Submit the assignment by the due date via Canvas. Assignments may be submitted up to 72 hours late for a 5 point reduction.
All files read, sourced, or referred to within scripts should be assumed to be in the same working directory (./).
Your code should be clearly written and it should be possible to assess it by reading it. Use appropriate variable names and comments. Your style will be graded using the style rubric [15 points].
Some of these exercises may require you to use commands or techniques that were not covered in class or in the course notes. You can use the web as needed to identify appropriate approaches. Part of the purpose of these exercises is for you to learn to be resourceful and self sufficient. Questions are welcome at all times, but please make an attempt to locate relevant information yourself first.
Please use the provided templates.
This assignment should be done primarily in SAS, with the exception that the write up and any associated figures or tables may be produced in R. As always you may use the Linux shell for data preparation and download documentation.
Your submission should include a write-up as a pdf or HTML document and all scripts needed to reproduce it. In your document, describe how the files submitted relate to one another and be sure to answer the questions.
For this assignment, scripts you should submit are: SAS (.sas), Rmarkdown (.Rmd or .R with spin) for the write-up, the write up itself (.pdf or .html), and (optionally) a shell script (.sh) ps4_make.sh to build the assignment.
This question is a modified version of question 1 from problem set 2. It is worth fewer points because the grouping structure is simplified and you should be able to adapt code for creating figures and tables from the earlier assignment.
Use the 2009 and 2015 Residential Energy Consumption Survey RECS data to profile the quantities and types of televisions in US homes, by Census Region.
TVCOLOR) in US homes in 2009 and 2015 by Census Region.
TVTYPE1).Notes:
Remember, to compute the variance of the differences, you should assume the 2009 and 2015 estimates are independent. That is if \((\hat \theta_1, \hat v_1)\) and \((\hat \theta_2, \hat v_2)\) are the estimates and variances for 2009 and 2015, respectively, then the differences and their variances are: \((\hat \theta_2 - \hat \theta_1, \hat v_1 + \hat v_2)\).
You may adapt either your own code or the solutions for problem set 2 for the figures and tables. In either case, please provide a clear citation in your write up, e.g. “A portion of this solution is adapted from (my or Dr. Henderson’s) solution to PS2 Question 1.”
Use proc export or a similar procedure to to output your results in SAS to be read into your write-up document.
In this question you will use the NHANES dentition and demographics data from PS3.
[10 points] Pick a single tooth (OHXxxTC) and model the probability that a permanent tooth is present as a function of age using logistic regression. For this part (“a”), assume the data are iid and ignore the survey weights. You should consider non-linear transforms of age but only need to document your final model in the write up. Control for other demographics included in the data as warranted.
[10 points] Refit your model from part a using proc surveylogistic to account for the weights. See the notes below for links to example code.
[5 points] In your write up, provide a side-by-side comparison of the results when using or ignoring the survey weights. This could be either a figure or a table (one will suffice).
Stats506_F20 repository under problem_sets/data/. You will need the following two files:
nahanes_demo.csvnhanes_ohxden.csvmec weights included in the data from the course repo.