*****FOR SCARLETTUTOR ONLY**** power point presentation
jwlinscombe
business_decision_making_project_part_ii.docx
Business Decision Making Project Part 2
Jared Linscombe
QNT/275
Dr. Davisson
September 12, 2016
Descriptive Statistics
Descriptive statistics are statistics that describe or summarize features of collected data. Descriptive statistics simply present quantitative information in a manner that can be easily managed. The large amount of data is reduced into a simple summary and therefore the whole process of describing the data is less laborious.
For example, finding the mean helps to summarize a lot of individual information into a way that is quickly understood. The samples are likely to produce different independent variables that affect the sales of Elite Technologies Limited. For this reason, we opt to use bivariate analysis in the describing the statistics. Bivariate analysis of the descriptive statistics that is derived from the data will help in drawing relationships between different variables.
For a more accurate representation the Pearson’s R bivariate method of statistical analysis will be used. The information that is received from the customers and the sales is put in a manageable way that can enable the management level to make timely but well informed decisions based on accurate summaries.
Inferential Statistics
With inferential statistics their aim is to derive information beyond that which the data does not present at face value. It gives a proposition about data concerning a particular population. Inferential statistics assumes that the data comes from a larger population and not merely limited to the observable data. A hypothesis or hypotheses are then proposed and tested to derive estimates. Konishi and Kagawa (2008) say that, “The majority of the problems in statistical inference can be considered to be problems related to statistical modelling”.
After the statistical inference is made then a statistical proposition can be made. It is at this point that a hypothesis can be formulated which may later on be accepted or even rejected after being proven to be true or false.
Trend Analysis
Trend analysis refers to the techniques for extracting an underlying pattern of behavior in a time series which would otherwise be partly or nearly completely hidden by noise. Trends may be linear or have more complex forms such as polynomial or logistic. It is important to specify the trend explicitly prior to further analysis and modelling.
Creating a time series graph where data like sales is plotted can be visually examined to determine whether there is the existence of a trend. Autocorrelation analysis is also a useful technique is useful for identifying the existence of such trends and is even more accurate than employing the use of visual inspection.
Having established that trends exist one can then consider procedures for identifying and managing trends. Some of these procedures include curve fitting, for example, through linear regression or growth curves and also filtering and differencing.
Linear Regression for Trend Analysis
Linear regression is the most basic and commonly used predictive analysis where estimates are used to describe data and to explain the relationship between one dependent variable and one or more independent variable.
With respect to trend analysis, linear regression may be used to identify the effect that the independent variables have on the dependent variables. For this case independent variables like customer dissatisfaction will be analyzed for their effect on sales which is the dependent variable.
Secondly we are able to understand how much the dependent variable will change when one or more independent variables are changed. For this case we will be able to understand and observe the change in sales when independent variables like customer dissatisfaction are changed.
By drawing a trend line we are able to see the variations that have taken place with respect to sales data. In as much as trend lines lack scientific validity, their ease of use has made them gain popularity. They may appear as straight lines connecting data points or may take a more complex form of polynomials.
Time Series
Time series can be defined as an ordered sequence of values of a variable at equally spaced time intervals. Time series analysis takes into account the fact that the data points taken over time have an internal structure such as autocorrelation, trend or seasonal variation that should be accounted for. Time series analysis, unlike linear regression, can be able to provide analyses over time and is not just simply instantaneous.
For purposes of making forecasting like economic forecasting and sales forecasting and also making projections and controls among other things, the application of a time series is then favorable for use.
Time series analysis comprises methods for analyzing time series data in order to extract meaningful statistics and other characteristics of the data. Time series forecasting is a model used to predict future values based on the previously observed values. The advantage of using time series analysis is that it can be applied to real-valued, continuous data, discrete numeric data, or discrete symbolic data such as letters that are used in the English alphabets.
Some of the methods used in the fitting of a time series model include Box-Jenkins ARIMA models, Box Jenkins Multivariate Models and Holt-Winters Exponential Smoothing (single, double, triple).
Instead of making assumptions that may be costly to Elite Technologies Company concerning its sales, more informed decisions may be made with the application of a time series analysis. The organization will be better placed at making decisions now that they will be able to anticipate certain events based on the information received from having a time series analysis.
Reference
Chatfield C. (1975). The Analysis of Times Series: Theory and Practice. Chapman and Hall. London.
Mann Prem S. (1995). Introductory Statistics (2nd ed). Wiley.
Nick Todd G. (2007). Descriptive Statistics. Topics in Biostatistics. Methods in Molecular Biology. New York: Springer. Pp. 33-52.
Bickel Peter J., Doksum Kjell A. (2001). Mathematical Statistics: Basic and Selected Topics. 2nd ed.
Cox D. R. (2006). Principles of Statistical Inference, Cambridge University Press.
Freedman D.A. (2009). Statistical Models: Theory and Practice (revised ed.) Cambridge University Press.
Lewis, S. (2007). Regression Analysis. Practical Neurology, 7(4), 259-264.
Shumway, R. H. (1988). Applied Statistical Time Series Analysis. Englewood cliffs, NJ: Prentice Hall.
Bloomfield, P. (1976). Fourier Analysis of Time Series: An Introduction. New York: Wiley
Australian Bureau of Statistics, (2008, July 25). Time Series Analysis. The Basics. Retrieved November 29, 2012, from Australian Bureau of Statistics.
