- Launched in 1993
- AUM- As of early 2026, USD 19.85 trillion (US listed ETFs 10.5 trillion).
- Compared to Mutual Funds?
- As a % of market - the total global market cap is $x trillion. So
"Exchange-traded funds (ETFs) debuted in 1993, marking a major shift in how investors could access the markets. Originally making up less than 1% of all fund trading, they've now grown into a powerhouse, representing about 26% to 30% of daily U.S. trading volume"
History - around 3 decades.
This is a rich question worth unpacking in two distinct threads, as you've correctly identified. Let me work through them both.
ETFs vs. Passive Mutual Funds — Why Both Exist, and Why Convergence Is Incomplete
The structural differences are more durable than they might appear. They're not the same product in different packaging.
How they differ mechanically. A passive mutual fund (think Vanguard's index funds) is priced once daily at NAV — you transact with the fund company directly at end-of-day. An ETF trades on an exchange continuously, like a stock, with a bid-ask spread and an intraday market price that can deviate slightly from the underlying NAV. The ETF uses an "authorised participant" (AP) mechanism — large banks that can create or redeem large blocks of ETF shares by delivering or receiving the underlying basket of stocks — to keep that deviation minimal. This creation/redemption mechanism is structurally elegant and is actually one reason ETFs can be more tax-efficient than mutual funds in US structures (capital gains are flushed through in-kind redemptions rather than taxed within the fund).
Why passive mutual funds haven't been displaced. A few structural reasons:
First, 401(k) and superannuation-equivalent plan architecture. Many employer-sponsored retirement plans in the US (and similar structures globally) are set up to transact in mutual fund units, not ETF shares. Changing the plumbing is slow and expensive. Vanguard's index mutual funds still hold enormous AUM simply because that's how the institutional 401(k) wrapper was built.
Second, fractional investment without a brokerage. Mutual funds accept any dollar amount — you invest $500 and get fractional units at NAV. ETFs traditionally required whole-share purchases (though fractional ETF share trading has grown). For automatic monthly investment plans (think direct debit from payroll), the mutual fund wrapper is cleaner.
Third, cost competition has largely converged anyway. Vanguard's S&P 500 index fund and its ETF equivalent now both sit at ~3 basis points. The fee gap that once made ETFs compelling has largely closed in the passive space. The competitive advantage of ETFs is sharper for active and thematic strategies — not the vanilla index.
Will they converge further? Probably yes, at the margin. The SEC has allowed ETF-of-mutual-fund structures, and there are active ETFs now that approximate the old mutual fund model with intraday liquidity. But complete convergence is unlikely because the distribution infrastructure — retirement plans, adviser platforms, direct-to-consumer savings products — was built around the mutual fund unit and re-plumbing it has costs that exceed the marginal benefit for most participants.
The Philosophical Question — From Stock-Picking to Theme-Picking
This is the more interesting question, and I think you've identified something genuinely significant in the architecture of contemporary investing.
The original mental model. When Graham wrote The Intelligent Investor (1949), the implicit model was: analyse a company, form a view on intrinsic value, build a position. The portfolio was an aggregation of discrete judgements on discrete entities. You were betting on companies.
What ETFs changed. ETFs didn't just lower costs — they shifted the unit of bet. The first generation of index ETFs (SPY launched in 1993) replaced stock selection with market selection: you're no longer asking "is Microsoft undervalued?" but "do I want US large-cap exposure?" The second generation — sector ETFs — refined this to "do I want technology exposure?" The third generation is where the philosophical shift becomes acute: thematic ETFs let you bet on narratives. "Clean energy transition." "Artificial intelligence." "Longevity." "Deglobalisation."
This is a meaningful change in how equity participation works. You are now buying a story, a structural trend, a thesis about the shape of the future — and the index provider translates that thesis into a basket of companies on your behalf. The investor's analytical work shifts from "what is this company worth?" to "do I believe in this theme, and has this ETF captured it well?"
Some second-order effects worth thinking about:
Price discovery becomes noisier at the stock level. If capital flows into an AI ETF, every company in that basket gets bought proportionally to its weight — regardless of individual merit. The marginal investor in Nvidia via a thematic ETF has done no analysis of Nvidia. At scale, this could push valuations in popular themes above fundamentals — and potentially create crowded reversals when sentiment shifts.
