Reference no: EM133929027

ASSIGNMENT - Data Use in Science

QUESTION 1
Rare-earth elements (REE) are critical for the high-tech industry due to their unique properties, making them essential components in many modern devices and technologies. REE therefore become a major sticking point for the US-China trade war because of China's dominance in the global supply chain of REE. Australia is also a major player in REE global production and reserves. Increasing REE refining capacity has strategic benefits for Australia.

Rare earth refining is a complex process involving multiple steps to separate and purify individual REEs from mined ore. Key methods include solvent extraction, ion exchange, and fractional crystallization, often used in combination. Superior refining process aims to achieve high purity levels of individual REEs from their ores at low cost.

The focus of this analysis is to determine if there is a difference in performance across five refin- ing processes: EXT, EXC, CRS, COMA, and COMB. The first three processes refer to solvent extraction, ion exchange, and fractional crystallization. The last two are processes involving com- binations of two or more methods. At this stage, we do not consider cost but focus only on the key performance indicator - the purity level (%) of REEs. There are 15 observations for each refining process. The indexing in the assginment2q1 data file is clear, and the data are provided by Rare Earth WA. It is appropriate to use a parametric method for this question.

Complete a comprehensive, structured analysis of the data to answer the question of interest. The analysis should follow the IMRD format. For guidance on the way to structure your answer consult the example write-up. Report summary statistic information to 2 decimal places and p values to 3 decimal places.

QUESTION 2
The assignment2q2 data set contains measurements on the quantity of food adult koalas were observed eating during a single day across different months of the year. The observations relate to different koalas, and the measurement values are in grams. The researcher is interested in understanding whether koala food consumption varies throughout the year. This information is needed to determine whether the carrying capacity of the region should be calculated with reference to the biomass available for consumption over the year, or whether the carrying capacity should be calculated separately for each month. Ultimately, the researcher is concerned with ensuring that the koala population in the region is sustainable. The number of observations for each group is relatively low, so the analysis is to be conducted using non-parametric methods. The data set has been provided by Koala Conservation Australia.

Complete a comprehensive, structured analysis of the data to answer the specific research question. The analysis should follow the IMRD format. Report summary statistic information to 1 decimal place and p values to 3 decimal places. Note: For guidance on the way to structure your answer consult the example write-up.

QUESTION 3
There is no data set for this question. Assume the mean kilojoule content of a fast food meal is 2,000 KJ, and that the associated standard deviation is 260 KJ. The researcher is interested in understanding how a specific intervention impacts the mean number of KJs in the meals people order. Pay careful attention to the values specified. Note: You just need to state the answer for each part of the question.

If the study is to compare two separate groups, what sample size is needed for each group to detect a difference in the group means of 260KJ, with test power of 0.9, and an alpha level of 0.01?

If the study is to compare two separate groups, what sample size is needed for each group to detect a difference in the group means of 260KJ, with test power of 0.9, and an alpha level of 0.10?

If, rather than compare two groups, the experiment is converted to a paired experiment, how many ‘pairs' are needed to detect a difference in the group means of 160KJ, with test power of 0.8 and an alpha level of 0.05?

If it is possible to recruit 50 people for each group for the study, and using an alpha level of 0.05, what will be the test power to detect a difference of 160KJ in the group means for an unpaired experiment? (report to 2 decimal places)

If it is possible to recruit 50 people for the study, who will participate twice, such that the experiment becomes a paired experiment, using an alpha level of 0.05, what will be the test power to detect a difference of 90KJ in the group means? (report to 2 decimal places)

QUESTION 4
The assignment2q4 data set contains measurements on the weight of a pig kept under natural conditions, where measurements were taken at one week intervals. The starting measurement was taken in week 11 of the pig's life, and the weight measurements are in kilograms. The farmer that collected the data is considering switching the diet of the animals on their farm, and so at this stage is trying to establish base line information on the growth of pigs through time when they are fed the existing diet. The data set has been provided by Healthy Farming Enterprises. Prepare a structured analysis of the data set. Report coefficient estimates, standard errors, and R squared information to 2 decimal places.

Note 1: For information on the way an answer should be structured, consult the regression example write-up. Note 2: It is not always clear that one data transformation is ‘more linear' than another. For the pig growth data set there is more than one acceptable way to represent the data. As long as the plot you present looks approximately linear, and as long as the interpretation you provide for the slope estimate is correct, you will receive full marks for the question. To be clear, for this question there is more than one ‘correct' answer.

QUESTION 5
The assignment2q5 data set contains measurements on Australian Grasstrees (Xanthorrhoea) taken from a site near Yanchep in Western Australia. The flower spike length is measured in centimetres and the seed count is the total number of seeds produced. The question under in- vestigation is whether the seeds produced by a plant can be explained by the flower spike length. Prepare a written analysis of the data set. The data have been provided by the Department of Parks and Wildlife. Get expert online assignment help in the USA.

Note 1: For information on the way an answer should be structured, consult the regression example write-up. Report coefficient estimates, standard errors, and R squared information to 3 decimal places.

QUESTION 6
The Commonwealth Department of Agriculture, Water and the Environment is interested in un- derstanding what the trend change in the NEM IBEI value for March has been for the period 2016 to 2024 inclusive. In the relevant data files the data is in the ‘ADJUSTED_INTENSITY_INDEX' column. The Department has asked for the following specific information: (i) a table that shows both the NEM mean and standard deviation values for the month of March, for each year from 2016 to 2024 inclusive; and (ii) an estimate of the trend change in the mean NEM IBEI value over the period 2016 to 2024 inclusive, derived from a linear regression model where the dependent variable is the log of the mean March NEM IBEI value and the explanatory variable is Year. Note: this estimate is derived from a linear regression model that uses the mean values used in the Table.

In terms of reporting, you need a single table for part (i); and for part (ii) you need to construct a single sentence, that includes the point estimate information, and also a statement about whether or not the estimate is statistically different from zero. Report to 3 decimal places. The data required for this question (Total question marks 5)

Note: to answer this question you will need to download a data file for each year, and then work through some data management steps.