the mean.
For a set of 𝑁 numbers 𝑥1 , 𝑥2 , …, 𝑥𝑁 , whose mean is 𝑥̅ , the standard deviation, denoted by S.D
or σ, is defined as

∑𝑁
𝑖=1(𝑥𝑖 − 𝑥̅ )
2
S.D = σ = √
𝑁
If 𝑥1 , 𝑥2 , …, 𝑥𝑘 , occur with frequencies 𝑓1 , 𝑓2 , …, 𝑓𝑘 respectively, as grouped data, the standard
deviation can be written as

∑𝑘𝑖=1 𝑓𝑖 (𝑥𝑖 − 𝑥̅ )2
S.D = σ = √
𝑁
where N = ∑𝑘𝑖=1 𝑓𝑖
If in a frequency table, the class marks are 𝑥1 , 𝑥2 , …, 𝑥𝑘 , and the respective frequencies are 𝑓1 ,
𝑓2 , …, 𝑓𝑘 , and let 𝑥0 represent a class mark, to be used as assumed mean, then the standard deviation is
defined as
2
∑ 𝑓𝑑 2 ∑ 𝑓𝑑
S.D = √ ( )
∑𝑓 ∑𝑓

If 𝑑𝑠′ have a common factor 𝑢 (i.e 𝑑 ′ = 𝑑⁄𝑢)

∑ 𝑓𝑑′2 ∑ 𝑓𝑑′ 2
S.D = 𝑢 √ ∑𝑓
( ∑𝑓
) .

6. Correlation Analysis
6.1 Introduction
In practice, we may come across with lot of situations which need statistical analysis of either one
or more variables. The data concerned with one variable only is called univariate data. For Example: Price,
income, demand, production, weight, height marks etc are concerned with one variable only. The analysis
of such data is called univariate analysis.
The data concerned with two variables are called bivariate data. For example: rainfall and
agriculture; income and consumption; price and demand; height and weight etc. The analysis of these
two sets of data is called bivariate analysis.
The date concerned with three or more variables are called multivariate date. For example:
agricultural production is influenced by rainfall, quality of soil, fertilizer etc.

6.2 Definition
The statistical technique which can be used to study the relationship between two or more
variables is called correlation analysis.
Two or more variables are said to be correlated if the change in one variable results in a
corresponding change in the other variable.

7
6.3 Methods of measuring correlation
Scatter Diagrams
The kind of distribution which gives this consists of a set of pairs of values called a bivariate
distribution. We can check the relationship between two variables by putting the two variables along the
two axes and plotting points from the table on the same graph. This is called a scatter diagram.

20 20 20

10 10 10

- 20 - 10 0 10 20 - 20 - 10 0 10 20 - 20 - 10 0 10 20

- 10 - 10 - 10

- 20 - 20 - 20

Positive Correlation Negative Correlation No Correlation

7. Regression Analysis
Correlation analysis analyses whether two variables are correlated or not. After having
established the fact that two variables are closely related, we may be interested in estimating the value
of one variable, given the value of another. Hence, regression analysis means to analyse the average
relationship between two variables and thereby provides a mechanism for estimation or prediction or
forecasting.
“Regression analysis is an attempt to establish the nature of the relationship between variables-
that is to study the functional relationship between the variables and thereby provides a mechanism for
prediction or forecasting”.
It is clear from the above definitions that Regression Analysis is a statistical device with
the help of which we are able to estimate the unknown values of one variable from known values
of another variable. The variable which is used to predict the another variable, is called
independent variable (explanatory variable) and, the variable we are trying to predict is called
dependent variable (explained variable).

7.1 Types of Regression

There are two types of regression. They are linear and multiple regression.

7.1.1 Linear Regression

It is a type of regression which uses one independent variable to explain and/or predict the
dependent variable.
The analysis used in regression is called simple linear regression analysis. It is called
simple because there is only one predictor (independent variable). It is called linear because, it is
assumed that there is linear relationship between independent variable and dependent variable.