The index provider becomes an enormous power in the market. MSCI and S&P Dow Jones decide which companies are "clean energy" and which aren't. When they include or exclude a stock from a major index, billions of dollars respond automatically. The index provider has become a gatekeeper without really being recognised as one.
Sector rotation has accelerated. It's now trivially cheap to move from "financials" to "healthcare" to "commodities" via ETF trades. This may have increased the volatility of sector-level factor moves even as stock-specific volatility has been diversified away.
But individual stock-pickers haven't disappeared — they've become the price-setters for everyone else. This is Grossman-Stiglitz's famous paradox applied to the ETF era: if no one analyses stocks, prices become inefficient, which creates an opportunity for someone to analyse stocks. The passive investors free-ride on the price-setting work done by the active investors who remain. There's an equilibrium somewhere — we don't know where it is — where the market is "just inefficient enough" to sustain the analysts needed to keep it approximately efficient.
For family offices and sophisticated allocators specifically. The thematic ETF world creates a new due diligence problem: not just "is this theme real?" but "has this index captured the theme accurately?" Many thematic ETFs are surprisingly poor representations of their stated thesis — the "clean energy" ETF that has significant fossil fuel exposure through diversified utilities; the "AI" ETF that's 30% Nvidia and then a long tail of loosely related companies. The sophistication has moved from stock analysis to index construction analysis.
The deeper question you're raising — whether the move from companies to themes represents a regression in the quality of capital allocation — is genuinely open. It democratises participation (anyone can bet on deglobalisation now), but it also collectivises the analytical process in a way that may distort prices over medium-term cycles in ways we haven't fully observed yet, because the thematic ETF era is still quite young.
Yes, and the placement is actually more nuanced than it first appears. Let me work through how a thoughtful allocator would think about this.
The straightforward answer first. A broad market ETF — S&P 500, MSCI World, ASX 200 — sits squarely within the equity bucket. It is equity. You're buying the same cash flows, the same economic exposure, just packaged differently. No portfolio construction debate there.
Where it gets interesting is with thematic ETFs. Here the question isn't "which bucket?" but "what am I actually buying, and does it complement or duplicate what I already hold?"
Consider a family office that owns direct positions in Macquarie, NextEra, and a handful of other infrastructure-adjacent businesses, and then adds a "clean energy transition" ETF alongside them. There's likely meaningful overlap — the ETF basket probably holds some of the same names, or companies whose returns are driven by the same macro variables. The thematic ETF isn't adding a new exposure; it's concentrating an existing one, often less efficiently (because the ETF has internal costs and index construction compromises).
So the more useful framework isn't where does it sit but what marginal exposure does it add?
Three distinct roles a thematic ETF can play in a portfolio:
Pure completion. You have a view on a theme — say, Indian domestic consumption — but you don't have the capacity or jurisdiction to pick individual Indian mid-cap companies. The ETF delivers the exposure efficiently where direct ownership is impractical. This is the strongest use case. The ETF is the only viable vehicle; it sits in the equity bucket alongside your direct holdings as a geographic or sector completion tool.
A placeholder pending conviction. You want semiconductor exposure but you haven't done the work to choose between TSMC, ASML, and Applied Materials. The ETF holds all of them proportionally while you build that view. This is a legitimate transitional use — but it should have a defined lifespan. Leaving it as a permanent holding means you're paying (even if modestly) for someone else's index construction decisions indefinitely.
A deliberate diversifier within equities. If your direct equity book is dominated by Australian financials and resources — which a home-biased family office often is — a global technology ETF or a healthcare ETF is genuinely adding factor diversification within the equity sleeve. The thematic ETF is doing the work of reducing the idiosyncratic concentration of the direct book. This is intellectually clean.
Where things get murkier. Some thematic ETFs blur asset class lines. A "real assets" ETF might blend listed REITs, infrastructure stocks, and commodity producers — things that belong in three different allocation buckets in a traditional framework. An "alternative income" ETF might hold a mix of preferred shares, REITs, and senior loans. If you drop these into the equity bucket because they're listed, you're likely misunderstanding the risk you're carrying — particularly their behaviour in an equity drawdown.
The practical discipline is to decompose the ETF's holdings and ask: what would I call these individually? If the answer is "mostly equity with some real asset flavour," it belongs in equity but you should note the bleed. If the answer is "this is really a bond proxy," it doesn't belong in the equity bucket at all, regardless of how it's packaged.
