Data to 20 November 2026
About

Tools

How did Mean-variance (shrunk covariance) do after costs and tax?

Long-only maximum Sharpe ratio with the Ledoit-Wolf covariance and each asset's mean excess return over the last 60 months (at least 36 when less history exists); minimum variance if no asset has a positive expected excess return; monthly. From Apr 2005 to Nov 2026 it compounded at 8.9% a year after costs and tax (10.2% before tax), against 11.6% after tax for 60/40. Its worst fall was −41%, bottoming in Oct 2008 and recovered by May 2010.

Written for investors weighing this allocation against a plain 60/40, and advisers who want its tax and cost drag measured. Data to 20 Nov 2026.

How it works

One of 141 portfolios in the lab, in the family "Risk-based". The rule and its parameters were written down before any result was computed.

Historical research on index portfolios, not investment advice. Returns are after fund costs; 'after tax' applies Indian capital-gains rules by date for a 30% slab investor and sells everything at the end. Most factor, mid-cap and small-cap index history before each index's launch date is back-tested by NSE. One 21-year sample, domestic assets only.

Construction
Long-only maximum Sharpe ratio with the Ledoit-Wolf covariance and each asset's mean excess return over the last 60 months (at least 36 when less history exists); minimum variance if no asset has a positive expected excess return; monthly.
Rebalancing
A rule sets the weights at each month-end close; trades happen at the next session's close.
From the literature
Markowitz (1952); Ledoit and Wolf (2004); see DeMiguel et al. (2009) on its out-of-sample record.

Weights held, month-end, Apr 2005 to Nov 2026. No fixed target: the rule decides each month.

Weights held, month-end, Apr 2005 to Nov 2026. No fixed target: the rule decides each month.
AssetAverage heldLowestHighestLatest (Nov 2026)More
G-sec 5-year (NSE benchmark index)38%0%94%0%
Nifty 50032%0%100%24%
Gold (domestic, rupees)30%0%76%76%

Growth and falls

What one rupee became, and how far it fell on the way. 60/40 is drawn in grey for comparison. Both curves are after fund costs and before tax; the after-tax figures are in the costs chapter.

Growth of 1 rupee

Weekly, shown month by month, Apr 2005 to Nov 2026. After costs, before tax. Log scale.

How to read it. On a log scale equal slopes are equal rates of return. One rupee became 8.20× here and 11.86× in 60/40; a steeper line in one stretch says which did better then.

Mean-variance (shrunk covariance)60/40
201020201×2×5×10×11.9×8.2×
Source: tipsheet portfolio lab, computed from domestic gold in rupees (World Gold Council), the NSE 5-year benchmark G-sec index (total return), NSE total-return indices.

Fall from the previous peak

The lowest weekly reading of each month, per cent below the highest value reached so far.

How to read it. Zero means a new high. The deepest fall here was −41.3% (Oct 2008), against −36.5% for 60/40. Depth is half the story: the width of each dip is how long an investor waited to get back to even.

per cent

Mean-variance (shrunk covariance)60/40
20102020−50%−40%−30%−20%−10%0%−1%−17%
Source: tipsheet portfolio lab, computed from domestic gold in rupees (World Gold Council), the NSE 5-year benchmark G-sec index (total return), NSE total-return indices.

The five deepest falls

Measured on daily values. Days are calendar days.

Measured on daily values. Days are calendar days.
FallPeakBottomBack to peakDays fallingDays below peakMore
−41.3%9 Jan 200824 Oct 200812 May 2010289854
−16.7%29 Jan 202619 Nov 2026not yet294295
−16.3%10 May 200614 Jun 200610 Nov 200635184
−12.4%29 Jan 20157 Sept 20153 Oct 2016221613
−9.4%26 Nov 20127 Aug 20137 Mar 2014254466

Year by year

Calendar-year returns, after costs and before tax, with 60/40 below for comparison. In 8 of 20 full years this portfolio did better. The market phases below are the lab's pre-registered splits.

Per cent. * Part year: Apr 2005 on, and to Nov 2026.
2026*202520242023202220212020201920182017201620152014201320122011201020092008200720062005*
Mean-variance (shrunk covariance) −6+29+11+14+6+6+13+10+2+13+10−3+13+1+10+6+15+41−30+51+17+18
60/40 +2+8+13+19+3+20+15+9+1+24+8+4+29+5+23−15+10+51−27+40+22+24

Annualised return and worst fall in each phase, after costs, before tax.

