Miscellaneous: Biostatistics

Biostatistics

Statistics of a Set of Values

  • Mean: The Average of Set of Values
  • Median: The Numerically Middle Number of a Set of Values
  • Mode: The Most Commonly Repeated Number of a Set of Values
  • Range: The Difference Between the Highest & Lowest Numbers of a Set of Values
  • Standard Deviation: A Measure of the Amount of Variance in a Set of Values
    • Percent of the Population within One Standard Deviation of the Mean: 68.27%
    • Percent of the Population within Two Standard Deviation of the Mean: 95.45%
    • Percent of the Population within Three Standard Deviation of the Mean: 99.73%

Statistics of Disease Within a Population

  • Prevalence: Number of People with a Disease at a Given Time
  • Incidence: Number of New Cases of a Disease Over a Given Period of Time

Statistics of Test Performance

  • Values:
    • True Positive: A Patient with a Disease Tests Positive
    • False Negative: A Patient with a Disease Tests Negative
    • False Positive: A Patient without a Disease Tests Positive
    • True Negative: A Patient without a Disease Tests Negative
  • Table Format:
Patient Has Disease Patient Does Not Have Disease
Test Positive True Positives (TP) False Positives (FP)
Test Negative False Negatives (FN) True Negatives (TN)
  • Tests:
    • Sensitivity (Sn) = TP / (TP+FN)
      • If You Have the Disease, what is the Chance the Test Is Positive?
    • Specificity (Sp) = TN / (FP+TN)
      • If You Do Not Have the Disease, what is the Chance the Test is Negative?
    • Positive Predictive Value (PPV) = TP / (TP+FP)
      • If the Test is Positive, what is the Chance You Have the Disease?
    • Negative Predictive Value (NPV) = TN / (FN+TN)
      • If the Test is Negative, what is the Chance You Do Not Have the Disease?
  • Predictive Values (PPV & NPV) are Dependent on Prevalence in the Population Being Tested
    • Populations with Increased Prevalence will Have Increased PPV & Decreased NPV
    • Sensitivity & Specificity Are Not Affected by Prevalence

Statistics of Outcome

  • Odds Ratio: Prevalence in Exposed Group / Prevalence in Unexposed Group
    • Uses: Case Control
  • Relative Risk = Incidence in Exposed Group / Incidence in Unexposed Group
    • Uses: Cohort Study & Controlled Trials
    • Generally the More Clinically Relevant Parameter Over Odds Ratio if Available
  • Risk Reduction
    • Absolute Risk Reduction = Control Rate – Experimental Rate
    • Relative Risk Reduction = (Control Rate – Experimental Rate) / Control Rate
  • Number Needed to Treat (NNT)
    • The Number of Patients Needed to Treat to Prevent One Adverse Event
    • NNT = 1/Absolute Risk Reduction

Correlation Coefficient (r)

  • Measures the Strength of Relationship Between Two Variables
  • Range: -1 to +1
    • Negative Values: Negative Relationship (Inversely Proportional)
    • Positive Values: Positive Relationship (Directly Proportional)
  • Strength:
    • 0: No Relationship
    • 0.0-0.3: Negligible
    • 0.3-0.5: Weak
    • 0.5-0.7: Moderate
    • 0.7-0.9: Strong
    • 0.9-1.0: Very Strong