Tag Archives: Predict cardiac attack using the included variables.

Cardiac Study Logistic Regression

For this exercise, you will be using the data set for the Cardiac study described in Chapter 13 (Activity 13.1) in your Statistics for the Health Sciences text.

Download Data Files

• Download the Data Files for Chapter 13 [ZIP].
• Select the appropriate data sets for each statistical test you need to perform. Please take some time to explore each data set to see how it was constructed.

Complete Exercises

Use this week’s readings and multimedia resources to complete the following:

• Logistic regression using data from the Cardiac study.
  • Predict cardiac attack using the included variables.
    

File Submissions

• For each exercise, upload the .jasp file with correct analyses and output saved.
  • Upload a separate Word document that includes appropriate graphics or tables copied from the output and pasted into the Word document. Interpret and report the test results in properly formatted APA style.aq`1““““““““““““““`aaaaa~aA`

    • Logistic regression using data from the Cardiac study., Predict cardiac attack using the included variables., For each exercise upload the .jasp file with correct analyses and output saved., Upload a separate Word document that includes appropriate graphics or tables copied from the output and pasted into the Word document., Interpret and report the test results in properly formatted APA style.

    ---

    Comprehensive General Answer

    1. Logistic Regression Using the Cardiac Study Data

    Logistic regression is used to model the probability of a binary outcome, in this case cardiac attack (yes/no). Unlike linear regression, logistic regression produces odds ratios, which show how the likelihood of an outcome changes with each independent variable. For the Cardiac study, common predictors may include:

    • Age

    • Sex

    • Smoking status

    • Cholesterol levels

    • Blood pressure

    • Weight/BMI

    • Physical activity level

    • Pre-existing cardiovascular conditions

    The dependent variable is coded 1 = cardiac attack and 0 = no cardiac attack.

    Import the relevant dataset into JASP and run a Binary Logistic Regression, choosing cardiac attack as the outcome and the other risk factors as predictors.

    ---

    2. Predicting Cardiac Attack

    The logistic regression model estimates how each predictor contributes to the odds of having a cardiac attack. Each coefficient shows whether the predictor increases or decreases risk when holding other variables constant.

    A typical output will present:

    • Beta coefficients (B)

    • Standard errors

    • Wald p-values

    • Exp(B) values (Odds Ratios)

    Interpretation Example (General):

    • Age (OR > 1): If older age has an odds ratio significantly greater than 1, then the risk of cardiac attack increases with age.

    • Smoking (OR > 1): A statistically significant positive OR indicates smokers are more likely to have a cardiac attack.

    • Exercise (OR < 1): An odds ratio less than 1 indicates exercise reduces the probability of a cardiac attack.

    A variable is typically significant when its p-value is less than .05.

    ---

    3. Output & .jasp File Submission

    While working in JASP:

    • Ensure all predictors are entered into the model.

    • Save the entire project as a .jasp file.

    • Make sure it includes the regression model, tables, and summary statistics.

    This file demonstrates your analytic steps and must be uploaded separately as required.

    ---

    4. Creating the Word Report

    Your Word document should include:

    A. Output Tables

    Copy and paste:

    • Model summary (Nagelkerke R²)

    • Parameter estimates (Odds Ratios)

    • Classification accuracy

    • Confusion matrices (if provided)

    B. Graphical Visualizations (Optional)

    You may paste:

    • Predicted probability plots

    • Receiver Operating Characteristic (ROC) curve

    • Scatter or density distribution of predictors

    Graphs should clearly support your interpretation.

    ---

    5. APA Interpretation Example (General Format)

    A binary logistic regression was conducted to examine whether age, smoking status, cholesterol levels, and physical activity predicted cardiac attack. The overall model was statistically significant, χ²(df) = XX.XX, p < .001, indicating that the predictors reliably distinguished between individuals with and without cardiac attack. The model explained XX% of the variance in cardiac risk (Nagelkerke R² = .XX) and correctly classified XX% of cases.

    Smoking significantly increased the odds of a cardiac attack (OR = X.XX, p = .XXX), suggesting smokers were approximately X times more likely to experience a cardiac event than non-smokers. Age was also a significant predictor (OR = X.XX, p < .001), with each additional year associated with a higher probability of cardiac attack. In contrast, physical activity reduced the odds of cardiac attack (OR = X.XX, p < .05). Cholesterol levels were not statistically significant (p > .05).

    These results indicate lifestyle and age-related risk factors contribute substantially to cardiac outcomes and may benefit from targeted preventive interventions.

    ---

    Final Notes

    • Use at least APA 7th edition formatting.

    • Do not present raw JASP screenshots without interpretation.

    • Clearly label tables copied from the output.

    • Discuss whether the model performs well and whether predictors are clinically meaningful, not only statistically significant.

    If you’d like, I can help:
    ✔️ Review your exported JASP results
    ✔️ Write your APA-style interpretation based on your actual numbers
    ✔️ Help format your Word document or tables

    Just upload your output or paste your results.