4. Methods

Purpose

Explain the analytical or statistical methods applied.

Details

Statistical Analysis: We employ a multivariable logistic regression model to estimate the association between patient factors and the likelihood of a missed appointment.

The model is defined as:

\[ \text{logit}(P(Y=1)) = \beta_0 + \beta_1(\text{age}) + \beta_2(\text{lead\_time}) + \beta_3(\text{appointment\_type}) + \beta_4(\text{previous\_missed}) + \beta_5(\text{deprivation}) \]

Where \(P(Y=1)\) is the probability of a missed appointment.

Example Code Implementation: The following is an illustrative example of the modeling code used (not executed in this document):

# Fit logistic regression model
model <- glm(missed_appointment ~ age + lead_time_days + 
             as.factor(appointment_type) + previous_missed + 
             as.factor(deprivation_quintile), 
             data = synthetic_data, 
             family = binomial(link = "logit"))

# Display summary
summary(model)

---

NoteAI Capability Checkpoint

Ethics, Equity & Impact: While AI tools assisted in drafting the model text and LaTeX equations, the selection of logistic regression was a human choice appropriate for binary outcomes. We carefully reviewed the output to ensure the equation accurately reflected the intended study variables.