Leukemia Remission Dataset

A dataset containing information about leukemia remission and associated risk factors. This dataset is commonly used for demonstrating logistic regression analysis in medical research.

data(remission)

Format

A data frame with 27 observations and 7 variables:

remiss

Binary outcome variable indicating leukemia remission status:

• 1 = Remission occurred

• 0 = No remission

cell

Numeric. Cellularity of the marrow clot section (percentage)

smear

Numeric. Smear differential percentage of blasts

infil

Numeric. Percentage of absolute marrow leukemia cell infiltrate

li

Numeric. Percentage labeling index of the bone marrow leukemia cells

blast

Numeric. Absolute number of blasts in the peripheral blood

temp

Numeric. Highest temperature (in Fahrenheit) before treatment

Source

Lee, E. T. (1974). "A Computer Program for Linear Logistic Regression Analysis." Computer Programs in Biomedicine 4:80–92.

Details

This dataset is particularly useful for:

• Demonstrating logistic regression analysis

• Studying risk factors for leukemia remission

• Teaching medical statistics and predictive modeling

References

• Lee, E. T. (1974). "A Computer Program for Linear Logistic Regression Analysis." Computer Programs in Biomedicine 4:80–92.

• Penn State University Statistics Online. "Logistic Regression Example." https://online.stat.psu.edu/stat501/book/export/html/1011

Examples

if (FALSE) { # \dontrun{
# Load the dataset
data(remission)

# View first few rows
head(remission)

# Summary statistics
summary(remission)

# Run logistic regression
model <- glm(remiss ~ ., data = remission, family = binomial)
summary(model)
} # }