英国统计作业代写 STA 104代写 Final Project代写

STA 104 Final Project, due

Wednesday, December 16^th at 6:00pm CA time

英国统计作业代写 Suggestions: Consider the effect of smoothing parameters. Consider the implications and limitations of your analysis.

Read the following instructions carefully:

You may work in a group of two, or by yourself.
You may discuss any part of the project with the instructor or TA and your groupmate. You may discuss coding issues and tips, and brainstorm ideas with the rest of the class on Piazza. If you are concerned you may be giving something away, email me or the TA’s directly.
You are allowed to use or modify your previous functions, or the instructor’s functions that are posted online. In general you may refer to reference texts such as books and manuals, but everything in the report should be your own words and demonstrate your own understanding of the material. 英国统计作业代写
If you reference posts on Piazza, please cite them in your report.
Do NOT share or ask for speciftc answers, values for calculations, or signiftcant chunks of code on Piazza or elsewhere.
Any outside help beyond the above is considered plagiarism. This including asking a tutor, your classmates, posting the questions to homework help sites, etc. Should we believe you have sought outside help, you will be reported to the Student Judicial Affairs office.
Submit a single group submission on Canvas. This also means you and your partner will get the same grade (assuming you have a partner). You are responsible for your own work, and your partner’s work.

Topic I: Theoretical task 英国统计作业代写

This topic is to demonstrate either your synthesis of the course material with previous statistical courses, or your synthesis of the course material core concepts. Select ONE of the following subtopics to do:

Subtopic 1: Developing a permutation test

In class, we learned about permutation tests comparing differences between measures of centrality. The book mentioned that these tests cannot specifically test a difference in variances while also comparing a difference in centrality. However, permutation tests are very general and can in fact test a difference in variance.

Propose a permutation test to test the difference in variance between two samples, and demonstrate an example. 英国统计作业代写

Suggestions: Take inspiration from how lectures introduce a new test: you should introduce the problem to address, assumptions, hypotheses, the test statistic, the p-value calculation, etc.

Subtopic 2: Simulation study of parametric vs. nonparametric methods for bivariate data

Conduct a simulation study to compare the performance of parametric vs. nonparametric methods for bivariate data. You may use as your measure of performance the percentage of times your hypothesis test rejects H₀ when H₀ is true and when H₀ is false. 英国统计作业代写

Suggestions: Refer to the simulation study in class. Consider the effect of different sample sizes and distributions. For a complete answer, you must consider non-Normal data. Arrange the comparison of results clearly. Consider the relative importance of Type I and Type II errors. You may use the following code to generate from a double exponential distribution, which has heavy tails:

rexptt <- function(n = 1, center = 0, rate = 1){  mult <- sample(c(-1, 1), n, replace  =  TRUE) mult * rexp(n, rate) + center

}

Subtopic 3: Simulation study of using paired tests vs. independent samples tests

Conduct a simulation study to compare the performance of using a two-sample test vs. a paired test on paired data. Use nonparametric tests for both. For a fixed α, you may use as your measure of performance the percentage of times your hypothesis test rejects H₀ when H₀ is false.

Suggestions: Refer to the simulation study in class. Consider the effect of different parameters of the true data. Feel free to modify the following code to generate your various simulated datasets:

makeSimData <- function(n, mu_x,  mu_d,  sd_d){ # Simulate X

x <- rexp(n, rate = 1/mu_x)

# Simulate Y

d <- rnorm(n, mean = mu_d, sd = sd_d)     y <- x - d




mydata <- data.frame(x = x, y = y) return(mydata)

}

Topic II: Data analysis task: Living conditions 英国统计作业代写

This topic is to demonstrate your ability to conduct and explain a real-world analysis. Questions are left vague on purpose; there is no one right answer.

Data was collected to investigate aspects of living conditions for several countries. (Vasilescu and Wainer, 2005). The dataset is provided in crowdedness.csv. It contains the following columns:

Country: The countryname
Crowdedness: The average number of persons per room living inhomes
fertility: The fertility rate (live births born per woman of a certain age peryear)
GDP: Gross domestic product, indicating the wealth of the nation

Pleaseperform the following tasks in your report:

1.We note that there are missing values in Crowdedness. Using a smoothing method, provide an estimate for the missing values using GDP as your predictor. 英国统计作业代写

2.Analyze fertility and the relationship between GDP and Do not use a smoothing method for this task. You may remove the observations where fertility ismissing.

Suggestions: Consider the effect of smoothing parameters. Consider the implications and limitations of your analysis.

Each question should be a short report. This means you write in full sentences, and have the following sections for each question, while being as speciftc as you can about your results. There should not be any “copy and pasted” R code in this report. You must format the results you get from R..

The Report Format 英国统计作业代写

The basic format suggestion from previous reports is still very relevant to the data analysis task and is as follows:

I. State the question you are trying to answer, why it is a question of interest (why might we be interested inthe answer), and what statistical technique you are going to use. This must be a non-parametric technique.

II.Summary of your data (and only the data you are using for the question). This could include things like plots (histograms,boxplots) including the interpretation of the plots, and summary values such as sample means and standard deviations. This is where you should justify which non-parametric technique you are using. An R handout is available online for graphing and summaries of various data types.

III.Report back confidence intervals, test-statistics, and p-values, nulls and alternatives, etc. You may use tables here, but be sure that you organize your work. Remember to write your results in full sentences wherepossible. 英国统计作业代写

IV.State your conclusion, and inference that you may draw from your corresponding tests or confidence intervals. These should all be in terms of yourproblem.

V.Summarize briefly your findings. Here you do not have to reiterate your numeric values, but summarize all relevantconclusions.

IV.If you’re in a group, briefly list the parts of the report that you individually contributed to.

The basic idea of this format can also be applied to the first topic, but naturally will have more deviations. Once you have an outline of how you might approach and format the first task (preferably both your tasks/subtopics), I encourage you to send me your outline and/or make a 10 minute appointment with me to go over your idea.

Details 英国统计作业代写

Your report should be the following format:

i.Typed.

ii.Atitle page/large header including your name/s, the name of the class, and the name of your instructor (me).

iii.Treat each question as a small, standalone report. 英国统计作业代写

iv.An appendix of your R code used to produce the results. Do not include any R code in the body of your report. For example, your project could be put together in the followingorder:

Cover Page

First report

Second report

Contributions

Code appendix

合作平台：essay代写论文代写写手招聘英国留学生代写