8
7.1.2 Multiple Regression
It is a type of regression which uses two or more independent variables to explain and/or predict
the dependent variable.

7.2 Least Square Method of computing Regression Equation

The method of least square is an objective method of determining the best relationship between
the two variables constituting a bivariate data. To find out best relationship means to determine the
values of the constants involved in the functional relationship between the two variables. This can be
done by the principle of least squares:
The principle of least squares says that the sum of the squares of the deviations between the observed
values and estimated values should be the least. In other words, ∑(𝑦 − 𝑦𝑐 )2 will be the minimum.

With a little algebra and differential calculators we can develop some equations (2 equations in
case of a linear relationship) called normal equations. By solving these normal equations, we can find out
the best values of the constants.

7.2.1 Regression Equation of Y on X:

The dependent variable is denoted by Y and the independent variable is denoted by X.
𝑦 = 𝑎 + 𝑏𝑥
The normal equations to compute ‘𝑎’ and ‘𝑏’ are: -
∑ 𝑦 = 𝑁𝑎 + 𝑏 ∑ 𝑥
∑ 𝑥𝑦 = 𝑎 ∑ 𝑥 + 𝑏∑𝑥 2 .

7.2.2 Regression Equation of X on Y:

The dependent variable is denoted by X and the independent variable is denoted by Y.
𝑥 = 𝑎 + 𝑏𝑦
The normal equations to compute ‘𝑎’ and ‘𝑏’ are: -
∑ 𝑥 = 𝑁𝑎 + 𝑏 ∑ 𝑦
∑ 𝑥𝑦 = 𝑎 ∑ 𝑦 + 𝑏∑𝑦 2 .

8. Time Series Analysis

Analysis of time series helps us to know the effect of factors which are responsible for changes.

9
8.1 Moving Average
In Statistics, a moving average (rolling average or running average) is a calculation to analyze
data points by creating a series of averages of different subsets of the full data set. It is also called a
moving mean or rolling mean and is a type of finite impulse response filter.
Given a series of numbers and a fixed subset size, the first element of the moving average is
obtained by taking the average of the initial fixed subset of the number series. Then the subset is
modified by “shifting forward”, that is, excluding the first number of the series and including the next
value in the subset.
The seasonal variations
are calculated by the model:
If 𝑆1 = any individual stock level
and 𝑥̅𝑖 is any individual average
then
𝑥1 = 1⁄2 (𝑆1 + 𝑆2 );
̅̅̅
𝑥2 = 1⁄2 (𝑥
̅̅̅ ̅̅̅1 + 𝑆3 );
𝑥3 = 1⁄2 (𝑥
̅̅̅ ̅̅̅2 + 𝑆4 ); …
and so on.
A moving average is commonly used with time series data to smooth out short-term fluctuations
and highlight longer-term trends or cycles. The threshold between short-term and long-term depends on
the application, and the parameters of the moving average will be set accordingly.

8.2 Exponential Smoothing

Exponential smoothing is a rule of thumb technique for smoothing time series data using the
exponential window function. Whereas in the simple moving average the past observations are weighted
equally, exponential functions are used to assign exponentially decreasing weights over time. It is an
easily learned and easily applied procedure for making some determination based on prior assumptions
by the user, such as seasonality. Exponential smoothing is often used for analysis of time-series data.

8.3 Trend
One very valuable tool to our user is a trend analysis and we may well be asked to produce the
analysis of data which allow the necessary graph to be generated.
Time series graphs can show up “seasonal’ variations – where the values of the variable tend to
peak or trough at fairly regular intervals.
We can suppress these seasonal variations with a suitable moving average.
We may now plot the data on a graph (against the time to which they relate) and since the
‘average’ may be assumed to be moving continuously, not in decrease steps, as are the stock figures, the
moving average should be shown as a continuous, smooth line (curve).
Finally, we may attempt to draw a line of best fit (from the moving average points), which is an
attempt to interpret the moving average fluctuations as overall trend.