Annualised return and worst fall in each phase, after costs, before tax.
PhaseDatesA year60/40, a yearWorst fall60/40, worst fallMore
The boom, FY06 to FY08Apr 2005 to Mar 200820.4%20.9%−21%−22%
The crisis, FY09Apr 2008 to Mar 2009−8.8%−14.6%−32%−27%
FY10 to FY14Apr 2009 to Mar 201412.7%14.4%−9%−17%
FY15 to FY20 (to March 2020)Apr 2014 to Mar 20206.8%7.9%−12%−23%
April 2020 onApr 2020 to Nov 202610.5%15.3%−17%−11%

What costs and tax took

The same Apr 2005 to Nov 2026 run, peeled back one layer at a time. Fund costs are those of the cheapest widely available index fund or ETF of each era; tax applies Indian capital-gains rules as they stood on each sale date, and everything is sold at the end so deferred tax is counted. Turnover was 0.79 times the portfolio a year.

Annualised return (CAGR) at each layer, and what that layer cost in percentage points a year.

Annualised return (CAGR) at each layer, and what that layer cost in percentage points a year.
LayerMean-variance (shrunk covariance)Cost of this layer (pts)60/40More
Index return, before any cost11.08%–12.70%
After fund costs and trading (before tax)10.21%0.8812.10%
After tax, 30% slab8.91%1.2911.62%
After tax and inflation2.31%6.604.85%

After-tax CAGR under other tax assumptions. The headline keeps the annual equity exemption off because it depends on the investor's other gains.

After-tax CAGR under other tax assumptions. The headline keeps the annual equity exemption off because it depends on the investor's other gains.
Tax caseMean-variance (shrunk covariance)60/40
30% slab, equity exemption off (the headline)8.91%11.62%
30% slab, equity exemption on (Rs 10 lakh start)8.96%11.65%
20% slab9.18%11.62%

How sure I can be

One 21-year history is one draw. These numbers say how much the result could move with a different ordering of the same months, and how it looks once the 141 portfolios tried are taken into account.

Return, 90% interval
6.9% to 13.8% a year before tax (block bootstrap of monthly returns; the point estimate is 10.2%).
Against 60/40, 90% interval
−5.4 pts to +1.5 pts a year. The interval straddles zero: the history cannot tell this portfolio and 60/40 apart.
Five-year windows ahead of 60/40
28% of rolling five-year windows. The windows overlap: only about 4 of them are independent, so this is a description of the past, not a probability.
Longest stretch below its best against 60/40
5,475 days: the longest run its wealth relative to 60/40 spent below an earlier high of that ratio. Not time behind 60/40; it can be ahead throughout.
Deflated Sharpe against 60/40
0.00. This is the probability that its edge over 60/40 is real once 141 tries are allowed for; 0.95 would be the usual bar.
Worst five years after inflation
−4.2% a year
Rolling five-year return
Lowest 5.2%, middle half 6.7% to 11.6%, highest 16.6% a year (before tax).

As a monthly SIP

Rs 10,000 a month, bought at the first session of each month, held for a fixed number of years and then sold, after costs and tax (with the annual equity exemption on). Each start month is one window. Windows that start a month apart share almost all their months, so the number of independent periods is printed next to every figure.

10-year SIP: after-tax return by start month

XIRR of each 10-year SIP, by the month it started (140 windows). Grey: the same instalments in one-year fixed deposits, taxed each year. The FD rate: banks' 1-3 year deposit rate (RBI Handbook Table 74 to July 2010, then RBI's weekly rate for deposits over a year, maximum), interest taxed each year at the 30% slab plus cess.

How to read it. Each point is a whole 10-year SIP. Neighbouring points share most of their months, so the line is far smoother than the evidence is deep. The best start was Mar 2016 (11.4%), the worst Jul 2012 (5.5%).

per cent a year, after tax

Mean-variance (shrunk covariance) SIPFixed-deposit SIP
201020154%6%8%10%12%8.6%5.0%
Source: tipsheet portfolio lab, computed from domestic gold in rupees (World Gold Council), the NSE 5-year benchmark G-sec index (total return), NSE total-return indices.

The latest 10-year SIP in the data started in Nov 2016. It put in ₹12,00,000 and was worth ₹18,74,095 after tax at the end, against ₹15,50,847 for the same instalments in fixed deposits.

After-tax XIRR across start months, per cent a year. 'Below FD' and 'below inflation' are shares of overlapping windows, not probabilities.

After-tax XIRR across start months, per cent a year. 'Below FD' and 'below inflation' are shares of overlapping windows, not probabilities.
YearsWindowsIndependent periods5th pctMedian95th pctWorstWorst startBelow FDBelow inflationMedian valueMore
322472.2%7.1%15.5%−5.0%2005-1123%33%₹4,01,273
520044.4%7.1%13.5%3.5%2011-0314%22%₹7,18,377
717635.3%6.6%11.7%4.7%2011-073%21%₹10,62,583
1014025.8%6.9%10.2%5.5%2012-070%11%₹17,13,711
158016.4%7.1%9.0%6.2%2007-100%0%₹31,61,227
202017.8%8.5%9.1%7.8%2005-040%0%₹60,73,845

The workings

Method

Data

Every chart has a table view, a CSV download and a link to its published JSON. Bundles are listed in data status.

Read with