Assignments


Homework08: (complete by Monday December 2)

For the math problems, scan your handwritten work to one .pdf file.

Additional Exercise 1: Submit your .html and .qmd files.

Using the code in the Handout: Likelihood Ratio Test examples

Change the Reduced Model to include be the model with ‘hp’ and ‘cyl’. And for the Logistic Regression change the model to include ‘spontaneous’.

Determine the results of the tests.


Homework07: (complete by Monday November 18)

For the math problems, scan your handwritten work to one .pdf file.

Additional Exercise 1: Submit your .html and .qmd files.

Run the following R code in the following R Quarto Notebook to simulate data and use the fitdistr function to estimate the parameters in the models from handout1a.pdf.

  1. Change the parameters used in each of the simulations and refit the models.

    1. Change theta <- 0.5 to a different value.
    2. Change theta <- 5 to a different value.
    3. Change theta <- 5 to a different value.
    4. Change theta <- 0.5 to a different value.

Additional Exercise 2: Complete the following problem in an R Quarto Notebook. Submit your .html and .qmd files.

Note: The solution to the Additional Exercise 2 has been posted in Canvas.

Note: The R package for the book fell off of CRAN April 2024. To install the package in R you can download the last version of the mistat archive and Install From: Package Archive File .tar.gz


Homework06: (complete by Monday November 4)

For the math problems, scan your handwritten work to one .pdf file. For the code problems, if you are using Colab, submit a .docx file containing the shared link to your Colab Notebook.


Homework05: (complete by Monday October 14)

For the math problems, scan your handwritten work to one .pdf file. For the code problems, if you are using Colab, submit a .docx file containing the shared link to your Colab Notebook.

Additional Exercise 1: (L.L.N.) Demonstrate the Law of Large Numbers for the Normal Distribution.

Additional Exercise 2: (C.L.T.) Demonstrate the Central Limit Theorem for the Normal and Exponential Distributions.

Additional Exercise 3: Demonstrate the independence of the sample mean and sample variance when sampling from the \(Normal(\mu = 5, \sigma^2 = 2^2 = 4)\).


Homework04: (complete by Monday September 23)

For the math problems, scan your handwritten work to one .pdf file. For the code problems, if you are using Colab, submit a .docx file containing the shared link to your Colab Notebook.


Homework03: (complete by Monday September 16)

For the math problems, scan your handwritten work to one .pdf file. For the code problems, if you are using Colab, submit a .docx file containing the shared link to your Colab Notebook.

Hint: For 2.27, assume that a stick being randomly broken at two spots is equivalent to randomly selecting two points on a stick. Assume the length of the stick is 1. Assume that the two points are uniformly distributed on the stick. What is the probability that the three pieces can form a triangle?

Try using Colab Generate to produce Python code to simulate the probability of the three pieces forming a triangle. You can use the following code Prompts to get started.

Prompts

  1. prompt: Using Python code simulate data from a bivariate distribution where the input variable has a Poisson distribution with mean 100 and the distribution of X given N is Binomial with p = 0.95. Plot a scatterplot of the simulated data.

  2. prompt: Fit a linear regression model to the data.

  3. prompt: Fit the same model without an intercept term.

  4. prompt: Compute the mean and standard deviation of the X data.

  5. prompt: Make prediction of X given N = 75 and N = 120.


Homework02: (complete by Wednesday September 4)

For the math problems, scan your handwritten work to one .pdf file. For the code problems, if you are using Colab, submit a .docx file containing the shared link to your Colab Notebook.

Additional Exercise 1: Using Python verify that these models are the same: GAMMA(\(\alpha = n/2, \beta = 1/2\)) = CHISQ(\(n\)). To show this compute the cumulative probabilities for the two models using the same value of \(x\) and parameter \(n\).


Homework01: (complete by Monday Aug. 26)

For the math problems, scan your handwritten work to one .pdf file. For the code problems, if you are using Colab, submit a .docx file containing the shared link to your Colab Notebook.