10
9. Two-layered chart
9.1 Control Chart

also known as Shewhart charts (after Walter A. Shewhart) or process-behavior charts, in statistical
process control are tools used to determine if a manufacturing or business process is in a state of
statistical control.
Purpose: To determine whether a process should undergo a formal examination for quality-related
problems
[Also called: statistical process control.
The control chart is a graph used to study how a process changes over time. Data are plotted in time
order. A control chart always has a central line for the average, an upper line for the upper control limit
and a lower line for the lower control limit. These lines are determined from historical data. By comparing
current data to these lines, you can draw conclusions about whether the process variation is consistent
(in control) or is unpredictable (out of control, affected by special causes of variation).
Control charts for variable data are used in pairs. The top chart monitors the average, or the centering of
the distribution of data from the process. The bottom chart monitors the range, or the width of the
distribution. If your data were shots in target practice, the average is where the shots are clustering, and
the range is how tightly they are clustered. Control charts for attribute data are used singly.]

9.2 Gantt Chart

A Gantt chart is a type of bar chart, developed by
Henry Gantt in the 1910s, that illustrates a project
schedule. Gantt charts illustrate the start and
finish dates of the terminal elements and summary
elements of a project. Terminal elements and
summary elements comprise the work breakdown
structure of the project.
A Gantt chart showing three kinds of schedule dependencies and percent complete indications.

9.3 Pareto Chart

A Pareto chart, named after Vilfredo Pareto, is a
type of chart that contains both bars and a line
graph, where individual values are represented in
descending order by bars, and the cumulative total is
represented by the line.

11
Purpose: To assess the most frequently occurring defects by category†

9.4 Radar Chart

A radar chart is a graphical method of displaying multivariate data in the form of a two-dimensional chart
of three or more quantitative variables represented on axes starting from the same point. The relative
position and angle of the axes is typically uninformative.
The radar chart is also known as web chart, spider chart, star
chart, star plot, cobweb chart, irregular polygon, polar chart,
or kiviat diagram.
One application of radar charts is the control of quality
improvement to display the performance metrics of any
ongoing program.
They are also used in sports to chart players' strengths and
weaknesses, where they are usually called spider charts.

9.5 Cause-and-effect diagram

Ishikawa diagrams (also called fishbone
diagrams, herringbone diagrams, cause-
and-effect diagrams, or Fishikawa) are
causal diagrams created by Kaoru
Ishikawa that show the causes of a
specific event.
A cause and effect diagram examines
why something happened or might
happen by organizing potential causes
into smaller categories. It can also be
useful for showing relationships between contributing factors. One of the Seven Basic Tools of Quality, it
is often referred to as a fishbone diagram or Ishikawa diagram.
One of the reasons cause & effect diagrams are also called fishbone diagrams is because the completed
diagram ends up looking like a fish's skeleton with the fish head to the right of the diagram and the bones
branching off behind it to the left.

10. Probability Distribution (Theoretical Distribution)

Probability distribution can be defined as a distribution obtained for a random variable on the
basis of a mathematical model, on the basis of probability law.

10.1 Random Variable

Random variable is a variable who value is determined by the outcome of a random experiment.
Random variable is also called chance variable or stochastic variable.

12
 A random variable 𝑋 can be discrete or continuous. If 𝑋 can take only finite or countably infinite
set of values, it is termed as a discrete random variable. On the other hand, if 𝑋 can take an uncountable
set of infinite values, it is called a continuous random variable.
The distribution o f a discrete random variable is called the Discrete Probability Distribution and
the corresponding probability function 𝑝(𝑋) is called a Probability Mass Function. In order that any
discrete function 𝑝(𝑋) may serve as probability function of a discrete random variable 𝑋, the following
conditions must be satisfied:
(i) 𝑝(𝑋𝑖 ) ≥ 0, ∀ 𝑖 = 1,2, … , 𝑛 and
(ii) ∑𝑛𝑖=1 𝑝(𝑋𝑖 ) = 1.

