Thursday, February 4, 2021

Testing for Covid 19, and Baye's Theorem: An Entry-Level Primer for Those Interested in Medical Testing Accuracy

I put together a little spreadsheet when Covid was first entering our awareness, in early 2020. Link to spreadsheet model (it may open in a Google app; if  so, there will be an "open" button somewhere that allows it to be opened in Excel, which may be better). 

There was an oft-repeated claim that the tests, though slow to come out, were highly accurate--I think they were often said to be 99% accurate, which is indeed very high. However, having been exposed to Bayesian revisions earlier in my career, I thought to see what this really means for accuracy in the field. Thus the spreadsheet. I pulled it up again recently, and though the early Covid testing issues are behind us, I still thought it might be interesting to some people. So I updated it as a learning tool--people are more interested in testing accuracy than they ever were before.

There are three inputs, the first two for what often passes for the "accuracy" of the test--the sensitivity of the test (its probability of identifying the disease among those known to have it); and the specificity of the test (its probability of identifying the absence of disease among those known to not in fact have it). The third input is the percentage prevalence of the disease in the tested population.

What we're interested in is the likelihood of true and false positive test results, and of true and false negative results. A more complete assessment of accuracy.

Saturday, November 28, 2020

Waring offers new paper assisting generalists in calculating durations and convexities, including dual durations, for perpetuities, annuities, zero coupon bonds, and coupon bonds 

In this reference note, intended for relatively easy use by finance generalists, we derive the formulae for a) the prices and dual and single durations and convexities for b) growing and nominal instruments, including c) coupon bonds, zero coupon bonds, annuities, and perpetuities, across d) the seven most useful and relevant combinations of coupon, discounting, and other cash flow details (forms)—all in a relatively compact form of presentation. These forms include 7 variations of continuous or discrete coupons, payment timing [i.e., payments made at the end of the period (most common) or payments made at the beginning of the period (annuity due)], growth beginning right away during the first period, or growth only beginning during the second period (the conventional form for most growing perpetuities and annuities), and continuous or discrete compounding.

This is ambitious; that’s a big delivery from a paper of only modestly excessive length— There are solutions for four types of fixed income instruments, each solving for either real or nominal values, across seven forms for growing instruments and five for nominal instruments; that’s 48 different solutions for duration and convexity. Not all are equally useful, but many are very much so.  Click here to read

Saturday, June 2, 2018

Waring and Siegel write a new article, on the true nature of investment risk, showing how it flows through to spending risk

In their latest joint effort, Waring and Siegel write on the nature of investment risk, titled "What Investment Risk Means to You: Strategic Asset Allocation, the Budget Constraint, and the Volatility of Spending During Retirement," in The Journal of Retirement, Volume 6, Number 2, Fall 2018. The authors' experience suggests that few investment professionals articulate risk well to their investors. This research uniquely and graphically reveals the nature of strategic asset allocation (SAA) investment risk not only for single-period investors, but also for multi-period investors such as those whose savings are held for retirement consumption purposes. Informed by Monte Carlo simulations, they evaluate and picture the nature of that multi-period consumption risk with both efficient spending rules and inefficient spending rules. Risk in a multi-period context means that expected spending may increase with greater SAA risk, but realized spending, a function of realized investment returns, may instead be worse.

Thursday, March 24, 2016

Waring and Siegel Win Prestigious Graham and Dodd Award for Spending Rule Article

One of CFA Institute's Highest Honors

To read the award-winning article, click here, or locate it in the Publications section of this website.

From the CFA Institute's press release (for full text, click here):

CFA Institute Names Top Financial Analysts Journal Articles with Annual Graham and Dodd Awards

Best article of 2015 contributes to addressing the retirement crisis by proposing a dynamic spending rule that prevents retirees from running out of money by making their income during retirement fluctuate with asset values. It is a simplification of the multi-period stochastic dynamic programming "lifestyle" models, but with very high fidelity.

New York, 8 March 2016: 

CFA Institute, the global association of investment management professionals, announces the results of the 2015 Graham and Dodd Awards, a program honoring the top articles published in the Financial Analysts Journal each year. “The Only Spending Rule Article You Will Ever Need” by M. Barton Waring and Laurence B. Siegel received the top award. The article appeared in the January/February 2015 issue, a special issue on retirement security that marked the 70th anniversary of the Journal. The article’s contribution is to use the annuity technique to determine the maximum income that retirees can withdraw each year without facing the risk of running out of money. The authors call their proposed spending rule an annually recalculated virtual annuity (ARVA). They explain and illustrate the mechanics of the ARVA, which allows retirees to recalculate each year how much they can spend based on their life expectancy and the current value of their retirement portfolio.

Barbara S. Petitt, CFA, managing editor of the Financial Analysts Journal, commented: “I am pleased that the Journal’s Advisory Council and Editorial Board chose to honor an article that plays a role in addressing the retirement crisis. Retirement security is one of the themes of the CFA Institute Future of Finance initiative, and the Financial Analysts Journal is well positioned not only to advance the knowledge and understanding of the challenges of achieving retirement security but also to offer practical solutions to these challenges. This article, which is written in language accessible to investors, should thus be valuable to them and their advisers.”

See Barton's earlier post describing the article in more detail.

Thursday, September 3, 2015

There Was Nothing I Could Do--All the Correlations Had Suddenly Gone to One!

Waring and Siegel post a new working paper, dealing with the frequently-heard claim after a losing streak that the underlying correlation structure had experienced a surprise change. They use an interesting approach to challenge traders and portfolio managers, as well as asset allocation strategists, to think beyond such simple claims. They show that rather than changes in the underlying correlation structure, short period realized correlations are widely distributed and highly random. The paper is supported by a user-friendly Excel(tm) spreadsheet, where the user can run simulations to explore the distribution of sub-period realized correlations given underlying "true" correlations between two assets. The working paper is here: Read working paper The supporting spreadsheet is here: OPEN SPREADSHEET

Friday, August 29, 2014

Waring and Siegel Resolve Spending Rule Debates

Puzzled for some time about the oversimplified spending rules usually proposed by financial advisors and others helping individual investors (such as the widely-used but dangerous "4% rule"), Duane Whitney and I briefly pointed out in our 2009 Journal of Portfolio Management article that modern portfolio theory provides a better answer (Summer, p. 123). That answer is that what one needs is an annuity for one's remaining life. The insight was that even if you don't want a commercial annuity, you can create a complete substitute on your own. One simply calculates each year the first payment on an annuity for one's maximum possible life, and spends that amount in that year.

Next year, you recalculate that first payment again, and spend that amount. In this way you self-correct for portfolio returns and interest rate fluctuations, and you avoid the possibility of running out of money. This was a side discussion in that article, which was primarily focused on the larger problem of investment strategy for investors with spending plans.

Larry Siegel and I thought that the idea warranted much more thorough discussion, as the industry starts to give more sophisticated attention to the issues facing individual investors. So in this current paper, published in the January-February 2015 issue of the Financial Analysts Journal, we dive in

Wednesday, April 10, 2013

Shanghai Securities News: Conference on the future of investment management in China

Barton's presentation to the Chinese investment management industry is available here: Shanghai Securities News conference presentation