For Assignment One, you will analyse a data set which relates to the performance of an engineering enterprise. Using the data you collect, you will use a statistical model of your choice to find the...

1 answer below »
For Assignment One, you will analyse a data set which relates to the performance of an engineering enterprise. Using the data you collect, you will use a statistical model of your choice to find the predicted value of your depenedent variable yi. You will need to use the tools available in Microsoft Excel to analyse the data, and present it in the form of a report. Your report will include four parts:In Part 1, you will collect data from a company of your choice, then briefly summarise the types of real data collected and analyse its comprehensiveness.In Part 2, you need to further analyse the data by constructing a stem and leaf plot and a box plot.In Part 3, you need to use the appropriate statistical modelling techniques to find the relationship between the data (variables).In Part 4, Use the data you collected to build a forecasting model using Microsoft Excel, and apply a suitable forecasting technique to make a set of predictions for the next 10 years.This assignment will include two components – a word file for the report, and an excel file.


School of Engineering — MANU2469 Performance Management Foundations Assessment 1: Data Collection, analysis and modelling Assessment Type: Report Word limit: 3000 (+/– 10%) Due date: Sunday of Week 3, 23:59 (Melbourne time) Weighting: 30% Overview For Assignment One, you will analyse a data set which relates to the performance of an engineering enterprise. Using the data you collect, you will use a statistical model of your choice to find the predicted value of your depenedent variable yi. You will need to use the tools available in Microsoft Excel to analyse the data, and present it in the form of a report. Your report will include four parts: In Part 1, you will collect data from a company of your choice, then briefly summarise the types of real data collected and analyse its comprehensiveness. In Part 2, you need to further analyse the data by constructing a stem and leaf plot and a box plot. In Part 3, you need to use the appropriate statistical modelling techniques to find the relationship between the data (variables). In Part 4, Use the data you collected to build a forecasting model using Microsoft Excel, and apply a suitable forecasting technique to make a set of predictions for the next 10 years. This assignment will include two components – a word file for the report, and an excel file. Learning Outcomes This assessment is relevant to the following course learning outcomes: CLO1 Perform a thorough data analysis of the performance data set and summarise the findings using Microsoft Excel. CLO2 Recognise situations and apply the appropriate forecasting models to represent the trend of the business. CLO3 Fit some parts of the data set to a regression or discriminant analysis model and interpret the implication of the model in terms of the enterprise’s past and future performance. CLO4 Define and apply the Monte Carlo technique to a number of different business modelling situations. After completion of this assessment you should be able to: − Describe the kinds of real data collected from a company and analyse its comprehensiveness. − Construct a stem cell and leaf plot and a box plot on the data and define its shape. − Calculate basic statistics and analyse the results. − Apply approproriate statistical modelling techniques. − Apply forecasting techniques to make valid predictions. − Analyse the results and note whether there are any outliers. − Use excel software to analyse the data and find the statistical model. Assessment details Part 1: Data Collection Collect data from a company of your choice, then briefly summarise the types of real data collected and analyse its compreheniveness. Example: You work in a bank, and you would like to analyse the number of customers, the date/time they arrive, the kinds of services they ask for, the length of time they generally wait, and the service time for each customer. Part 1 of your report should: − Identify the types of real data collected (i.e. is it qualitative or quantitative?) − If it is quantitative, indicate whether it is discrete or continuous. − Assess the comprehensiveness of the data. Part 1 of your report should be 300 words. Part 2: Data Analysis Anlyse your collected data by constructng a stem and leaf plot, and a box plot on the data. Part 2 of your report should: − Comment on its shape noting whether there are any outliers. − Complete the calculation of basic statistics. − Check the normal distribution prediction of how many measurements lie between: − one standard deviation of the mean, − two standard deviations of the mean, and − three standard deviations of the mean. Discuss the result of your data analysis. Part 2 of your report should be 700 words. Part 3: Data Modelling In the last section of your report, you are required to see how close the data came to the theoretical Normal distribution. Select an appropriate statistical modelling technique (i.e. Discriminant Analysis or linear regression).In this section