For a family office specifically, the cleanest portfolio architecture treats ETFs as tools, not categories. The equity sleeve has a target allocation — say 40% of the portfolio. Within that sleeve, you might have direct equities (Australian and international), one or two broad passive ETFs for efficient market exposure (US large-cap, MSCI Emerging Markets), and perhaps a thematic ETF or two where direct construction isn't practical. The ETFs don't occupy a separate bucket; they're just delivery mechanisms for equity beta and factor exposures that you've decided you want.
The discipline is periodic review: is this ETF still doing the job I hired it for, or has it drifted (through index rebalancing) into something I no longer recognise?
On the regional split, in the United States institutions hold 69% of listed equity — their dominance is largely what drives the global 47% figure. That share falls to 20% in Asia excluding China and Japan, 9% in China, and 20% in Latin America. Corporate cross-holdings are significant in Asia (24% of listed equity in Asia ex-China/Japan), while the public sector dominates in China at over one-third of market cap. Strategic individuals are large owners in Asia, China, and Latin America. OECD
On where ETFs and mutual funds nest within this. The OECD data doesn't disaggregate the institutional 47% further — that bucket contains everything from Vanguard index funds to Norwegian sovereign wealth to Japanese life insurance companies to university endowments. But we can reason through it with what we know:
The 47% institutional bucket, decomposed roughly, contains equity mutual funds (estimate ~18–22% of global equity market cap, derived from $27–33T mutual fund equity AUM against $152T market cap), equity ETFs (~8–9% as we established), and the remainder — pension funds, insurance companies, sovereign wealth funds, hedge funds, and other institutional direct holdings — probably another 17–21%.
The "other free float" 27% is not pure retail. This is an important methodological note: when flow-of-funds data aggregates household sector holdings, it includes a lot that is not individual mom-and-pop investors — smaller funds, unattributed positions, and miscellaneous intermediaries all get swept into that category. ICI True retail direct stock-picking is probably closer to 10–15% of global equity, concentrated heavily in the US, Australia, and parts of East Asia.
The thing that stands out when you look at the regional data as an allocator: the "institutional" framing of equity markets is almost entirely a developed-market phenomenon. In China, the state and strategic families own the majority. In Latin America and Southeast Asia, corporate group structures and founder families still dominate. The liquid, institutionally-held, analyst-covered equity market that we tend to think of as "the market" is largely a US and OECD construct — which is exactly why passive indexing and ETFs work best there, and why the efficiency arguments for active management are so much stronger outside those markets.
This is one of the more consequential and underappreciated structural shifts in capitalism over the last fifty years. Let me think through it carefully.
The original theory of the public corporation
When Berle and Means wrote The Modern Corporation and Private Property in 1932, they identified what they called the separation of ownership and control as the defining feature of the modern firm. Shareholders own, managers control — and because shareholders are dispersed and disorganised, managers effectively run companies in their own interest. The principal-agent problem was born.
The implicit assumption was that shareholders were individuals — thousands of them, atomised, unable to coordinate, rationally ignorant about any particular company because their stake was too small to justify the cost of attention. This assumption held reasonably well for decades.
Institutional ownership changes the premise entirely. When two-thirds of US equity is held by institutions, you no longer have dispersed, disorganised shareholders. You have a relatively small number of highly concentrated, highly informed, professionally managed entities sitting on the other side of the table from corporate management. The principal is no longer weak.
The "Big Three" concentration problem
The institutional 69% isn't spread evenly. A meaningful fraction of it flows through a very small number of hands. BlackRock, Vanguard, and State Street — the passive index giants — are the largest single shareholders in most S&P 500 companies simultaneously. They own approximately 20–25% of the average S&P 500 company collectively, often as the single largest shareholder bloc.
This creates a structural novelty that has no historical precedent: a small number of permanent, universal shareholders who cannot sell. Because index funds must hold every stock in the index, they cannot exit a poorly-governed company. They cannot vote with their feet. Their only lever is voice — proxy voting, engagement, governance pressure. This transforms the governance dynamic fundamentally. The old market discipline (bad management → selling → share price falls → discipline) doesn't operate for passive holders. They must govern through engagement rather than exit.
The consequence is that three asset managers — whose combined assets exceed the GDP of every country except the US and China — effectively have a say in the governance of nearly every significant publicly traded company in the world. The political economist John Coates called this "The Problem of Twelve" — roughly twelve individuals at the major index managers make proxy voting decisions that effectively determine corporate governance norms across the entire economy.
