Ways Multivariate Techniques Contribute to Big D Incorporated

This report provides an analysis of multivariate techniques and their applications for Big D Incorporated, focusing on how these statistical methods can aid in business decision-making. The report begins by defining multivariate analysis and its importance in understanding the relationships between multiple variables within a dataset. It explores various techniques such as multivariate analysis of variance (MANOVA), cluster analysis, multidimensional scaling, factor analysis, and multiple regression analysis, highlighting their specific uses and benefits for Big D Incorporated. The report assesses the suitability of each technique for different types of business questions, such as exploratory and decisional questions, and recommends cluster analysis as the most appropriate multivariate technique for the company's needs, particularly for market research and customer profiling. It also provides real-world examples of how other companies utilize multivariate analysis and concludes by emphasizing the diverse utility of multivariate analysis in providing a design for inverse design, capability, analyzing alternatives and concepts, it also enables identifying critical design-drivers and correlations through various hierarchical levels.

Running Head: MULTIVARIATE TECHNIQUES APPLICATIONS
WAYS IN WHICH MULTIVARIATE TECHNIQUES WILL CONTRIBUTE TO
BIG-D INCORPORATED

MULTIVARIATE TECHNIQUES APPLICATIONS
Statistical tools and various techniques are used across multiple corporations to resolve
their daily challenges (Hudaverdi, 2012). Statistical analysis is applied across most companies
now for the purpose of serving a various purpose and resolve client related queries. In the current
report scope, the various purposes of multivariate analysis are analyzed for Big D Incorporated.
Along with the analysis of various multivariate techniques, the chosen multivariate technique in
comparison to the other methods is analyzed. The importance of the technique is told to the
Board of Directors, which can contribute to the overall process of decision making.
Big D sporting goods company when faced with an investment dilemma, while the
expansion of the business operations conducted varied statistical analysis. In order to carry out
the analysis of ways the multivariate techniques are used to serve the clients in the best possible
way, one needs to have a proper understanding of the topic. Multivariate analysis makes use of
statistical principles used to identify the relationship where variables are two or more (Haware,
Tho & Bauer-Brandl, 2009). These techniques are used to create a real situation where every
product, situation or any decision is affected by multiple factors. They are used to study data sets
and identify whether the variables are dependent on each other. This is a very effective test of
significance which entails a more accurate picture after analyzing multiple variables instead of
any one variable. This type of technique is commonly applied for research and development,
consumer research, quality control, market research, process control, quality assurance, and
optimization. Additionally, multivariate techniques are also effective in identifying potential
problems. The new client at Big D Incorporated which is sporting company for whom; they are
required to identify the best multivariate technique.
Big D Incorporated can utilize more than 20 multivariate techniques, however, the best
possible method varies between different companies and also owing to the category of data
2

MULTIVARIATE TECHNIQUES APPLICATIONS
researched. Some of the different types of multivariate techniques that can identify various
dependent and interdependent responses are - multivariate analysis of variance (MANOVA),
multidimensional scaling, cluster analysis, multiple regression analysis, and factor analysis.
Multivariate analysis of variance identifies how one or more variable can influence a
group by calculating statistical averages. For example, in pharmaceutical companies, this type of
analysis is used to determine whether a drug will work or not, whether the severity of side
effects, average life expectancy and perceived pain of an experimental group on whom the dug is
administered would differ from that of the established product (Jackson, Riley & White, 2011).
Big D Incorporated can use this analysis to identify the type of customers who buys outdoor
sports goods most based on their current demographics of customers.
Cluster analysis helps in grouping similar variables in corresponding categories, thereby
generating clusters and segments. It cannot identify a dependent or independent variables; rather
they provide a structure within data in the absence of any interpretation or explanation. Taken,
for example, insurance companies use this type of data analysis to identify the reason behind the
rise in insurance claims, if a particular region experiences a high number of claims. Similarly,
big D Incorporated can utilize this type of analysis to develop market segment that can help their
client in positioning their products in a better way and also put them in a competitive position
over their competitors. Besides, this technique can also help them in exploring new markets such
as Lincoln Park neighborhood in Chicago and develop products that are useful and relevant to
specific clusters.
Multidimensional scaling is used to analyze the similarities or differences between two
sets of objects through a visual representation of distance. In multidimensional scaling plotting
on a graph, objects which have more similarities are depicted with a shorter distance and in
3

