Statistical Management

Student Name:
Student ID:
Contents
Introduction......................................................................................................................................3
LO1 Evaluate business and economic data/ information obtained from published sources...........3
P1 Evaluate the nature and process of business and economic data/information from a range of
different sources...........................................................................................................................3
P2 Evaluate data from a variety of sources using different methods of analysis........................6
P3 Analyze and evaluate qualitative and quantitative raw business data from a range of
examples using appropriate statistical methods...........................................................................8
P5 Using appropriate charts/tables communicate findings for a number of given variables....15
Conclusion.....................................................................................................................................18
Reference.......................................................................................................................................18
Introduction
The aim of this assignment is to understand how important management information is for an
organization. And also, how statistical methods can be used for enhancing a decision. Every
business organization should be aware of the statistical method and try to use it for their
advantage. In the assignment, we have discussed the topic in four different parts. We will
evaluate the business and economic data and information that can be found from different
sources. Later, we will discuss about statistical methods available for business organizations and
how to properly use it for business planning. And lastly, we will communicate findings using
appropriate charts and tables.

LO1 Evaluate business and economic data/ information obtained

from published sources
P1 Evaluate the nature and process of business and economic
data/information from a range of different sources

Figure 1 Statistics

Statistics is an important entity in the field of science and mathematics. It is a study of collecting,
organizing and analyzing data in a mathematical way from which the researcher can come to a
valid and evocative conclusion. It is also an inseparable part of data management. Statistics
methods can help turn data in to useful information by means of many systematic process and
formulas. Business organizations need useful information from the ocean of data. So, there is no
question and hesitation about the importance and usefulness of statistics.
Statistics is comprised of key characteristics mentioned below:

1. Statistics is the study aggregates of facts

Statistics has to work on the ocean of data and facts. This study is also known as ‘Big Data’.
Statistics considers all the data and facts to bring out the valid information.

2. Many causes can affect the result

Many factors can be present in a certain research topic. Statistical methods consider all the
factors included in the study. Not considering any of the effect can change the result of the study
dramatically.

3. Numeric expressions

Statistics is a part of mathematics. The number representations showcase the conclusion of the
research. The factors stated in the statistical paper should be countable or be in quantitative form.

4. Accurate methodology for estimation

The statement of the paper should be meaningful and targeted to fulfill a certain objective. The
correct estimation of statements helps the research to be accurate. The estimation may vary from
the structure of collecting data. For example, the area of a room can be measured in square
meters. But the small tiles cannot be measured in the same manner.

5. Systematic manner for data collection

The data collection method has to be done in a systematic and scientifically supported way.
Before the data collection, methods should be properly analyzed and the process needs to be
done under a professional.

6. Purpose has to defined at the beginning

Before the starting of collection of data, it is necessary to identify the purpose of the project from
right at the beginning. Data collection without any purpose is like a boat without any boatmen.
The collection of data won’t be fruitful if the purpose is not clear.

7. Factors should be correlated

Last but not least, the conclusion and the result found should be comparable to previous results
and information. So, the factors are correlated to each other. If statistics do not have factors or
results correlated to each other, it may lose its significance.

Statistical data has a lot of significance in the field of science. It helps to demonstrate the best
method of data collection in a research, statistical data helps for assuming correct analysis.
Behind every discoveries of science, statistical data has always played a vital factor. The same
thing goes for inventions. Statistical data helps to gain knowledge on a particular topic more
deeply.

To process the data for business and economics, we have to use statistical components and
several scale of measurement.

Statistics is comprised of two components: a. Theoretical Statistics b. Practical Statistics.

Theoretical statistics discusses the mathematical side of statistics. The mathematical side
includes probability theory, properties of estimators, central limit theorem etc. These theories
help to carry on a practical approach to analysis of data. For example: Categorical data analysis,
Functional data analysis. On the other hand, practical statistics is the study where the data is
analyzed and presented in an understandable way. Practical statistics defines the relations among
different variables and factors.

Scales of measurement are means by which variables are measured and quantified. There are
four scales of measurement: 1. Nominal 2. Ordinal 3. Interval 4. Ratio. Among these four scales,
Nominal and Ordinal are qualitative measuring scale, Interval and Ration scales are quantitative
measuring scale. Nominal scales include categories like gender, city code, ID no etc. Ordinal
scales measure the elements in a hierarchical order which includes class ranks, letter grades, rank
orders etc. There is no specific difference in the order. Interval scale has a difference in each
value. For example, temperature, number serial etc. Ratio scale on the other hand has a specific
numerical distance among each of the elements. Unlike other scale, ratio scale has an anchor
point.
P2 Evaluate data from a variety of sources using different methods of analysis
Data are collected by several methods and then processed into useful information. In the process,
many analytical methods are used. There are mainly two sources of data: Primary data and
Secondary data.

