代做Assignment TWO: SCIE1104调试R程序

日期：2024-09-12 05:39

Assignment TWO

Questions and Assessment Guide

Data sets

The relevant data sets can be found on the LMS.

Submitting Assignment TWO

· The assignment must be submitted via the LMS. Please compile the final assignment document into a pdf document before submission.  This is likely to be the safest way to upload your assignment.  People generally find that using the Print to pdf option renders higher quality files compared to the Save as pdf option. The recommended method to crease the pdf for upload is to use the print to pdf option.

· There is a word file called “Start my Assignment” on the LMS. Please download this file. The file has the cover page structure and the appendix heading that you need as part of the Assignment. Complete the cover page with your details; put your answers in the section left blank for your answers; and add your R code under the Appendix heading at the end of the document.

Assignment Due Date

The assignment is due as per the LMS due date. There is no need to wait until the last minute to upload the assignment. Don’t trust the technology to work at 11:55pm on the due date. Give yourself plenty of time for things to go wrong. The UWA policy on late assessment is a per day penalty.  

Assignment content

All assignment answers are to be collated into a single pdf document that includes the (i) cover page details; (ii) answers to the questions; and (iii) an appendix containing the R code.  Start each assignment answer must on a new page.  You also need to use section headings for each part of your answer.  If you consult the unit style. guide you will see that it says “Section headings are to be in 14pt font and in bold.”  For any given answer, the Introduction, Methods, Result, and Discussion headings are all section headings.  Note if you also choose to have question headings, such as Question 1, etc., these are also be formatted as section headings.  Figures and tables must be labelled sequentially as part of each question.  In practice this means you start with Figure 1 and Table 1 again, for each question.  Each figure and table must also have an appropriate caption title.  See the unit style. guide for further details on how to set out the tables and figures.  For Assignment 1, many people lost marks for presentation matters.  Please do focus on the formatting aspect requirement for the assignment.

marking guide

The first three question will be marked out of 20, and question four will be marked out of 3 (so the final mark is out of 63). For questions one, two, and three, use the IMRD format for your answers (see the example write-up as a guide to the process and the mark allocation per section). The lab exercises, including the practice at writing up your results during a computer lab, are closely aligned to the first three assignment questions. For question four use bullet points and just state each answer.    

Note that the specific assignment weights to each section of the IMRD questions might vary slightly from the weights shown in the example you have seen in the practical lab classes. The example is provided as a ‘representative’ illustration only, and the section weights can vary slightly depending on question complexity and tests involved.   

FIGURE Quality: IMPORTANT information

For Assignment 1 figure quality was variable. If you lost marks for figure quality in Assignment 1, please make sure you understand the expected format and standard. If you complete the assignment on a PC, use the metafile format to save your figures from R. If you use a mac, use the pdf file format to save your figures. If you want to get into the finer detail of figure quality control consult the course website/textbook for example code.  The relevant section is section 6.4, saving plots.

For figures that are in a low quality format, such as the bitmap format, there will be a mark deduction. Figure axis labels etc., also need to be correctly proportioned for this assignment. Please take care with your figures.  

If random lines get added to your figures when you use a pdf converter please do not worry. The teaching team is aware of the issues that can occur during conversion to pdf. You will not be penalised.

Assignment 2 must include the relevant R code as an appendix. For Assignment 1, there was no penalty if you did not include the R code as an appendix. For Assignment 2, there will be a mark deduction if you do not include the R code in the appendix. Providing the R code to support your approach to analysis is now a common requirement when communicating science findings that involve statistics.  Providing the code assists with making the results reproducible by others, and is part of good practice in science.

Alpha level

Unless directed otherwise, for testing use an alpha level of 0.05 (α=0.05).

Assignment TWO: SCIE1104

Question 1: Fisheries health

Blue Swimmer Crabs (Portunus armatus) are found between Karratha and Dunsborough.  In WA, they can regularly be caught with a carapace width of 20-25 cm and a claw span of 70-80 cm.  There is a commercial Blue Swimmer Crab fishery, and recreational crabbing is both popular and possible from Shark Bay to Geographe Bay.  In 2006, concern that Blue Swimmer Crab stocks had been depleted resulted in large areas of the WA coast being closed to both commercial and recreational crabbing.  By 2009 stock levels had recovered and the fishery was reopened.  Due to this past experience the Department of Fisheries actively monitors crab stock level along the WA coast.

In 2014 and 2024 the Department of Fisheries recorded the number of breeding Blue Swimmer Crabs observed at different sites along the Western Australian coast.  The number of crabs observed during the sample window provides the Department with information on the crab population.  If there are changes in the overall crab population the Department of Fisheries will change the policy for recreational fishing and either increase or decrease the length of the season when recreational fishers are allowed to take Blue Swimmer Crabs.  You are required to conduct a structured data investigation to determine whether or not there has been a change in the Blue Swimmer Crab population between 2014 and 2024.  Other than p-values (3 dp), report key values to 1 decimal place (20 marks).  