of the report, you should: − Explain why you used this statistical modelling technique. − Illustrate how you used this technique. − Discuss the model result by noting whether there are any outliers. − Use Microsoft Excel to make Discriminant Analysis or linear regression as explained in the week 2 and week 3 topic. − Use the appropriate statistical modelling techniques to find the relationship between the data (variables). Part 3 of your report should be 1,000 words. Page 3 of 8 Part 4: Data forecasting In the last section of your report, you are required to use that data to build a forecasting model using Microsoft Excel. You will need to determine the most appropriate forecasting techniques, based on the data and make a predicition for the next 10 years. You will need to: • identify the major factors to consider when choosing a forecasting technique. • measures of forecast accuracy. • briefly describe averaging techniques, trend and seasonal techniques, and regression analysis, and solve typical problems, • choose the best forecasting model by comparing different technique. • use excel to find the forecasting model, make the comparing between the different technique and find the forecast accuracy. Part 4 of your report should be 1000 words You are requifred to submit your report as two components, which include − A Microsoft Word document containing the report, which includes details of the model and recommendations to the problem. − An excel spreadsheet which analyses the data. You will need to submit this as a single zip file in Canvas. Page 4 of 8 Referencing guidelines Use RMIT Harvard referencing style for this assessment. You must acknowledge all the courses of information you have used in your assessments. Refer to the RMIT Easy Cite referencing tool to see examples and tips on how to reference in the appropriated style. You can also refer to the library referencing page for more tools such as EndNote, referencing tutorials and referencing guides for printing. Submission format You will zip the Word Document and Excel file and upload as one (1) single file via Canvas. Academic integrity and plagiarism Academic integrity is about honest presentation of your academic work. It means acknowledging the work of others while developing your own insights, knowledge and ideas. You should take extreme care that you have: • Acknowledged words, data, diagrams, models, frameworks and/or ideas of others you have quoted (i.e. directly copied), summarised, paraphrased, discussed or mentioned in your assessment through the appropriate referencing methods • Provided a reference list of the publication details so your reader can locate the source if necessary. This includes material taken from Internet sites If you do not acknowledge the sources of your material, you may be accused of plagiarism because you have passed off the work and ideas of another person without appropriate referencing, as if they were your own. RMIT University treats plagiarism as a very serious offence constituting misconduct. Plagiarism covers a variety of inappropriate behaviours, including: • Failure to properly document a source • Copyright material from the internet or databases • Collusion between students For further information on our policies and procedures, please refer to the University website. Assessment declaration When you submit work electronically, you agree to the assessment declaration. Page 5 of 8 https://www.rmit.edu.au/library/study/referencing/referencing-guides-for-printing https://www.lib.rmit.edu.au/easy-cite/ https://www.rmit.edu.au/students/student-essentials/rights-and-responsibilities/academic-integrity https://www.rmit.edu.au/students/student-essentials/assessment-and-exams/assessment/assessment-declaration Assessment Criteria Criteria Ratings Pts HD D C P N Criterion 1 Describe kind of real data collected from the company and analyse its comprehensiveness. The report describes what kind of real data was collected from the company and demonstrates the comprehensiveness of the data well. The report describes what kind of real data was collected from the company and demonstrates the comprehensiveness of the data. The report describes what kind of real data was collected from the company and demonstrates the comprehensiveness of the data well, but there are some unclear areas. The report describes what kind of real data was collected from the company and demonstrates the comprehensiveness of the data. The report does not, or hardly, describes what kind of real data was collected from the company and demonstrates the comprehensiveness of the data. 5.0 to >3.99 3.99 to > 3.49 3.49 to > 2.99 2.99 to > 2.49 2.49 to > 0 5.0 Criterion 2 Construct a stem cell and leaf plot and a box plot on the data and define its shape. The report shows a stem and leaf plot and a box plot on the data and demonstrates a professional level of understanding of the result. The report shows a stem and leaf plot and a box plot on the data with logical extrapolations from research and analysis. The report shows basic understanding of a
Answered 4 days AfterJul 13, 2021

Answer To: For Assignment One, you will analyse a data set which relates to the performance of an engineering...