Figure 2 Data Sources of Statistical Data

Primary data sources include: questionnaires, survey, photograph collection etc. In this method,
data are collected directly from the respondents. Secondary data are the results of primary data
sources. For example, books, journals, online articles, newspaper etc.
 Figure 3 Tree chart of Data Analysis Procedure

There are two approaches od fata collection method: Qualitative and Quantitative. Deductive
approach is a part of quantitative method whereas Inductive approach is a part of qualitative
method. Deductive approach is mainly used for testing out a theory of statistics whilst inductive
approach is tied up with the generation of new theory.

Deductive approach develops a hypothesis in a research and the emphasis is based on a casual
matter. Deductive procedure is matched with quantitative strategy. Inductive approaches are
based on research questions that help the research study be narrow and easier for conduct.
Inductive approach also targets to analyze previous statistical data from a different perspective
and find a conclusion that can be related to that source. So, inductive approach is a part of
qualitative research. This strategy aims to develop a new theory based on the data and
information found.

There are two more statistical analysis approaches: Exploratory Analysis & Confirmatory
Analysis.
Exploratory Analysis: In the field of statistics, exploratory analysis is the approach that
summarizes the overall results and conclusions in a presentable way. In other words, it is a
method to show the audience beyond the formal modeling or the generated hypothesis. The
exploratory data analysis encourages the statisticians and mathematicians to explore every data
and information and from the existing data, developing a hypothesis and new field of research.
So, finally we can say that, exploratory analysis is a broad statistical study that investigates and
researches on data of previous publications and discovers anomalies, patterns, new hypothesis
presented by numerical plus graphical presentations.

Confirmatory Analysis: In easy words, confirmatory analysis refers to confirming a statistical

point. In this analysis process, the analyst has to evaluate the evidence with means of several
statistical tools. The analyst can use tools like significance, confidence, interference etc.
Confirmatory analysis is comprised of analyzing hypotheses, estimating variables precisely,
correlation and regression analysis, variance etc.

Both of the analysis process can be done by statistical methods like descriptive statistics and
inferential statistics.

Figure 4 Descriptive and Inferential Statistics

Descriptive statistics: This statistical method is used for summarizing and describing statistical
data. The presentation has to be done in a meaningful manner. For example: 50 students have
gotten their marks in math subject. Finding the central tendency of the numbers can give the
analyst a base point.

Inferential statistics: Inferential statistics is the method where data are taken from samples and
general estimations are made about the population. For example: Thousands of shopper’s
markets at Walmart. From that population the analyst can ask sample of 100 people what they
think about the shopping mall and come to a general concept of the popularity.

P3 Analyze and evaluate qualitative and quantitative raw business data from
a range of examples using appropriate statistical methods
Business data can be classified into qualitative data and quantitative data. These two methods are
important for conducting any research and interpreting data. These methods have the same
objective in a research but can be used independently or relatively.

In the following we will see the differences between the Qualitative data and the quantitative
data.

Subject Qualitative Analysis Quantitative Analysis

Definition Qualitative data analysis is a study Quantitative data analysis is
of objects based on the research. based on data that are
measurable.
Data Collection Data is collected in a unstructured Data is collected in a large,
way and cannot be numerically structured way. The
represented. conclusions can be numerically
expressed.
Research The methodology is exploratory. The research methodology is
Methodology conclusive.
Findings The findings of the research are The findings of the research
based on the subject of research. The can be applied to general
conclusion cannot be applied to population.
general population.
 Method of Data Data is collected by conducting Data is collected by
Collection survey, taking interviews, one on measurements, experiments
one questions. and by survey.
Purpose Wider understanding on the research The purpose is to analyze a
topic. hypothesis and set predictions
for future.

Descriptive statistics

This statistical method is used for summarizing and describing statistical data. The presentation
has to be done in a meaningful manner. For example: 50 students have gotten their marks in
math subject. Finding the central tendency of the numbers can give the analyst a base point.
Measures of central tendency, measures of variability are parts of descriptive statistics.