Note 1: In terms of the data source, for this question the data are hypothetical. For the purposes of the write-up you can state that the data have been collected by the Fisheries section of the Department of Primary Industries and Regional Development in accordance with Department policy for data collection.  The context for the question is, however, real.  Between 2003 and 2006 the commercial Blue Swimmer Crab catch collapsed from 226 tonnes to 38 tonnes (a fall of 83%) and the fishery was closed in 2006 to allow the stock to recover.  The fishery was reopened in 2009.

Note 2: Look carefully at the data when you read it into R to make sure you get the data column headings correct.  

Question 2: Water supply

Historically, dam infrastructure provided almost all of metropolitan Perth’s scheme water. Overtime, as the population living North of the Perth CBD increased, the water utility began to develop (extract water from) groundwater resources in the Northern metropolitan zone.  Perth’s major water supply sources then became a combination of dams and groundwater. Perth scheme water is now sourced from: dams (30%), groundwater (37%), desalination (28%), and groundwater replenishment (wastewater recycling) (5%); and the total volume of scheme water supplied is around 300GL. By 2035 it is expected that the water utility will need to supply around 350GL of scheme water, and based on current infrastructure planning, the relative source of supply shares are expected to be: dams (3%), groundwater sources (26%), desalination plants (65%) and groundwater replenishment (6%).  So, by 2035, it is expected that more than 70% of Perth’s scheme water will be sourced from rainwater independent sources.

The average winter rainfall at the Mundaring Weir rainfall data collection point (key reference for dam inflows) for the period 1910 to 1970 was 629 mm.  This is a given reference value.  

Water sourced from desalination plants and water recycling plants is expensive, relative to water sourced from dams.  Both Victoria and New South Wales built unnecessary desalination plants in the 2000s so there is a genuine reason to be concerned that water utilities overinvest in expensive desalination plant infrastructure.  

Dam recharge main occurs during winter and you are to conduct a structured investigation to establish whether the average winter rainfall (winter rainfall is the total (sum of) rainfall in June, July, and August) for the period 2000-2024 (inclusive of the 2000 and 2024 values) is statistically different to the historical reference value of 629 mm per year.  If the current period (2000-2024) winter rainfall is lower than the historic reference level, it is appropriate that the water utility develop rainfall independent infrastructure to supply Perth with scheme water.  If the current level of winter rainfall is the same as the historical average, then the water utility is wasting money by investing in desalination plants.  Other than p-values (3dp), report key values to 1 decimal place (20 marks).

Note 1: The data set has been downloaded for you.  For this question state Bureau of Meteorology weather station 009030 (Mundaring) as the data source.  

Note 2: Some data management is required for this question.

Note 3: Make reference to the 95% confidence interval as part of your answer.  

Question 3: Energy production

Energy generation is a significant source of CO₂ emissions.  On 1 January 2017 the royalty for coal extraction that the Victorian government charges increased substantially.  At the time the Victorian government stated that the policy change was consistent with a desire to shift energy generation in Victoria away from (brown) coal-based energy sources towards non-fossil fuel alternatives that would lower CO₂ emissions from energy generation in Victoria. 

The Industry Benchmark Emission Index (IBEI) provides an indication of the extent of CO₂ emissions per megawatt hour of electricity generated.  Lower IBEI values indicate lower CO₂ emissions from energy generation.  It is not necessary to reference the formula in your answer, but for completeness, the formula for calculating the Index is shown in Box 1.    

Box 1. Extract from the Australian Energy Market Operator

Methodology for constructing Industry Benchmark Emission Index (IBEI) The IBEI is a NEM-wide emission index adjusted for marginal loss factors.  The IBEI is calculated according to the following formula:   where: IBEI = Industry Benchmark Emission Index for the NEM (t CO2-e/MWh) adjusted for marginal losses.   CDEi = Carbon Dioxide Equivalent emission from a generating unit (t CO2-e) as measured at the connection point for the generator. Ei = Sent Out Energy (MWh) generated from a generating unit, as measured at the connection point.   MLFi = Marginal Loss Factor applicable for a generating unit for the relevant day.

For Victoria, compare the IBEI data for the month of June 2016 to the month of June 2024 and comment on the results.  The IBEI values are the Adjusted Intensity Index values.  The data values are in the last column in the data files and the column title is: “ADJUSTED_INTENSITY_INDEX”. Report values to 3 decimal places (20 marks).

Note 1: For this question the data sets are from the Australian Energy Market Operator.  In your write-up you can simply state that the IBEI data was sourced from the Australian Energy Market Operator.

Note 2: To obtain the data you need to engage in some data management activities (Pivot Table functions) to sort the data and then combine the relevant information.  If you are struggling with the data management requirement, watch the Practical class week 8 video on downloading and managing IBEI data. The recording covers more than you need for this activity, as the data has already been downloaded for you.  Experience with data management is an activity that you can put on your CV, and is highly valued by employers.

Question 4: Wine and Weather

This question is worth 3 marks only and requires substantial work. The final few parts of an assignment are typically difficult. Depending in the time you have, you may not want to even attempt this question.  If you do not attempt this question the maximum mark for the Assignment is 95 percent. The threshold for a HD grade is 80 percent.   