MULTIVARIATE TECHNIQUES APPLICATIONS
objects with little similarities are shown to have larger distance. In this, the dataset is shown
using their dimensionality. Dimensionality is a dataset having various attributes. The marketing
team of any business uses this analysis to visualize market segmentations and assess the
effectiveness of various advertising activities. Big D Incorporated can use this analysis to help
their client develop new products based on the unexplored market segments which have been left
by their competitors. Datasets in multidimensional scaling are often referred to as high
dimensional and low dimensional data. In high dimensional data, there are a number of
dimensions involved, calculations are difficult to conduct. The low dimensional dataset is just
the reverse with lesser dimensions and easier calculations.
Factor analysis checks all the relevant data and the individual variables and identifies
whether the variables are related to any underlying factors. This relationship is expressed by the
factor loading. One example where factor analysis could be used is the sports industry. A study
would help to reveal different variables that are considered while purchasing an automobile such
as the variety of products, prices, and many more variables. This analysis can further help to
identify the factors that actually determine the purchase. Once these factors are identified, the
sellers can plan their marketing strategies accordingly. Similarly, Big D Incorporated can utilize
this method for their new client by considering several variables such as school teams in the
neighborhood, different products with school logos, and popular sports in Chicago, and so on.
Multiple regression analysis encompasses a method for predicting the values of a variable
on the known value of two or more variables. The variable’s value that is to be estimated is
called the dependent variable, and the variables whose value are already known and are used for
estimation are called independent variables. This type of analysis has one dependent alongwith
two or more independent variables.
4

MULTIVARIATE TECHNIQUES APPLICATIONS
Independent variables comprises of factors that are considered to have an effect on
dependent variables. Big D Incorporated can make use of this analysis by using two variables
such as buyer of sports good and the active lifestyle population in Chicago, especially in the
areas such as Lincoln Park and surrounding areas.
Selecting an appropriate alternative is extremely important for Big D Incorporated, to
help the outdoor sports goods company to be able to expand its business. It is depended on two
types of questions - decisional and exploratory. The exploratory questions do not validate any
hypothesis, rather it provides the research of multivariate datasets in convenient ways.
Researching of multivariate dataset enables designed and execute connecting ideas amongst the
dataset. Decisional questions test the correlation between the two variables sets or analyze a set
of variables with others. If it is an exploratory question with a table along with data description
consists of a proximity matrix, then choosing multidimensional analysis will be the best choice
(Williams, Onsman & Brown, 2010).
Again, factor analysis will be an appropriate alternative, if it is an exploratory question,
comprising of one table along with quantitative variables. In exploratory questions, with one
table and only quantitative variables, tools for cluster analysis such as AHC and k-means will be
the best method. In single questions, with either qualitative and/or quantitative tables, factor
analysis will be a suitable alternative. Undertaking decisions can be used from cluster analysis
can provide various benefits to the company. The cluster analysis can be conducted directly on
the qualitative table by using row scores. On the other hand, for decisional question with one
table, one dependent variable, and multiple quantitative or qualitative explanatory variables,
multiple regressions will be the best alternative to select from.
5

MULTIVARIATE TECHNIQUES APPLICATIONS
The cluster analysis will be considered the best matched multivariate technique. It helps
to find similar subjects that are in relevance to the entire character set. This method also helps to
identify various patterns which are not shown in the data. The clusters created are studied to
understand their meaning and ways they differ from the parent population. This type of analysis
is ideally suited for customer profiling, market research, and for recognizing pattern.
The Big D Incorporated for their client - the outdoor sports goods company can carry out
research to identify if there is a better proposition than Lincoln Park. Cluster analysis is enhanced
in comparison to multidimensional scaling as it is quite simple. It is also considered better than
factor analysis as it does not involve any outliers or correlation (Esbensen, Guyot & Westad,
2009). Firstly, they can group the entire population into different clusters. Next, by using
systematic or random sampling, they can select a number of clusters. Review of the clusters
along with other variables such as their lifestyle, earning, education or marital status. An
important benefits of this type of process is that every cluster has a chance to get selected due to
random sampling. The same cluster can be either one-stage or two-stage sampling. One-stage
samples refer to all the variables that the researcher includes from randomly selected clusters. On
the other hand, two-stage samples includes a certain number of variables selected from every
cluster using the process of random sampling.
Various social media platform, for example Facebook or Google use this type of analysis
to understand the users' behavior and find answers to an unknown question. These companies use
cluster analysis instead of keyword analysis is because the latter doesn't help in asking new
questions. This analysis undertakes a statistical approach to read documents and analyze and
compare words in relation to other words. The Autonomy Corp in the U.K, have an IDOL engine
and they embed this technology in the products.
6

