Lab 2 Rubric

Total: 18 points
Each row is scored from 0–3 points based on the criteria.

Lab Activity	3 points	2 points	1 point	0 points
Restate project type	Identifies project type. If purposeful: research question follows the 1-sentence format and provides clear context.	Identifies project type. If purposeful: question has minor phrasing or format issues.	Project type identified. If purposeful: question is vague or improperly structured.	Missing or unclear.
Make sure variables are coded correctly	All variables checked via map() or class(). Outcome is a factor with “No” as reference level. All types (factor/numeric) are correct.	Most variables checked/recoded correctly; minor error in one variable type or reference level choice.	Variable types checked but not corrected, or reference level is incorrect for the outcome.	Does not check or recode variable types.
Table 1: For purposeful model selection only	Table 1 is recreated with correct variable types; dichotomous variables correctly show both “Yes” and “No” levels.	Table 1 recreated but missing “Yes/No” formatting or has minor alignment/display issues.	Table 1 attempted but contains incorrect variable types or major formatting errors.	Table 1 is missing or unchanged from Lab 1.
Consider potential confounders and effect modifiers	Table/list is complete for all 10 variables (or LASSO ranking); reasoning is thoughtful and logically sound for the context.	Completes most entries with reasonable reasoning; a few entries are thin or slightly illogical.	Table is incomplete or reasoning lacks clarity/depth.	Table is missing or mostly incorrect.
Bivariate exploratory data analysis	Uses ggpairs() and contingency tables; explicitly notes cells with < 10 observations; identifies tests for numeric distributions.	Performs EDA but fails to note small cell counts or lacks insight into numeric distribution testing.	Attempts EDA but contains errors, missing tables, or output is unorganized/hard to read.	No exploratory analysis completed.
Fit simple logistic regression	Correctly fits model with glm(); displays and interprets ORs and 95% CIs with contextual accuracy.	Model fit correctly; interpretation is basic, lacks context, or has minor phrasing issues.	Model/output has major issues; interpretation is missing or ignores confidence intervals.	Model not attempted or entirely incorrect.
Plot the predicted probability	Accurately plots or tables predicted probabilities; clear labeling and formatting that reflects the main independent variable.	Produces plot/table with minor issues in clarity, labeling, or aesthetic accuracy.	Attempt made, but result is confusing or represents log-odds instead of probability.	No plot or table presented.