In a similar way, the distribution of a continuous random variable is called a Continuous

Probability Distribution and the corresponding probability function 𝑝(𝑋) is called a Probability Density
Function. The conditions for any function of a continuous variable to serve as a probability density
function are:
(i) 𝑝(𝑋) ≥ 0, ∀ real values of 𝑋, and
∞
(ii) ∫−∞ 𝑝(𝑋)𝑑𝑥 = 1.

10.2 Mean and Variance of a Random Variable

Mean: If 𝑋 is a discrete random variable which can take values 𝑋1 , 𝑋2 , … , 𝑋𝑛 , with respective
probabilities as 𝑝(𝑋1 ), 𝑝(𝑋2 ), … , 𝑝(𝑋𝑛 ), then its mean, also known as the Mathematical Expectation or
Expected Value of 𝑋, is give by:
E(𝑋) = 𝑋1 𝑝(𝑋1 ) + 𝑋2 𝑝(𝑋2 ) + ⋯ + 𝑋𝑛 𝑝(𝑋𝑛 ) = ∑𝑛𝑖=1 𝑋𝑖 𝑝(𝑋𝑖 ).
The mean of a random variable or its probability distribution is often denoted by 𝜇, i.e., E(𝑋) = 𝜇.
Remarks: The mean of a frequency distribution can be written as
𝑓1 𝑓2 𝑓
𝑋1 ∙ + 𝑋2 ∙ + ⋯ + 𝑋𝑛 ∙ 𝑛 , which is identical to the expression for expected value.
𝑁 𝑁 𝑁

Variance: The concept of variance of random variable or its probability distribution is also similar to the
concept of the variance of a frequency distribution.
The variance of a frequency distribution is given by
1 𝑓
𝜎2 = ∑ 𝑓𝑖 (𝑋𝑖 − 𝑋̅)2 = ∑(𝑋𝑖 − 𝑋̅)2 ∙ 𝑖 = Mean of (𝑋𝑖 − 𝑋̅)2 values.
𝑁 𝑁
The expression for variance of a probability distribution with mean 𝜇 can be written in a similar way, as
given below:
𝜎 2 = 𝐸(𝑋 − 𝜇)2 = ∑𝑛𝑖=1(𝑋𝑖 − 𝜇)2 𝑝(𝑋𝑖 ), where 𝑋 is a discrete random variable.
Remarks: If 𝑋 is a continuous random variable with probability density function 𝑝(𝑋), then
∞
𝐸(𝑋) = ∫ 𝑋 ∙ 𝑝(𝑋)𝑑𝑋
−∞
∞
𝜎 2 = 𝐸(𝑋 − 𝜇)2 = ∫ (𝑋 − 𝜇)2 ∙ 𝑝(𝑋)𝑑𝑋
−∞

13
10.3 Classification of Probability Distributions

10.3.1 Discrete Probability Distributions

If the random variable of a probability distribution assumes specific values only, it is called
discrete probability distributions. Binomial distribution and Poisson distribution are discrete probability
distributions.

10.3.2 Continuous Probability Distributions

If the random variable of a probability distribution assumes any value in a given interval, then it is
called continuous probability distributions. Normal distribution and Exponential distribution are
continuous probability distributions.

10.4 Binomial Distribution

We considered repeated and independent
trials of an experiment with two outcomes; we call
one of the outcomes success and the other outcome
failure. Let 𝑝 be the probability of success, so that
𝑞 = 1 − 𝑝 is the probability of failure.
The probability of exactly 𝑘 successes in 𝑛 repeated
trials is denoted by
𝑛
𝑏(𝑘; 𝑛, 𝑝) = ( ) 𝑝𝑘 𝑞 𝑛−𝑘 .
𝑘
𝑛
Here ( ) is the binomial coefficient.
𝑘
Observe that the probability of no successes is 𝑞 𝑛 , and therefore the probability of at least one success is
1 − 𝑞𝑛 .
Properties of the Binomial distribution follow:
Binomial distribution
Mean 𝜇 = 𝑛𝑝
Variance 𝜎 2 = 𝑛𝑝𝑞
Standard deviation 𝜎 = √𝑛𝑝𝑞