Mean refers to the average of a data set. All the elements of data set are added and then divided
by the number of data sets. If the elements of data set are arranged from lowest to highest, the
middle value is the median. The mode refers to the element that mostly occur in a data set.

Descriptive statistics are usable in businesses in many ways. With this method business
organizations can determine the average earnings of the employees by simply determining the
mean. Also, can be used for other small details. With mode method, they can find when customer
arrives the most and how they can decrease queue times.

Inferential statistics

Inferential statistics is the method where data are taken from samples and general estimations are
made about the population. For example: Thousands of shopper’s markets at Walmart. From that
population the analyst can ask sample of 50 people what they think about the shopping mall and
come to a general concept of the popularity. In inferential statistics, population and sample have
a lot of significance. The population data set contains all the elements in a data set whereas
sample is only a part of it. Every part of population data set, big or small, can be regarded as
sample data set. So, sample data set is a small entity whereas population data set is a large one.
P4 Apply a range of statistical methods used in business planning for quality, inventory and
capacity management

Quality, inventory and capacity management is three important considerations of an

organization. Inventory is a key asset for an organization to maintain the supply according to
demand. Companies can tackle any kind of problems if they have proper inventory management
process. For example, an organization can face the problem of transportation cost and with
proper inventory they can reduce this cost. Capacity management is related to inventory
management. Capacity management refers to the process that demonstrates the capacity of
production an organization needs to meet their product demands in the market. Design capacity
is another part of this management where the organization can determine the amount of
production they can make in a certain period of time.

Methods to plan quality, inventory and capacity management

Figure 5 Pareto Chart

 Figure 6 Process Flow Diagram

Pareto Chart: Pareto chart is a combination of bars and lines. The bars represent the individual
values whereas the line represents the cumulative value. The visual presentation is same as
histogram. It is also known as Pareto Diagram.

Process Flow Diagram: Process flow diagram is used for correlating different elements. It is
mostly used in manufacturing plant. From the figure we see how it relates among the different
equipment.
Check Sheet: Check sheet is also known as tally sheet. It is used in a collection of data and is
recorded in real time. The data in the sheet can be both qualitative and quantitative.

Control Chart: Control chart is a type of graph that records measurement changes over a certain
period of time. The central line represents the average of the measurement. So, from the dots in
the graph, one can estimate if it is lower control limit or higher.
Run Chart: Run chart is also a representation of graph that is built on measurements and data
over long period of time. It is the best process to find the trend or the pattern of the whole
research.

Statistical Process Control

Statistical process control is also known as SPC. It is a method used by organizations for quality
management. In this process the analyst has to use statistical procedure to observe and manage a
process. Organizations use this process to maximize their production with the least amount of
waste and keep up with the demand curve. SPC is helpful for reducing the variation and to
estimate how the process may change in future. Decreasing variation can be helpful for
improving quality.

To do SPC, we are going to use case 1.

8.00 am 10.00 am 12.00 am 2.00 pm 4.00 pm 6.00 pm 8.00 pm

37 142 66 94 84 75 40
33 144 61 96 88 70 42
35 145 60 99 66 72 46

Normal distribution is a graphical representation that distributes many random data into a
symmetrical ball shaped graph. For the case 1, the normal distribution graph is as below:
 Normal Distribution of Case 1
0.01

0.01

0.01

0.01

0.01

0
30 40 50 60 70 80 90 100 110 120 130 140 150

Control limit is also known as the boundary of the distribution model. In the graph we see that
the mean is 75.9 = 76 (almost) and the standard deviation is 34.88 = 35 (almost). The empirical
rule of normal distribution states that 68% of total distribution will fall within 1 standard
deviation of mean 76. 95% of the observations will fall within the 2-standard deviation of the
mean. And lastly, 99.7% of the observations will fall under 3-standard deviations of mean. In the
case, lower limit is 33 and higher limit is 145.

P5 Using appropriate charts/tables communicate findings for a number of

given variables
The objective of statistics is to show case the findings to the audience in an understandable way.
So, proper use of charts and tables are necessary for the communication. We will use the
following two cases to show how raw data is processed and analyzed and communicate findings
appropriately.

Case 2

Average hotel room rates for 20 cities

City Average Rate/ Flight

London 245
Edinburgh 146
Manchester 167
Birmingham 177
Glasgow 166
Liverpool 126
Bristol 125
Glasgow 123
Leeds 120
Nottingham 144
 Newcastle 173
Brighton 192
Cardiff 160
Sheffield 139
Cambridge 134
Southampton 167
Belfast 162
Leicester 145
York 155

The mean of the rate is the summation of the rates divided by the number of hotels.

