Which style is inside your fund?
Style analysis looks for the fixed mix of style indices that best replicates a fund's returns. This mix is the style benchmark; what the fund does better or worse is the manager's selection return.
Free during the beta, no ads and no subscription. Once you sign in, this page opens the tool.
How it works
The method goes back to William Sharpe (1992): instead of looking at a fund's holdings, it compares only its monthly returns with those of simple building blocks such as global equities, emerging markets, bonds, gold and money market. It looks for weights of at least 0% that add up to 100% and keep the tracking error (the fluctuation of the difference) as small as possible.
Read the result in three steps: the style weights show how the fund actually behaved, e.g. like a mix with a little more than half in stocks. The R² says how much of the fluctuation the styles explain. Selection is the fund's return minus that of the style benchmark; if it is negative, the passive mix would have earned more.
Estimated on a rolling window of e.g. 36 months, it shows whether the manager shifts style (style drift). Weights from the preceding months only give a style benchmark without hindsight (out of sample); this is how Sharpe recommends measuring selection.
What a result looks like
Sample dataMade-up sample data, no real prices and no recommendation. Calculated with the same methods as the tool itself.
Inputs in this example
Locked: you can't change the inputs in the preview.
Run your own numbers with a free account Your own inputs, real data and every setting.
Create accountFund 5.35% p.a. · tracking error 1.6% · information ratio -0.25 · t-stat -1.1. Selection = fund return p.a. minus style benchmark return p.a.; |t| > 2 counts as roughly significant.
Style weights 01/2006 to 12/2025
Weight with standard error and range; contribution = weight × avg. return of the style.
| Style | Weight | Standard error | Range (±2 SE) | Avg. return p.a. | Contribution p.a. | Given in the example (avg.) |
|---|---|---|---|---|---|---|
| Global equities | 44.6% | 1.2% | 42% to 47% | 7.9% | 3.50% | 45.0% |
| Bonds | 35.7% | 2.2% | 31% to 40% | 3.5% | 1.25% | 37.5% |
| Money market euro | 9.8% | 37.6% | 0% to 85% | 4.7% | 0.46% | 7.5% |
| Equities emerging markets | 6.9% | 0.7% | 5% to 8% | 7.7% | 0.53% | 7.5% |
| Gold | 3.1% | 0.8% | 2% to 5% | 5.6% | 0.17% | 2.5% |
The analysis only knows the monthly returns and recovers the given mix on average. The money market barely fluctuates, so its weight is uncertain (large standard error).
Rolling style weights (36 months)
For each window end, the weights of the preceding months.
The given mix moves evenly from 35% Global equities, 5% Equities emerging markets, 50% Bonds, 10% Money market euro to 55% Global equities, 10% Equities emerging markets, 25% Bonds, 5% Gold, 5% Money market euro. Style shift 15.1% per year on average.
Where does the return come from?
Arithmetic averages: avg. fund return = Σ weight × avg. style return + avg. selection.
| Source of return | Weight | Avg. return p.a. | Contribution p.a. |
|---|---|---|---|
| Global equities | 44.6% | 7.9% | 3.50% |
| Equities emerging markets | 6.9% | 7.7% | 0.53% |
| Bonds | 35.7% | 3.5% | 1.25% |
| Gold | 3.1% | 5.6% | 0.17% |
| Money market euro | 9.8% | 4.7% | 0.46% |
| Style benchmark | 100.0% | – | 5.93% |
| Selection | – | – | -0.40% |
| Fund | – | 5.5% | 5.53% |
Cumulative excess return of the fund
When the line rises, the fund beats the passive mix of the same styles.
Assumptions: Fund entirely made up: each month the given mix of the five styles, -0.9% p.a. for costs and selection and a random residual of 1.2% p.a. The styles are the made-up building blocks and a made-up money market.
Frequently asked questions
What is a returns-based style analysis?
A regression with constraints: a fund's monthly returns are explained by a mix of style indices. All you need are the fund's prices, no holdings lists.
What is the selection return?
The difference between the fund's return and the return of the style benchmark. If it is negative after costs, a passive mix of the same styles would have earned more.
What is style drift?
When the estimated style weights shift clearly over time, e.g. from defensive to aggressive. That can be a deliberate decision by the manager, but part of it is always estimation noise.
Which style indices should I choose?
A few that differ clearly and cover the fund's investment universe: asset classes for multi-asset funds, regions for global equity funds, maturities for bond funds. Indices that move alike make the weights uncertain.
How does this differ from factor analysis?
Factor analysis explains excess returns with factors such as value or momentum, and the weights are free. Style analysis looks for an investable mix of indices with weights of at least 0% that add up to 100%.
Learn more in the knowledge base
- MethodologyReturns-based style analysis: methodology
- ArticleSharpe's style analysis: what a fund really does
- ArticleTracking error and information ratio: deviation from the index
- ArticleActive or passive investing: ETFs versus fund managers
- ArticlePerformance attribution: Brinson decomposition, factors and linking over time
Run it with your own portfolios
Create an account, confirm your email and use this tool with real prices and your own ETFs.
- Price
- Free during the beta
- Data
- Prices, interest rates, inflation and factors from public sources
- Privacy
- Servers in the EU, no ads, statistics without cookies
- Devices
- Computer and phone, everything saved in your account