14
10.5 Poisson Distribution
The Poisson distribution is defined as follows:
𝜆𝑘 𝑒 −𝜆
𝑝(𝑘; 𝜆) = , 𝑘 = 0, 1, 2, …
𝑘!
where 𝜆 > 0 is some constant. It is a discrete
probability distribution that expresses the
probability of a given number of events occurring
in a fixed interval of time or space if these events
occur with a known constant rate and
independently of the time since the last event.
This countably infinite distribution appears in
many natural phenomena, such as the number of patients arriving in an emergency room between
10 and 11 pm, the number of telephone calls per minute at some switchboard, the number of misprints
per page in a large text, and the number of 𝛼 particles emitted by a radioactive substance.
Properties of the Poisson distribution follow:
Poisson distribution
Mean 𝜇=𝜆
Variance 𝜎2 = 𝜆
Standard deviation 𝜎 = √𝜆

10.6 Geometric Distribution

We considered repeated and independent
trials of an experiment with two outcomes; we call
one of the outcomes success and the other
outcome failure. Let 𝑝 be the probability of
success, so that 𝑞 = 1 − 𝑝 is the probability of
failure.
The probability that the first success occurs on
the nth trial is denoted by
𝑃(𝑋 = 𝑛) = (1 − 𝑝)𝑛−1 𝑝.
Properties of the Geometric distribution follow:
Geometric distribution
1
Mean 𝜇=
𝑝
(1 − 𝑝)
Variance 𝜎2 =
𝑝2
√(1 − 𝑝)
Standard deviation 𝜎=
𝑝

15
10.7 Normal Distribution
The normal (or: Gaussian)
distrib1ution or curve is defined as
follows:
1 𝑥−𝜇 2
1 − ( )
𝑓(𝑥) = 𝑒 2 𝜎
𝜎√2𝜋
Where 𝜇 and 𝜎 > 0 are arbitrary
constants. This function is certainly one of
the most important examples of a
continuous probability distribution.
Properties of the Normal distribution follow:
Normal distribution
Mean 𝜇
Variance 𝜎2
Standard deviation 𝜎
We denote the above normal distribution with mean 𝜇 and variance 𝜎2 by
𝑁(𝜇, 𝜎 2 ).
If we make the substitution 𝑡 = (𝑥 − 𝜇)⁄𝜎 in the above formula for 𝑁(𝜇, 𝜎 2 ) we obtain the standard
normal distribution or curve
1 1⁄ 𝑡 2
∅(𝑡) = 𝑒− 2
√2𝜋
Which has mean 𝜇 = 0 and variance 𝜎2 = 1.

(a) 68.27 percent of the variates are included between 𝜇 − 𝜎 and 𝜇 + 𝜎.

(b) 95.45 percent of the variates are included between 𝜇 − 2𝜎 and 𝜇 + 2𝜎.
(c) 99.73 percent of the variates are included between 𝜇 − 3𝜎 and 𝜇 + 3𝜎.

16
10.8 Exponential Distribution
The exponential distribution (also
known as the negative exponential
distribution) is the probability distribution
that describes the time between events in a
Poisson point process, i.e., a process in
which events occur continuously and
independently at a constant average rate.
The probability density function (pdf) of an
exponential distribution is
−𝜆𝑥
𝑓(𝑥; 𝜆) = {𝜆𝑒 𝑥≥0,
0 𝑥<0.
Here 𝜆 > 0 is the parameter of the distribution,
ofetn called the rate parameter. The distribution is supported on the inteval [0, ∞).
Properties of the Exponential distribution follow:
Exponential distribution
1
Mean 𝜇=
𝜆
1
Variance 𝜎2 = 2
𝜆
1
Standard deviation 𝜎=
𝜆