Does it change decision-making in companies? Substantially yes, in three directions.
Short-termism — the conventional worry that probably overstates the case. The common argument is that institutional pressure forces CEOs to prioritise quarterly earnings over long-term investment. There is something to this — the activist hedge fund that accumulates a 5% stake and demands a buyback or a spinoff is a real force. But the passive giants, by contrast, have explicitly long-term horizons. Vanguard's investment horizon is, in a literal sense, infinite — they will hold a company forever. The governance pressure they apply is not "hit this quarter's number" but "build durable, long-term value." Larry Fink's annual letters to CEOs over the last decade were explicitly demanding long-term thinking, stakeholder capitalism, and resistance to short-termism. Whether you agree with the content or not, it is structurally opposite to the short-termism critique.
Homogenisation of governance norms. When the same three shareholders are simultaneously the largest holder in Apple, Microsoft, Google, JPMorgan, and ExxonMobil, they necessarily apply a common governance template across all of them. They cannot develop bespoke governance views for each of the three thousand companies they hold. They codify — proxy voting guidelines, governance scorecards, ESG frameworks — and apply them universally. This creates enormous pressure toward conformity. Companies converge toward the same board composition, the same executive pay structures, the same disclosure frameworks, the same sustainability reporting, because they are all being evaluated against the same institutional checklist. The diversity of corporate governance models that might otherwise evolve through competition is compressed.
The rise of stakeholder language. When BlackRock and Vanguard tell CEOs to think about employees, communities, and climate alongside shareholders, it changes what is legitimate to say in a boardroom. The Business Roundtable's 2019 statement redefining corporate purpose away from shareholder primacy — signed by 181 CEOs — was partly a response to this institutional pressure. Whether stakeholder capitalism is a genuine philosophical shift or a sophisticated form of reputational risk management for the institutions themselves (who face political pressure to justify their enormous concentrated power) is a separate and very live debate. But the mechanism is clear: institutional owners now set the terms of what counts as responsible corporate behaviour, more than regulators or market competition.
The deeper philosophical question — who does the company serve?
The shift to institutional dominance reopens, in a more complex way, the very question Berle and Means raised. In the old dispersed-ownership model, the answer was theoretically "shareholders" but practically "managers." In the institutional model, the answer is theoretically "shareholders" (who now have actual power), but the shareholders themselves are intermediaries whose ultimate principals are pension beneficiaries, index fund holders, insurance policyholders — the whole working population, essentially.
Vanguard's ultimate beneficial owners are, in a significant sense, the American middle class saving for retirement. So when Vanguard votes on executive pay at a Fortune 500 company, it is nominally a capitalist governance act — one shareholder checking management. But in substance, it is something closer to a diffuse form of social ownership expressing preferences through a financial intermediary. The philosophical gap between "institutional shareholder capitalism" and "market socialism" is narrower than either side of that debate typically acknowledges.
This produces a genuinely novel governance structure: dispersed beneficial ownership (millions of retirement savers), concentrated formal ownership (three asset managers), exercised through standardised governance templates, over managers who are themselves institutional actors with their own principal-agent dynamics. There is no clean theory of corporate governance that maps onto this reality. The old models — shareholder primacy, stakeholder theory, managerial capitalism — were all built for a world that no longer exists.
The one thing that probably hasn't changed as much as people think
For all the structural novelty, the actual daily decision-making inside most companies still belongs to the management team and the board. Institutional shareholders vote once a year, publish proxy guidelines, and occasionally engage directly with management — but they don't set strategy, approve capital allocation decisions, or choose customers. The CEO of a large public company still has enormous discretion in practice, constrained by board oversight and quarterly market feedback, but not meaningfully directed by any individual shareholder. The power of institutional ownership is most visible at the margin — in contested votes, in board composition, in compensation structure, in responding to activist pressure — rather than in the day-to-day.
What has changed is the legitimacy framework. The question "who do we serve?" is now asked differently, answered differently, and enforced differently than it was when shareholders were individuals. The definition of good corporate governance is now written largely by institutions who are themselves answerable to a diffuse beneficial ownership that spans most of the population. That is a profound, quiet, and largely unnoticed revolution in the theory of the firm.
No comments:
Post a Comment