Third-Party Research & Methodology Only

This section shares summaries of third-party academic research and descriptions of quantitative models. The content represents the findings of the original researchers, not the opinions or recommendations of Foxholm Financial. Foxholm Financial does not publish hypothetical or backtested performance metrics on its quantitative research pages. All content is restricted to methodology, signal construction, factor logic, and risk architecture. SEC rules require that investment advisers not present misleading performance data, and our methodology-only approach reflects that standard and the firm's fiduciary obligations.

Variance

Statistical Measure Risk Measurement Academic Finance

Variance measures how far a set of numbers spreads out around its average. In finance, it quantifies how much an asset's returns scatter around their mean return, making it one of the oldest and most fundamental measures of risk. A larger variance means returns are more spread out and less predictable.

Variance sits at the mathematical core of modern portfolio theory. It is the quantity that mean-variance optimization seeks to minimize for a given level of expected return, and it is the building block from which standard deviation and volatility are derived. Understanding variance clarifies why diversification works and why some risks combine while others cancel.

Definition

Variance is the average of the squared differences between each return and the mean return. The squaring step matters: it makes every deviation positive, so gains and losses both add to the total spread rather than offsetting each other. It also gives extra weight to large deviations, which is why a few extreme moves can dominate the variance of a return series.

Key Principle

Variance is expressed in squared units, which makes it hard to interpret directly. The square root of variance, the standard deviation, restores the original units and is easier to read. Variance and standard deviation describe the same underlying spread; they differ only in scale and interpretability.

Why It Uses Squared Deviations

Squaring the deviations serves two purposes that simpler measures cannot. First, it prevents positive and negative deviations from canceling, which would otherwise make the average deviation zero by construction. Second, it produces a quantity with a convenient mathematical property: the variance of a sum of independent returns equals the sum of their individual variances. This additivity is what makes portfolio mathematics tractable.

That same additivity explains the trade-off. Because deviations are squared, variance is dominated by the largest moves and is sensitive to outliers. A single extreme return can inflate the measure substantially, which means variance can understate or overstate everyday risk depending on the shape of the return distribution. This sensitivity is the price paid for the clean algebra that variance provides.

Variance in a Portfolio

The variance of a portfolio is not simply the average of the variances of its holdings. It also depends on how the holdings move together, measured by their correlation and recorded in the covariance matrix. When assets move in opposite directions, their combined variance falls below the sum of the parts, which is the mathematical engine behind diversification.

Relationship Between Assets	Effect on Portfolio Variance
Move together (positive correlation)	Variances add with little offset; limited diversification benefit
Move independently (zero correlation)	Combined variance is lower than the simple sum
Move oppositely (negative correlation)	Variances partly cancel; the strongest diversification benefit

Known Limitations

Limitations to Keep in Mind

It treats upside and downside the same. Variance counts a large gain and a large loss as equally undesirable, even though most investors welcome upside surprises. Downside-focused measures address this asymmetry at the cost of added complexity.
Squared units obscure meaning. Variance cannot be read on the same scale as returns, so it is almost always converted to standard deviation for interpretation. The conversion adds a step where mistakes can creep in.
It is sensitive to outliers. Because deviations are squared, a few extreme moves can dominate the estimate. This makes variance unstable when returns have fat tails (a higher chance of extreme outcomes than a normal distribution implies).
It assumes the past resembles the future. Variance estimated from history is only useful if the underlying behavior persists. When market conditions change, a historical variance can mislead.
It captures only the second moment. Variance ignores skewness and kurtosis, so two return series with identical variance can carry very different real-world risk profiles.

Academic Origin

Variance entered finance as the formal definition of risk in Harry Markowitz's 1952 work on portfolio selection. By treating risk as the variance of returns and reward as the mean return, Markowitz turned portfolio construction into a precise optimization problem. The choice of variance was deliberate: its clean additive properties made it possible to derive the efficient frontier and to show mathematically why combining assets reduces risk. Later researchers questioned whether variance fully captures what investors mean by risk, but it remains the foundation on which much of quantitative finance is built.

This content is for educational and informational purposes only and does not constitute an offer to sell or a solicitation of an offer to buy any securities. Nothing herein constitutes investment advice or recommendations tailored to your individual situation. All investments involve risk, including the potential loss of principal. Past performance is no guarantee of future results. Information presented is believed to be factual and up-to-date, but Foxholm Financial does not guarantee its accuracy and it should not be regarded as a complete analysis of the subjects discussed. Before making investment decisions, consult with a qualified financial advisor who can evaluate your specific circumstances.