Pritam Kumar answered on Jul 18 2021
149 Votes
Time Series Analysis: Reymons Electricals
Introduction
“The trend is your friend” is what business managers call as the only mantra. This manta is always at the forefront of any business decision for managers. Managers often seek to have a detailed look at future forecasts (Chatfield, 2000) of sales figures, production volume, and profitability before making these business decisions. The trick is to best identify and discover business trends (Chatfield, 2000) such that various objectives of the enterprise are met, keeping in mind the competition in the market and also maintaining co
mpetitive advantage.
Time series is a series of data points (Kenneth Lawrence, 2009) with time as the index. Yearly sales figures data in an engineering enterprise is a time series dataset which has two variables, a timestamp and the amount of revenue generated for selling finished goods. Time series data is collected at different points in time, unlike cross-sectional data which observes multiple features (Kenneth Lawrence, 2009) at a single point in time. In statistical forecasting, time series analysis plays a very important role for forecasting and predictions. Seasonality and trend (Peter Brockwell, 2016) are two main components in a time series data set.
Seasonal index or seasonality represents the degree of seasonal influence (Peter Brockwell, 2016) (seasons) on the data in a year. If the time series data is with a quarterly, or monthly, or a daily timestamp, it is very important to consider the effect of seasonality on the data analysis. However, for yearly data, seasonality has very little effect on any analysis. Calculations for seasonality involves comparison of the expected values of the particular period (season) to the overall mean/average.
Similar to seasonality, trend is obviously an important component in time series analyses. Trend is a pattern in time series datasets where movement (Peter Brockwell, 2016) of a series to some higher or lower values over a period of time is shown. So, we observe trend in a time series data when either an increasing or a decreasing slope (Mills, 2019) is seen in the data. In trend analysis, we use regression (Kenneth Lawrence, 2009) with time as the feature variable (independent variable) and any of the data points (which are mapped over time) as the dependent variable.
Deseasonalizing is a process (Chatfield, 2000) where adjustments are made on the data in order to nullify the seasonality (regularly repeating movements tied to some recurring events over time) effect on the data. Recurrent and periodic variations (Kenneth Lawrence, 2009) are removed over time-frames such as quarters, months, and sometimes weeks. Clearly this process is not required for yearly data.
Apart from dealing with seasonality and trend, smoothing is also performed on the dataset before any analysis. This removes random fluctuations and other irregularities (Kenneth Lawrence, 2009) in the dataset. This is again important for daily and weekly timestamps, where double or triple order smoothing (Chatfield, 2000) is often required. In most cases, a time series analysis ends with forecasting the trend for some future time period.
Finally, we move to correlation analyses. Correlation (Chatfield, 2000) is a popular measure in statistics which provides information about the association among different variables. However, in time series data, a more important metric is autocorrelation. Autocorrelation (Mills, 2019) is a measure used to get information between two data points of the same variable. It can be referred as lagged correlation or serial correlation also. It measures the relationship between a variable's current value and its past values, a usual scenario in case of time series analysis.
About the dataset
Reymons Electricals is an electrical home appliances manufacturing company in India. The company has been traditionally catering to the developed economies since it started its operations (predominantly US & Canada). Reymons works on bulk orders from third-party organizations for home appliances such as lighting solutions for homes.
We have a dataset that is collected from Reymons which provides information on yearly cost and yearly sales amounts from the year 1986 till 2009 (24 years). The original dataset that is collected from Reymons looks like this:
Table 1: Yearly cost & sales performance for Reymons Electricals
    sl.no.
    year
    total cost
    total sales
    1
    1986
    944.75
    1011.46
    2
    1987
    1344.84
    1453.65
    3
    1988
    1858.37
    1999.54
    4
    1989
    2553.54
    2758.53
    5
    1990
    3516.72
    3815.35
    6
    1991
    4705.32
    5136.62
    7
    1992
    6533.46
    7148.43
    8
    1993
    8446.79
    9238.76
    9
    1994
    11359.89
    12476.69
    10
    1995
    14109.29
    15470.35
    11
    1996
    17769.51
    19535.53
    12
    1997
    21857.68
    24156.37
    13
    1998
    27185.16
    30219.58
    14
    1999
    34176.56
    38434.34
    15
    2000
    40946.23
    45738.78
    16
    2001
    47812.39
    53553.25
    17
    2002
    51514.36
    58247.68
    18
    2003
    56894.27
    64816.16
    19
    2004
    63849.21
    73094.23
    20
    2005
    70585.76
    81511.45
    21
    2006
    79402.34
    90837.28
    22
    2007
    68317.89
    77347.43
    23
    2008
    64195.33
    71288.26
    24
    2009
    59303.82
    65955.96
The dataset contains three variables (columns), year as the time index, total cost amount in INR[footnoteRef:1] million and total sales amount in INR million. For our analysis, we will consider two of these three variables, year and total sales as independent and dependent variables. As “year” is a time variable, “total sales” is a continuous variable. We calculate the autocorrelation for total sales at lag 2 and lag 3. These values come out to be 0.8338 and 0.7106 respectively. As it is in most of the cases, autocorrelation is very common among time series data points. Here we see that there is a strong autocorrelation, around 0.8 between two data points...
SOLUTION.PDF

Answer To This Question Is Available To Download

Related Questions & Answers

More Questions »

Submit New Assignment

Copy and Paste Your Assignment Here