Moving Average, Exponential Smoothing and Trend Forecasting

Forecasting in a project entails making conjectures about the future. Several approaches
can be used in the process. They include the moving average, exponential smoothing, and trend
analysis. The main is to predict the future by identifying risks involved in creating a contingency
plan at the moment. Forecasting makes it easy for the project managers to decide whether to
continue with the current project or create new ideas. The essay will discuss the three methods
used in forecasting, provide data, and illustrate Statistical Package for the Social Science (SPSS).
Overview of Moving Average, Exponential Smoothing and Trend Forecasting
Moving Average
Moving average( MA) is used in the indication of stocks for much technical analysis. The
simplest version is a computation that entails using the mean for a given set of prices for a
specific period in the past. There is the creation of a series of averages which are analyzed at the
end. The information that is collected is for different subsets of data. In other instances, it is
referred to as a moving or rolling mean (Sharpe, De Veaux, and Velleman, 2019). The main rule
in the analysis is that if the price value is above the moving average, then there is an upward
trend.
Exponential Smoothing
Exponential smoothing refers to time series forecasting that takes advantage of the
univariate information. The data can be expanded to offer the needed support to a trend that is
systematic or seasonal. Other methods such as Box-Jenkins can be used in exponential
smoothing, but it is the most preferred because it is powerful. The rule of thumb is that
observations made in the past are weighted to be equal and will be assigned a declining weight in

3
the process (Lewis, McGrath, and Seidel, 2011). It is determined by multiplying the most recent
demand with the smoothing factor identified in the equation.
Trend Forecasting
Trend forecasting entails research and the creation of predictions on consumers based on
their present and future habits in consumption. The focus is on identifying the source, tracing the
evolution, and recognizing the patterns that have been created (Priyavadana, Sivashankari, and
Senthil, 2015). The consumption fluctuation at the moment or that which was observed in the
past can predict the future. It is mainly used to evaluate past sales, or there is a need to consider
the growth experienced in the market over time.

Data and Illustration of SPSS understanding

SPSS is a statistical software used in social sciences in the assessment of data and making
the prediction. It is used in market and health research, surveys done by the government,
organization analysis, and many more processes that require an evaluation of the data presented
(Tomar and Agarwal, 2013). Consider the following data that can be analyzed using SPSS.
Subject Height Weight
1.00 1.78 78.00
2.00 1.82 92.00
3.00 1.65 81.00
4.00 1.55 56.00
5.00 1.92 92.00
6.00 1.78 77.00
7.00 1.75 75.00

4
The above data consists of the weight and height of seven different individuals. While
using SPSS, the main focus will be on establishing the correlation between the two variables. For
instance, the focus might be on determining a statistically significant relationship between a
person’s height and weight. The question to ask is where the measurement of a person dictates
their weight. Both size and weight are cardinal data in SPSS. They can be put on the range, and
there is no specific value that is associated. The information can be analyzed using regression
analysis in SPSS. There will be the determination of a covariate that will be used in making the
prediction. The test to be carried out will be two-tailed since the focus is on establishing a normal
distribution.

Strength and Weaknesses of the Numerical Methods

A key strength is the use of SPSS is that it is easy to use and quick. It can be used to
analyze a massive amount of data that cannot be effectively analyzed using other approaches.
Another gain is that the user interface is excellent. That implies that it can carry out the
multivariate analysis where more than two means can be compared. However, there is a
disadvantage because the function that can be carried out using the numerical methods can be
performed on an excel spreadsheet (Manaswini, 2014). There are limitations to its functionality,
and the presentation of the outcomes of analysis is challenging.
Findings in a Project Management Context

It will be necessary to use more than a single approach to analyze data and information in
project management. That is because the focus will be on improving the accuracy level of the
outcomes and making sure that the prediction is on point. It will be easy to identify the
associated risk and implement a contingency plan that will be effective and efficient at the same
time.

5

A Prediction of Future Trends

Technological advancement has predicted the future to be easy. However, in most
instances, the prediction is just but an estimate of the values and outcomes which are anticipated.
However, trends in the future are more likely to be accurate. It will no longer be the rage but the
actual value that can assist with the evaluation of gains at the moment.

6

References

Lewis, J., McGrath, R. & Seidel, L. (2011). Essentials of Applied Quantitative Methods for
Health Services Managers. Boston, MA: Jones and Bartlett Publishers.
Manaswini, P. (2014). Data Mining & Health Care: Techniques of Computer. Communication
Engineering, 2(12), 7445-7455.
Priyavadana, A., Sivashankari, V. & R. Senthil, K. (2015). A Comparative Study of Data
Mining. Applications in Diagnosing Technology, 2(7), 1046-1053.
Sharpe, N. D., De Veaux, R. D., & Velleman, P. F. (2019). Business statistics (4th Ed.). Pearson.
Print.
Tomar, D., & Agarwal, S. (2013). A survey on data mining approaches for healthcare.
International Journal of Bio-Science and Bio-Technology, 5(5). 241-266.