17
11. Bayes rule
True Bayesians actually consider conditional probabilities as more basic than joint probabilities. It
is easy to define 𝑃(𝐴|𝐵) without reference to the joint probability 𝑃(𝐴, 𝐵). To see this note that we can
rearrange the conditional probability formula to get:
𝑃(𝐴|𝐵)𝑃(𝐵) = 𝑃(𝐴, 𝐵)
but by symmetry we can also get:
𝑃(𝐵|𝐴)𝑃(𝐴) = 𝑃(𝐴, 𝐵)
It follows that:
𝑃(𝐵|𝐴)𝑃(𝐴)
𝑃(𝐴|𝐵) =
𝑃(𝐵)
which is the so-called Bayes Rule.
It is common to think of Bayes rule in terms of updating our belief about a hypothesis 𝐴 in the light of
new evidence 𝐵. Specifically, our posterior belief 𝑃(𝐴|𝐵) is calculated by multiplying our prior belief 𝑃(𝐴)
by the likelihood 𝑃(𝐵|𝐴) that B will occur if 𝐴 is true.
The power of Bayes' rule is that in many situations where we want to compute 𝑃(𝐴|𝐵) it turns out that it
is difficult to do so directly, yet we might have direct information about 𝑃(𝐵|𝐴). Bayes' rule enables us to
compute 𝑃(𝐴|𝐵) in terms of 𝑃(𝐵|𝐴).

For example, suppose that we are interested in diagnosing cancer in patients who visit a chest clinic.
Let 𝐴 represent the event "Person has cancer".
Let 𝐵 represent the event "Person is a smoker".
We know the probability of the prior event 𝑃(𝐴) = 0.1 on the basis of past data (10% of patients
entering the clinic turn out to have cancer). We want to compute the probability of the posterior event
𝑃(𝐴|𝐵). It is difficult to find this out directly. However, we are likely to know 𝑃(𝐵) by considering the
percentage of patients who smoke – suppose 𝑃(𝐵) = 0.5. We are also likely to know 𝑃(𝐵|𝐴) by checking
from our record the proportion of smokers among those diagnosed. Suppose 𝑃(𝐵|𝐴) = 0.8.
We can now use Bayes' rule to compute:
0.8×0.1
𝑃(𝐴|𝐵) = = 0.16.
0.5
Thus, in the light of evidence that the person is a smoker we revise our prior probability from 0.1 to a
posterior probability of 0.16. This is a significance increase, but it is still unlikely that the person has
cancer.
The denominator 𝑃(𝐵) in the equation is a normalising constant which can be computed, for example,
by marginalisation whereby
𝑃(𝐵) = ∑𝑖 𝑃(𝐵, 𝐴𝑖 ) = ∑𝑖 𝑃(𝐵|𝐴𝑖 ) ∙ 𝑃(𝐴𝑖 ).
Hence we can state Bayes rule in another way as:
𝑃(𝐵|𝐴)∙𝑃(𝐴)
𝑃(𝐴|𝐵) = ∑ .
𝑖 𝑃(𝐵|𝐴𝑖 )∙𝑃(𝐴𝑖 )

18
12. Programming Techniques:
Programming techniques are also called operations research techniques. Programming techniques are
model building techniques used by decision makers in modern times.
Programming techniques involve:

12.1 Linear Programming Method

Linear programming technique is used in finding a solution to determine the optimum allocation of scarce
resources among competing demands. Resources typically include raw materials, manpower, machinery,
time, money and space. The technique is very powerful and found especially useful because of its
application to many different types of real business problems in areas like finance, production, sales and
distribution, personnel, marketing and many more areas of management. As its name implies, the linear
programming model consists of linear objectives and linear constraints, which means that the variables in
a model have a proportionate relationship. For example, an increase in manpower resource will result in
an increase in work output.

12.2 Queuing Theory:

Queuing theory deals with mathematical study of queues. It aims at minimizing cost of both servicing and
waiting.

12.3 Game Theory:

Game theory is used to determine the optimum strategy in a competitive situation.

