First, calculate basic statistics for each group, such as average and standard deviation. The average of the two groups for 4 biomarkers are different. The cancerous group has larger standard deviations for AFP, CEA, and CA50, while the opposite is true for CA125. Descriptive statistics only provide limited information on a variable. Next, analyze histograms to capture a richer picture of the variables. Separate cancerous and benign groups to find differences in biomarkers. Calculate average and standard deviation to determine the center and spread of each group. Pivot tables alone cannot explain which biomarkers are most predictive. Use scatterplots and Excel's data analysis tool to analyze frequency, percentage, and cumulative percentage distributions. Line graphs and histograms visually break down the data. Compare cumulative percentage distributions between cancerous and benign patients. More differences increase predictability of cancer. Ultimately, CEA is the most predictive biomarker for cancer with the widest distribution