Week 10

Other generalized linear regressions
Published

June 3, 2024

Modified

July 11, 2024

Room Locations for the week

On Monday, 6/3, we will be in RPV Room A (1217)

Resources

Lesson Topic Slides Annotated Slides Recording
16 Poisson Regression
17 Other types of categorical regressions!

On the Horizon

  • Quiz 3 open 6/3 at 2pm

    • Closes on 6/5 at 1pm
  • Lab 4 due yesterday!

  • HW 5 due 6/6 at 11pm

  • Project report due 6/13 at 11pm

Announcements

Monday 6/3

  • In the last stretch of the project

    • Class time next week dedicated to project report help

    • I may have other time slots for project help next week. I just need to take a serious look at my calendar

      • I’m attending a virtual stat ed conference, so I just need to balance meetings with conference attendance
  • No office hours this Wednesday 6/5

  • #3 “The Last Bounce: Bunnies, Burritos, and DIY Bath Salts”

    • Wednesday, June 5th Noon-2pm

    • Student Success Center, 6th floor Vanport

Wednesday 6/5

  • Last day of lecture!!

  • Quiz 2: added 3 points to everyone’s grade for that one confusing question (I forget the number, maybe question 6?)

  • Lab 4

    • Your starting variables should be the TEN from lab 2, not the 5 from Lab 3

    • g-value for Hosmer-Lemeshow test

      • Please look at Lesson 12!! There is a note on how to pick the g-value when we have many samples!!

      • Some of us are getting NA’s when we put the correct g

        • Double check that your observed values are in numeric form
    • If doing LASSO, make sure you describe the process!

      • We used LASSO regression with a penalty of 0.001 to identify important predictors. We used a single test and training split of 80% and 20%, respectively. Only main effects were considered in our LASSO regression.

      • Always think: what are the key pieces of information that someone else might need to recreate this method?

  • The class will end on June 14, 2024. All coursework is expected to be completed by June 16, 2024 at 11pm.

    • I need to have grades in on June 21st. In order to grade fairly and thoroughly, I need the whole week to grade the project report and any late assignments.
  • A word on project grading

    • In the final lab, I gave you the option to do LASSO regression and focus on prediction. I know this created some confusion since we mostly set up the project as a question of association in Lab 1-3. We can still interpret the odds ratios from LASSO regression. I will be fairly lenient if reports are confused between prediction and association aims. I will try to give feedback on it, but I will not penalize any minor confusions.

      Another word: My process starts harsh. I want to give you as much feedback as possible, and this will also reflect in lower assigned scores. At this point, I put the report grades into Sakai. I check to see if anyone’s overall course letter grade goes down. If less than ~5 course grades go down, then I revisit their project reports. If their report fails to demonstrate the most important learning objectives from the course, then I will keep the lower grade. If they demonstrate an understanding of the most important learning objectives, then I will adjust their score to increase their course grade. If more than 5 grades go down, then I revisit everyone’s reports. I will make a class wide grade bump in all reports.

    • The most important learning objectives are: understanding when and what test is appropriate, and interpreting odds ratios (from main effects and interactions)

  • Project: LASSO

    • You can take the finalized formula for LASSO and use it in glm()

      • In this case, use the test data to come up with predictive values (like AUC)

      • You can run it on the full dataset to get the coefficient estimates and other diagnostic information

  • Guide on figures

Class Exit Tickets

Monday (6/3)

Wednesday (6/5)

Muddiest Points