CFA Quant: Statistical Asset Return Metrics

CENTRAL TENDENCY AND DISPERSION:  

  1. Central Tendency
  • Arithmetic Mean: Average of values; sensitive to outliers. 
  • Median: Middle value in an ordered dataset; better than mean when data has outliers. 
  • Mode: Most frequent value; datasets can be unimodal, bimodal, or trimodal. 
  1. Dealing with Outliers
  • Trimmed Mean: Excludes extreme values from both ends. 
  • Winsorized Mean: Replaces extreme values with nearest percentiles. 
  1. Measures of Location
  • Quantiles: General term (e.g., quartiles, quintiles, percentiles). 
  • Interquartile Range: Difference between 75th and 25th percentiles. 
  • Box-and-Whisker Plot: Visual tool for showing data spread and potential outliers. 
  1. Dispersion (Risk)
  • Range: Difference between maximum and minimum values. 
  • Mean Absolute Deviation (MAD): Average absolute difference from mean. 
  • Sample Variance: Average of squared deviations (divided by n−1). 
  • Standard Deviation: Square root of variance; interpretable in original units. 
  • Coefficient of Variation (CV): Standard deviation divided by mean; allows comparison across datasets. 
  1. Downside Risk
  • Target Downside Deviation: Measures deviations below a specific target (e.g., the mean); focuses only on negative risk. 

SKEWNESS, KURTOSIS, AND CORRELATION:  

  • Symmetry in Distributions: A symmetrical distribution has equal frequency of gains and losses around the mean; asymmetry indicates skewness. 
  • Skewness Types
  • Positive Skew (Right-skewed): Outliers are above the mean; mean > median > mode. 
  • Negative Skew (Left-skewed): Outliers are below the mean; mean < median < mode. 
  • Skew affects the mean most and pulls it in the direction of the skew. 
  • Sample Skewness
  • Measures asymmetry using cubed deviations from the mean. 
  • Positive skewness means right-skewed; negative means left-skewed. 
  • Values > |0.5| are significant. 
  • Kurtosis
  • Measures peakedness of a distribution. 
  • Leptokurtic: More peaked with fatter tails; Platykurtic: Flatter; Mesokurtic: Normal kurtosis. 
  • Excess Kurtosis = Kurtosis − 3; used to compare with normal distribution. 
  • Higher excess kurtosis and negative skew increase investment risk. 
  • Scatter Plots & Correlation
  • Scatter plots visualize variable relationships; can show linear and nonlinear patterns. 
  • Correlation coefficient (ρ) standardizes covariance, ranges from −1 to +1. 
  • ρ = +1 (perfect positive), ρ = −1 (perfect negative), ρ = 0 (no linear relationship). 
  • Correlation Considerations
  • Correlation ≠ causation. 
  • Outliers can distort correlation. 
  • Spurious correlation may occur due to a third variable or random chance (e.g., humorous examples from Tyler Vigen). 

KEY CONCEPTS : 

  • Measures of Central Tendency
  • Mean: Arithmetic average; sample mean applies to a sample. 
  • Median: Middle value in ordered data. 
  • Mode: Most frequent value; modal interval used for continuous data. 
  • Trimmed/Winsorized Mean: Reduce outlier impact by omitting or capping them. 
  • Quantiles
  • Values dividing data: quartiles (4 parts), quintiles (5), deciles (10), percentiles (100). 
  • Measures of Dispersion
  • Range: Difference between max and min. 
  • MAD: Average absolute deviation from the mean. 
  • Variance/Standard Deviation: Average squared deviation and its square root. 
  • Coefficient of Variation (CV): Ratio of standard deviation to mean. 
  • Semideviation: Measures downside risk. 
  • Skewness and Kurtosis
  • Skewness: Right-skewed (mean > median > mode); left-skewed is the reverse. 
  • Kurtosis: Measures tail weight; leptokurtic (fat tails), platykurtic (thin tails). 
  • Excess Kurtosis: Compared to normal distribution kurtosis of 3. 
  • Correlation
  • Measures linear association (−1 to +1). 
  • Scatter plots show nonlinear trends. 
  • Correlation ≠ causation; spurious correlations may arise. 

Leave a comment