stroke_reduced: Simulated case control dataset for 6856 stroke cases and 6856...
In graphPAF: Estimating and Displaying Population Attributable Fractions

stroke_reduced

R Documentation

Simulated case control dataset for 6856 stroke cases and 6856 stroke controls

Description

Dataset containing simulated data on risk factors for 6856 stroke cases and 6856 stroke control, based on risk factors and associations in the INTERSTROKE study

Usage

stroke_reduced

Format

A data frame with 13712 rows and 19 variables:

region: Geographic region, 1: Western Europe, 2: Eastern/central Europe/Middle East 3: Africa, 4: South Asia, 5: China, 6: South East Asia, 7: South America
case: case control status, (1 for stroke cases)
sex: Gender of individual, 0: male, 1:female
age: Age of individual
smoking: Smoking status, 0: Never, 1: Current
stress: 1: sometimes stressed, 0: never stressed
waist_hip_ratio: Waist hip ratio
exercise: Physical Activity. 1: mainly inactive, 0: mainly active
alcohol: Alcohol history and frequency, 1:never, 2:low/moderate, 3:high intake
diabetes: Diabetes, 0: No, 1: Yes
diet: Healthy eating score (higher is better)
early_stage_heart_disease: presence of risk factors for heart disease. 0: No, 1: yes
lipids: Ratio of Apolipoprotein B to Apolipoprotein A
education: Years of education. 1: No education, 2: 1-8 years, 3:9-12 years, 3:Technical college, 4: University
high_blood_pressure: Diagnosed hypertension: 0 No, 1: yes
weights: weights that are proportional to inverse sampling probabilities. We have scaled the weights to be 0.0035 for a case and 0.9965 for a control to reflect any approximate incidence of 1 serious stroke in every 0.9965/0.0035 person years in the population
time: simulated time variable (for illustrating survival models)
event: simulated event indicator (0 if censored, 1 if event happened): for illustrating survival models
strata: Strata number based on sex and region. For illustrating conditional regression