12.4 Decision Theory:

This is concerned with making sound decisions under conditions of certainty, risk and uncertainty.

12.5 Inventory Theory:

Inventory theory helps for optimizing the inventory levels. It focuses on minimizing cost associated with
holding of inventories.

12.6 Network Programming:

It is a technique of planning, scheduling, controlling, monitoring and co-ordinating large and complex
projects comprising of a number of activities and events. It serves as an instrument in resource allocation
and adjustment of time and cost up to the optimum level. It includes CPM, PERT etc.

12.7 Simulation:
It is a technique of testing a model which resembles real life situations.

12.8 Replacement Theory:

It is concerned with the problems of replacement of machines, etc due to their deteriorating efficiency or
breakdown. It helps to determine the most economic replacement policy.

19
12.9 Non Linear Programming:
It is a programming technique which involves finding an optimum solution to a problem in which some or
all variables are non-linear.

12.10 Sequencing:
Sequencing tool is used to determine a sequence in which given jobs should be performed by minimizing
the total efforts.

12.11 Quadratic Programming:

Quadratic programming technique is designed to solve certain problems, the objective function of which
takes the form of a quadratic equation.

12.12 Branch and Bound Technique

It is a recently developed technique. This is designed to solve the combinational problems of decision
making where there are large numbers of feasible solutions. Problems of plant location, problems of
determining minimum cost of production etc. are examples of combinational problems.

13. Inventory Costing Method

The inventory means physical stocks of good which is kept in hand for smooth and efficient running of
future affairs of an organisation at the minimum costs of funds blocked in inventories. Inventory can be
defined as the stock of goods, commodities or other resources that are stored at any given period for
future production. In real, inventory control is a process itself, with the help of which, the demand of
items, scheduling, purchase receiving, inspection, storage and despatch are arranged in such a manner
that at minimum cost and in minimum time, the goods can be despatched to production department.
Inventory control makes use of available capital in a most effective way and ensures adequate supply of
goods for production.
Determining the cost of ending inventory must begin a general rule: Inventory should include all costs
that are “ordinary and necessary” to put the goods “in place” and “in condition” for their resale.
Once the unit cost of inventory is determined via the preceding rules of logic, specific costing methods
must be adopted. In other words, each unit of inventory will not have the exact same cost, and an
assumption must be implemented to maintain a systematic approach to assigning costs to units on hand
(and to units sold).
Inventory Costing methods are:

13.1 First-in First-out method (FIFO)

It assumes that the first purchased goods are also the ones that are sold first. Therefore, your
remaining stock would be valued at the most recently incurred costs. As a result, the costs listed
on your balance sheet should be quite close to their value in the current marketplace.

20
13.2 Last-in First-out method (LIFO)
LIFO is the opposite of FIFO and stands for ‘last in, first out.’ It’s currently the inventory method used by
Target. In this case, rather than assume you’re selling your first acquired products first, you assume
you’re selling your most recently (last) acquired products first.

13.3 Weighted-average method (Periodic average method)

The weighted-average method relies on average unit cost to calculate cost of units sold and ending
inventory. Average cost is determined by dividing the total cost of goods available for sale by total units
available for sale.

13.4 Moving average method

It is a method for inventory valuation or delivery cost calculation, by which the unit cost is calculated
every time inventory goods are accepted instead of calculating the cost at the inventory clearance of the
end of month or accounting period.
Under the moving average inventory method, the average cost of each inventory item in stock is re-
calculated after every inventory purchase. This method tends to yield inventory valuations and cost of
goods sold results that are in-between those derived under the first in, first out (FIFO) method and the
last in, first out (LIFO) method. This averaging approach is considered to yield a safe and conservative
approach to reporting financial results.

13.5 Acquisition cost method (Final purchase cost method)

The acquisition cost is usually computed on a first-in-first-out (FIFO) basis, last-in-first-out (LIFO) basis or
average cost basis. M3 can compute the acquisition value using all three inventory systems and indicates
the system which results in the lowest value.

21