A proposal has been developed to classify Australian wine regions into one of three categories: Very Hot, Hot, Hot-Warm, Warm, Warm-Cool, Cool, or Cold.  To ensure the classification remains up-to-date, the data used to classify regions is a rolling 20-year window.  The current period analysis will therefore consider the weather data for the period 2005 to 2024 (inclusive).  The Nuriootpa weather station (station reference number 023373) is representative of temperatures in the Barossa Valley wine region of South Australia and will be used for the analysis of the Barossa Valley.

The specific metric proposed to classify wine regions is the average of the maximum and minimum monthly temperature in January.  The available data for this weather station is for the period 1997-2024 and you will need to download both the Max Mean Temperature data and the Mean Minimum Temperature data.  Once you have downloaded the data you create the relevant data column for analysis in Excel as the average of the maximum and minimum monthly average temperatures as follows:

[(Mean Max Jan 1997) + (Mean Min Jan 1997)]/2,

[(Mean Max Jan 1998) + (Mean Min Jan 1998)]/2, …    

…., [(Mean Max Jan 2024) + (Mean Min Jan 2024)]/2.

The proposed methodology to group regions is as follows. The reference temperature for classification as a Cool region is 18 degrees C; the reference temperature for classification for as a Medium temperature region is 22 degrees C; and the reference temperature for classification as a Hot region is 26 degrees.  The criterion proposed to classify wine regions is as follows. A region can be classified as Cool, Medium, or Hot, if it there is insufficient evidence to reject the null hypothesis that the sample is drawn from a population where the mean is equal to 18C, 22C, and 26C, respectively.  If there is insufficient evidence to reject the null for more than one category, a hyphen is be used to join the classifications. For example, if there is insufficient evidence to reject the null hypothesis for a Cool region, and also insufficient evidence to reject the null hypothesis for a Medium region, the region can be classified as a Medium-Cool or a Cool-Medium region (the order of the two region names does not matter).  If there is sufficient evidence to reject the null that the sample is drawn from a population with a mean of 26, and the sample mean is above 26C, the region is classified as Very Hot.  If there is sufficient evidence to reject the null that the sample is drawn from a population with a mean of 18, and the sample mean is below 18C, the region is classified as Cold.  If the sample mean is between 18C and 22C and there is sufficient evidence to reject the null that the mean is 18C and there is sufficient evidence to reject the null that the mean is 22C the region is classified as Cool-Medium.  If the sample mean is between 22C and 26C and there is sufficient evidence to reject the null that the mean is 22C and there is sufficient evidence to reject the null that the mean is 26C the region is classified as Medium-Hot.  

The first step in answering these questions is to go to the Bureau of Meteorology (BOM) website and download the relevant data.  The link below will take you to the relevant section of the BOM website. Instructions that walk you through the steps of getting the data from the BOM site to your computer are provided below.

Data link:

http://www.bom.gov.au/climate/data/

To download the data from the BOM website you need to select the data type you want, which is Temperature and Monthly; and you need to enter the station number details: 023373. You need to download both the mean maximum and mean minimum monthly temperatures as separate downloads, so you will go through the get data process twice.  To access the source data hit the ‘get data’ radio button next to where you enter the station number (see Figure 1).

Figure 1: Screenshot of selecting the monthly mean temperature data for station No. 023373

Once you hit the ‘get data’ radio button you should be taken to a screen such as that shown in Figure 2.  To download the data select the ‘all years of data’ link in the top right hand corner of the page.  Once you click on ‘all years of data’ the download process should start automatically.  Once the files have been download, open the relevant Zip files, and for both the maximum and minimum data file select the file with the name ending in “…_Data12” as this is the file that you want to open (see Figure 3).  If you have opened the correct data file, you should see something like that shown in Figure 4 when you open the file.  Finally, you need to calculate, for each month, the average of the maximum and minimum temperature values.  Once the process of organizing the data is complete you should end up with a file structure that looks similar to that shown in Figure 5.  Note that in Figure 5 the values shown are for the first few years of the relevant data sets, and the values that you actually need for analysis are those for the years 2005 to 2024 (inclusive) only.

Figure 2: Screenshot of source data for station No. 023373

Figure 3: Screenshot of files downloaded and ready to be extracted/opened

Figure 4: Screenshot of what a file that you down load and open should look like

Figure 5: Screenshot of representative data structure post formatting to get monthly average

To answer question four you will need to calculate the mean average temperature of the sample for the period (2005-2014) and the 95% confidence interval around that estimate.  To answer these questions simply use a bullet point style.  There is no need for any extra text for these answers. Keep it short.

The specific questions are:

(i) What is the mean average January temperature for the sample period (2dp)?

(ii) What is the 95% confidence interval lower bound for the sample period (2dp)

(iii) What is the 95% confidence interval upper bound for the sample period (2dp)

(iv) Using the reference decision framework, specify which of the following classifications is the most appropriate classification for the Barossa Valley: Cold, Cool, Cool-Medium, Medium, Medium-Hot, or Very Hot.  Just state the correct classification.

Note 1: The data you download will be for the period 1997 to 2024, but the data required to answer the relevant questions is for the period 2005 to 2024 (inclusive) only.