MULTIVARIATE TECHNIQUES APPLICATIONS
Nidar uses multivariate analysis in order to conduct analyses related to their product
quality problems. The outcome from this analysis help in optimizing the manufacturing steps.
SAB Miller uses it to investigate both research of the market and manufacturing data to obtain
improvised value. John Deere uses this analysis to measure various products such as neutral
detergent fiber, starch, protein, sugar, and so on.
Wise Window applies this analysis for the purpose of determining predictive value
forecasting of various social media content. By tracking the comments regularly, the company
can determine future trends. Indicators could also be revealed by tacking growing clusters. This
analysis involves analyzing comments with respect to the musical act. It has been noticed that
there is a correlation between social media activity and record sales.
Board of Directors of Big D can use this analysis to take various business decisions. This
analysis can be applied for forecasting demand by analysis of the response on social media. The
company can also analyze the preference of the consumers prior to their business expansion in
Chicago. This analysis can also be used for determining the strength of specific product
categories. This type of analysis is quite cheap and the result can be derived faster. For the
successful expansion of business in a particular area, extensive planning and a lot of research
work are needed to carry out. The above analysis provided to the Board of Directors could
enable profits to expand. Analytics of Big D are well versed in the varied statistical techniques
which they can apply and gain considerable benefits from.
To conclude, it can be said that multivariate analysis has various utility in Big D
Incorporated. Multivariate analysis is focused on the statistical principles of multivariate
statistics. It encompasses analysis and observation from one or greater than one variable at a
particular time. Using multivariate analysis could provide a design for inverse design, capability,
7

MULTIVARIATE TECHNIQUES APPLICATIONS
analyzing alternatives and concepts, it also enables identifying critical design-drivers and
correlations through various hierarchical levels.
8

MULTIVARIATE TECHNIQUES APPLICATIONS
References
Esbensen, K. H., Guyot, D., & Westad, F. (2009). Multivariate data analysis. practice, 4.
Retrieved from
https://www.camo.com/training/australia/MVA_Australia_March_1201090719.pdf
Haware, R. V., Tho, I., & Bauer-Brandl, A. (2009). Application of multivariate methods to
compression behavior evaluation of directly compressible materials. European Journal of
Pharmaceutics and Biopharmaceutics, 72(1), 148-155. doi: 10.1016/j.ejpb.2008.11.008.
Retrieved from
https://www.sciencedirect.com/science/article/abs/pii/S0939641108004438
Hudaverdi, T. (2012). Application of multivariate analysis for prediction of blast-induced ground
vibrations. Soil Dynamics and Earthquake Engineering, 43, 300-308. doi:
10.1016/j.solidyn.2012.08.002. Retrieved from
https://www.sciencedirect.com/science/article/pii/S026772611200200X
Jackson, D., Riley, R., & White, I. R. (2011). Multivariate meta‐analysis: potential and
promise. Statistics in medicine, 30(20), 2481-2498. doi: 10.1002/sim.4172. Retrieved
from https://onlinelibrary.wiley.com/doi/full/10.1002/sim.4172
Williams, B., Onsman, A., & Brown, T. (2010). Exploratory factor analysis: A five-step guide
for novices. Australasian Journal of Paramedicine, 8(3). doi: 10.33151/ajp.8.3.93.
Retrieved from http://ajp.paramedics.org/index.php/ajp/article/view/93
9