Overcoming experimenter bias in scientific research and finance

History of measurements of the speed of light; from Henrion and Fischloff, “Assessing uncertainty in physical constants,” American Journal of Physics, September 1986

Reproducibility in modern science

Reproducibility has emerged as a major issue in numerous fields of scientific research, ranging from psychology, sociology, economics and finance to biomedicine, scientific computing and physics. Many of these difficulties arise from experimenter bias (also known as “selection bias”): consciously or unconsciously excluding, ignoring or adjusting certain data that do not seem to be in agreement with one’s preconceived hypothesis; or devising statistical tests post-hoc, namely AFTER data has already been

Continue reading Overcoming experimenter bias in scientific research and finance

2023: Another miserable year for market forecasters

S&P500 (black) and QQQ i.e. Nasdaq-100 (orange), 22 Dec 2022 through 23 Dec 2023; courtesy BigCharts

Forecasters’ December 2022 predictions

On 20 December 2022, Bloomberg published the results of their annual survey of prominent market forecasters. The consensus: “Investors ready to turn the page on the worst year for equities since the global financial crisis should brace for more pain heading into 2023.”

In particular, the average target of 22 forecasters canvassed by Bloomberg on 20 Dec 2022 was that the S&P500 index of U.S. stocks would close December 2023 at 4078, or in other words with

Continue reading 2023: Another miserable year for market forecasters

Aliens made this rock: The post-hoc probability fallacy in biology, finance and cosmology

Updated 1 February 2024

Space aliens made this rock

Extraterrestrial aliens made this rock

While out hiking, I found this rock. The following table gives measurements made on the rock. The first two rows give the overall length and width of the rock. Each of the next six rows, after the first two, gives thickness measurements, made on a 3cm x 6cm grid of points from the top surface. All measurements are in millimeters:

Measurement or row Column 1 Column 2 Column 3 Length 105.0 Width 48.21 Row 1 35.44 35.38 36.54 Row 2 38.06 38.27

Continue reading Aliens made this rock: The post-hoc probability fallacy in biology, finance and cosmology

Chart-watching market timers fail again

Nasdaq-100 (QQQ) (blue) and S&P500 (orange), Jan-June 2023; courtesy BigCharts

Mid-March 2023

For a moment, let us turn back the clock to mid-March 2023. Here is a brief summary of the financial news current at the time:

The cryptocurrency community was still reeling from the November 2022 collapse of FTX, led by wunderkind Sam Bankman-Fried. The speed of FTX’s downfall, transpiring over just a few days, stunned the crypto industry, which had long promoted itself as a high-tech means to avoid the risk of traditional banking. The U.S. Federal Reserve, defying pleas for mercy from politicians and investors

Continue reading Chart-watching market timers fail again

Active versus index funds: Latest results

A random walk on the base-4 digits of pi (see http://gigapan.com/gigapans/106803)

A Random Walk Down Wall Street

Fifty years ago, Princeton economics professor Burton Malkiel published A Random Walk Down Wall Street. He boldly asserted that a blindfolded chimpanzee throwing darts could pick a stock portfolio that would do as well as one created by many expert practitioners in the field.

At the time, Malkiel envisioned a strategy of owning a broad-based set of stocks, saying mimicking a major stock index such as the U.S. Standard and Poor’s 500 index (S&P 500). At the time, such investment vehicles

Continue reading Active versus index funds: Latest results

Major brokerages and news media feature technical analysis

Introduction

Suppose, in a national TV newscast, instead of citing data, analysis and predictions from major government agencies, the weatherperson displayed a chart of recent temperatures, noting “trends,” “waves” and “breakout patterns.” Most of us would not have confidence in such a dubious and unorthodox forecast.

Or suppose, at a medical clinic, that a cardiologist made some hand measurements of events on an electrocardiogram and noted a “triangle pattern” or “Fibonacci ratio” between them. If this were to happen, most of us would start looking for another cardiologist. [Note: The “Fibonacci ratio,” also known as the “golden ratio,” usually

Continue reading Major brokerages and news media feature technical analysis

Can factor investing become scientific?

A new paper, Causal factor investing: Can factor investing become scientific?, has been written by our esteemed colleague Marcos Lopez de Prado of Cornell University, Abu Dhabi Investment Authority and True Positive Technologies.

In his 75-page preprint, Lopez de Prado argues that almost all journal articles in the “factor investing” literature make assertions that are merely associational observations from statistical analyses, with no attempt to connect these findings to any coherent underlying theory. In other words, these authors justify their chosen model specification merely in terms of correlations or other statistics, and they do not propose experiments for falsifying causal

Continue reading Can factor investing become scientific?

Are hedge funds losing their hedge?

Labyrinth at Schonbrunn Garden, Vienna; Credit: Andrea Schaufler and Wikimedia Commons

Origin of long-short hedge funds

“Hedge funds” were pioneered some 70 years ago by Australian financier Alfred Winslow Jones. His idea was to combine a “long” position (i.e., one that profits if the securities go up in price), typically a set of growth stocks, with a “short” position (i.e., one that profits if the securities go down in price) on the other part of the portfolio. Jones argued that this “long-short” strategy is more stable that either of the two parts by themselves — if the overall market

Continue reading Are hedge funds losing their hedge?

How safe are cryptocurrency investments?

Credit: Onov3056 and Wikimedia Commons

The mathematics behind cryptocurrency

In a previous Mathematical Investor blog, we presented an overview of the mathematics behind blockchain technology, which is the basis of all cryptocurrency systems. At the present time, most systems are based on the SHA-256 algorithm, which is a specific instance of the Elliptic curve digital signature algorithm.

To attempt to break SHA-256 by brute force computation, one would need to exhaust over 2256 ≈ 1077 possible private keys, which is comparable to the number of atoms in the visible universe. In other words, while the computations necessary to actually

Continue reading How safe are cryptocurrency investments?

Active mutual funds underperform passive funds, again

Credit: Mutual Fund Advisors

Introduction

For the vast majority of individuals investors, investing in one or a small number of mutual funds or exchange-traded funds makes more sense than directly owning a set of stocks or bonds. For one thing, investors often sleep better with mutual funds, rather than fretting whenever one of their stock or bond holdings is mentioned in a news report. Also, for many individuals, mutual fund holdings are less likely to run afoul of conflict-of-interest difficulties in their professional work.

In a previous Mathematical Investor blog, we presented data on actively managed versus passive fund

Continue reading Active mutual funds underperform passive funds, again