Total average rate is= 2966 and there are total of 19 hotels.

The mean is (2966/19) = 156.

For finding the median, we have to arrange the rates from lowest to highest.

120 123 125 126 134 139 144 145 146 155 160 162 166 167 167 173 177 192 245

The median is the 10th number, the middle of the serial= 155

Also, we see that 167 has been occurred the most amount of time. So, the mode is 167.

First Quartile:

To find the first quartile, we can use the following formula

(1/4) * (n + 1); where n is the number of observations

= (1/4) * (19+1)

= 5th term

= 134

1st quartile is the 5th term of the series. Hence, 134.

Third Quartile

To find the third quartile, we can use the following formula

(3/4) * (n + 1); where n is the number of observations

= (3/4) * 20

= 15th term = 167

167 is the third quartile of the series.

Case 3:

A manger wants to see if geographical region is associated with ownership of a

Macintosh computer. The manager surveys 100 people and the data break down as
follows:

Mac No Mac Row Total

North East 12 14 26
South West 21 18 39
Mid-West 17 18 35
Total 50 50 100

We will demonstrate chi-square on this problem. First, we need to find the expected cell
frequency by the following formula:

Expected Cell Frequency= (Row total * Column Total)/ Grand total

North east= (26*50) / 100= 13

South west= (39*50) / 100= 19.5

Mid-West= (35*50) / 100= 17.5

The DF for the tests is (Row-1) * (Columns- 1) = (3-1) * (2-1) = 2

Alpha is 0.05

Chi Square with 2 DF pf alpha 0.05 is 5.99.

We have six cells in the problem.

Cell 1= (12-13) / 13= - 0.077

Cell 2= (14-13) / 13= 0.077

Cell 3= (21-19.5) / 195.5= 0.115

Cell 4= (18-19) / 19.5= 0.115

Cell 5= (17-17.5) / 17.5= 0.014

Cell 6= (18- 17.5) / 17.5= 0.014

The summation of the results is= 0.412 which is our chi square of the statistic.

The two variables are not related. They function independently.

Conclusion
In the assignment, we have seen how statistics play a vital role for every business analyst. It is
also a key part of statistical management. The key characteristics are important for every
statistician to know. With the help of statistics and by applying several methods, the researcher
can find how the organization can make the most production with the least amount of waste.
Also, the business organization can figure out the relations among the factors and how effect on
one factor can instantly effect on the other making the scenario tough for processing. With the
help of statistics, the admin panel can avoid this situation. Business organizations can identify
the best amount of supply they need to carry for production and meeting with supply. Overall the
success of a business organization depends on how the application of statistics is made.

Reference
Blanco-Fernández, A. and Winker, P., 2016. Data generation processes and statistical
management of interval data. AStA Advances in Statistical Analysis, 100(4), pp.475-494.

Blanco-Fernández, A. and Winker, P., 2016. Data generation processes and statistical
management of interval data. AStA Advances in Statistical Analysis, 100(4), pp.475-494.
Bongiorno, C., Gurtner, G., Lillo, F., Mantegna, R.N. and Miccichè, S., 2017. Statistical
characterization of deviations from planned flight trajectories in air traffic management. Journal
of Air Transport Management, 58, pp.152-163.

Jackson, F.L., Fryer, R.J., Hannah, D.M., Millar, C.P. and Malcolm, I.A., 2018. A spatio-
temporal statistical model of maximum daily river temperatures to inform the management of
Scotland's Atlantic salmon rivers under climate change. Science of the Total Environment, 612,
pp.1543-1558.

Karr, A.F., Sanil, A.P. and Banks, D.L., 2006. Data quality: A statistical perspective. Statistical
Methodology, 3(2), pp.137-173.

Kwak, S.K. and Kim, J.H., 2017. Statistical data preparation: management of missing values and
outliers. Korean journal of anesthesiology, 70(4), p.407.

Way, S., Morales, B., Tinsley, H. and Baumgartner, M., Qcash Financial LLC, 2019. Statistical
risk management system for lending decisions. U.S. Patent Application 15/861,659.

Wooff, D.A., Anderson, J.M. and Jamalzadeh, A., 2016. Statistical Management of Pay-Per-
Click Processes for Search Engines. In UK Success Stories in Industrial Mathematics (pp. 297-
303). Springer, Cham.