Calculator Inputs
Example Data Table
| Case | Age | Smoker | BMI | Visits | Glucose | Exercise Flag | Outcome |
|---|---|---|---|---|---|---|---|
| 1 | 42 | 1 | 28 | 2 | 150 | 0 | 1 |
| 2 | 35 | 0 | 24 | 1 | 118 | 1 | 0 |
| 3 | 57 | 1 | 31 | 4 | 168 | 0 | 1 |
| 4 | 29 | 0 | 22 | 0 | 96 | 1 | 0 |
| 5 | 48 | 1 | 27 | 3 | 142 | 0 | 1 |
This sample shows binary outcomes with mixed continuous and indicator predictors.
Formula Used
Linear score: z = β0 + β1x1 + β2x2 + ... + βnxn
Probability: p = 1 / (1 + e-z)
Odds: odds = p / (1 - p)
Odds ratio for each predictor: OR = eβ
The calculator converts the linear score into a probability between zero and one, then compares that probability with your chosen threshold.
How to Use This Calculator
- Enter the model intercept from your logistic regression output.
- Fill in each predictor coefficient and its observed value.
- Choose a classification threshold, such as 0.50.
- Select the actual class if you want a quick correctness check.
- Press the calculate button to view probability, odds, and class.
- Use the CSV or PDF buttons to save the displayed results.
Why Use Logistic Regression
Logistic regression estimates the probability of a binary event. It is widely used for classification problems where outcomes are coded as zero or one, such as approval, disease presence, conversion, churn, or defect detection.
This page focuses on applying an existing model rather than training a new one. It helps translate coefficients into understandable probabilities and odds ratios.
Frequently Asked Questions
1. What does the probability represent?
It represents the estimated chance that the outcome equals one, based on the intercept, coefficients, and predictor values you entered.
2. What is the linear score?
The linear score, or logit input, is the weighted sum of the intercept and predictor contributions before the logistic transformation converts it into probability.
3. Why is the threshold important?
The threshold decides when a probability becomes class one. Lower thresholds increase positive predictions, while higher thresholds make predictions more conservative.
4. What does an odds ratio mean?
An odds ratio shows how the odds change for a one-unit increase in a predictor, holding the other predictors constant.
5. Can I use negative coefficients?
Yes. Negative coefficients reduce the linear score and lower the estimated probability when the related predictor increases.
6. Does this calculator train a model?
No. It evaluates a logistic regression model using coefficients you already know from prior analysis or published output.
7. How many predictors can I enter?
This version supports six predictors plus an intercept, which is enough for many classroom, screening, and planning examples.
8. When should I export the results?
Export results when you need to document assumptions, compare scenarios, share calculations, or archive outputs for reports and audits.