Lab 7

Published

2025-01-09

General Instructions

  • Submit your work via Canvas.
  • The deadline for this Lab is specified on the Course Calendar.
    • We charge a 5 point penalty for a lab that is 1-48 hours late.
    • We do not grade work that is more than 48 hours late.
  • Your response should include a Quarto file (.qmd) and an HTML document that is the result of applying your Quarto file to the data we’ve provided.
Important

You can skip exactly one of Labs 1-5 without penalty, but all students must complete both Lab 6 and Lab 7.

Template

You should be able to modify the Lab 3 Quarto template available on our 432-data page to help you do this Lab.

Our Best Advice

Review your HTML output file carefully before submission for copy-editing issues (spelling, grammar and syntax.) Even with spell-check in RStudio (just hit F7), it’s hard to find errors with these issues in your Quarto file so long as it is running. You really need to look closely at the resulting HTML output.

The Data

  • The chr_2015.csv csv file (from Lab 1), hbp3024.xlsx Excel file (from Lab 2), nh_1500.Rds R data set (from Lab 3) and the remit48.sav SPSS file all appear on the 432 data page.
  • A detailed codebook for all of the data in the chr_2024 file is available here.
  • A detailed description of each variable in the hbp3024 data is available here.
  • A detailed description of each variable in the nh_1500 data is available here.
  • The variables included in the remit48 data are described in Question 4, below.

Question 1. (14 points)

Use the chr_2015 data to build a model to predict each county’s percentage of the population ages 16 and older who are unemployed but seeking work, as measured in 2013 (and reported in CHR 2015). Note that each of the values in the data are integers (that fall between 1 and 28), and so we will treat the unemp values as if they were counts in Question 1. Use two quantitative predictors in your model: the county’s food environment index and the county’s adult obesity rate. You will produce two models for unemp using the two predictors, a Poisson regression model, and a quasi-Poisson regression model.

  1. {5} Produce the Poisson regression model, which I’ll call mod1, then interpret the coefficient (the point estimate is sufficient) for the food_env variable.

  2. {5} Produce and interpret the meaning of a rootogram for mod1, and specify the model’s \(R^2\) value.

  3. {4} Use mod1 to make a prediction for Cuyahoga County, in Ohio, based on Cuyahoga’s values for food_env (6.7) and for obesity (28) and compare the prediction to the observed unemp for Cuyahoga County as reported in 2013 as part of CHR 2015.

Question 2. (12 points)

Import the data from the hbp_3024.xlsx file into R, being sure to include NA as a potential missing value when you do, since all missing values are indicated in the Excel file with NA. Next, create a data set I’ll call q2dat, which:

  • restricts the hbp_3024 data to only the 1296 subjects who were seen in one of three practices, specifically: Center, King or Plympton, and
  • includes only those 1284 subjects from those three practices with complete data on the three variables we will study in Question 2, specifically income, insurance and practice.

  1. {6} Using your q2dat data set, build a multinomial logistic regression model to predict practice (a nominal categorical outcome) for each of the 1284 subjects on the basis of main effects of the subject’s insurance and income.

  2. {6} Then produce a classification table for the 1284 subjects which compares their actual practice to their predicted practice so that you can specify (in a complete sentence) how well the model classifies the data.

Question 3. (12 points)

Use the nh_1500 data to predict self-reported overall health (which is a five-category ordinal categorical outcome) on the basis of the subject’s age, waist circumference, and whether or not they have smoked 100 cigarettes in their lifetime. The R data for health are ordered to produce the following order:

nh_1500 |> tabyl(health)

    health   n   percent
 Excellent 138 0.0920000
    V_Good 404 0.2693333
      Good 646 0.4306667
      Fair 264 0.1760000
      Poor  48 0.0320000

  1. {6} Produce two proportional odds logistic regression models. The first, which I’ll call mod3a, should use all three predictors to predict health, while the second model, called mod3b, should use only two predictors, leaving out age. In each case, interpret the meaning of the point estimate for waist circumference.

  2. {6} Validate the C statistic and Nagelkerke \(R^2\) for each of your models using a bootstrap procedure with the default number of iterations and a seed set to 2025. Specify your conclusion about which model looks better on the basis of this work.

Question 4. (12 points)

The remit48.sav gathers initial remission times, in days (the variable is called days,) for 48 adult subjects with a leukemia diagnosis who randomly allocated to one of two different treatments, labeled Old and New. Some patients were right-censored before their remission times could be fully determined, as indicated by values of censored = “Yes” in the data set. Note that remission is a good thing, so long times before remission are bad.

  1. {6} Plot appropriate Kaplan-Meier estimates of the survival functions for each of the two treatments.

  2. {6} Then write (at least two) complete sentences explaining and providing context to accompany your estimates and plots. Do not use a regression model.

Use of AI

If you decide to use some sort of AI to help you with this Lab, we ask that you place a note to that effect, describing what you used and how you used it, as a separate section called “Use of AI”, after your answers to our questions, and just before your presentation of the Session Information. Thank you.

Be sure to include Session Information

Please display your session information at the end of your submission, as shown below.

xfun::session_info()
R version 4.4.2 (2024-10-31 ucrt)
Platform: x86_64-w64-mingw32/x64
Running under: Windows 11 x64 (build 22631)

Locale:
  LC_COLLATE=English_United States.utf8 
  LC_CTYPE=English_United States.utf8   
  LC_MONETARY=English_United States.utf8
  LC_NUMERIC=C                          
  LC_TIME=English_United States.utf8    

Package version:
  base64enc_0.1.3   bslib_0.8.0       cachem_1.1.0      cli_3.6.3        
  compiler_4.4.2    digest_0.6.37     evaluate_1.0.3    fastmap_1.2.0    
  fontawesome_0.5.3 fs_1.6.5          glue_1.8.0        graphics_4.4.2   
  grDevices_4.4.2   highr_0.11        htmltools_0.5.8.1 htmlwidgets_1.6.4
  jquerylib_0.1.4   jsonlite_1.8.9    knitr_1.49        lifecycle_1.0.4  
  memoise_2.0.1     methods_4.4.2     mime_0.12         R6_2.5.1         
  rappdirs_0.3.3    rlang_1.1.4       rmarkdown_2.29    rstudioapi_0.17.1
  sass_0.4.9        stats_4.4.2       tinytex_0.54      tools_4.4.2      
  utils_4.4.2       xfun_0.50         yaml_2.3.10

After the Lab

  • We will post an answer sketch to our Shared Google Drive 48 hours after the Lab is due.
  • We will post grades to our Grading Roster on our Shared Google Drive one week after the Lab is due.
  • See the Lab Appeal Policy in our Syllabus if you are interested in having your Lab grade reviewed, and use the Lab Regrade Request form specified there to complete the task. Thank you.