macrocephalopod on Twitter: "It’s true no matter what the weights are, as long as the weights for the index you measure beta to are the same as the weights you use for calculating weighted beta. The average (equal weighted) beta to an equal weighted index is still 1.… https://t.co/tA63DjJckR"

@macrocephalopod

Paul Allen, Vice President M&A, Pierce & Pierce (Sie/Hir) | Vegan | Silence is Violence | Women’s Rights Are Human Rights | ACAB (Assigned Cephalopod At Birth)

Joined December 2020

Country	Code	For customers of
United States	40404	(any)
Canada	21212	(any)
United Kingdom	86444	Vodafone, Orange, 3, O2
Brazil	40404	Nextel, TIM
Haiti	40404	Digicel, Voila
Ireland	51210	Vodafone, O2
India	53000	Bharti Airtel, Videocon, Reliance
Indonesia	89887	AXIS, 3, Telkomsel, Indosat, XL Axiata
Italy	4880804	Wind
3424486444	Vodafone
» See SMS short codes for other countries

Robot James ‏ @therobotjames 16 Mar 2021

Replying to @breakingthemark @macrocephalopod and

Daily returns on R1000 stocks since 1999. Point-in-time (no survivorship bias). Removed obvs with price < $5 or volume < 0. Observations: 5,541,053 AR Mean: 0.055% Geo Mean: 0.020% Stdev: 2.625%

3 replies 0 retweets 3 likes

Robot James ‏ @therobotjames 16 Mar 2021

Replying to @therobotjames @breakingthemark and

Avg risk free rate (3 month bills) was 0.589% over that period. Which is 0.002% per day. I'm not 100% sure what you're expecting to see here so I haven't tried to interpret this for you.

1 reply 0 retweets 2 likes

Robot James ‏ @therobotjames 16 Mar 2021

Replying to @therobotjames @breakingthemark and

Here's the annualised arithmetic return plotted against the annualised variance for each stock. (Each point is a unique stock ticker.) I've truncated axes a bit...pic.twitter.com/wKiETH1zgN

2 replies 0 retweets 2 likes

Robot James ‏ @therobotjames 17 Mar 2021

Replying to @therobotjames @breakingthemark and

Here is the data summarised by ticker. https://filebin.net/ctycg7t0rgpozadj/byticker.csv?t=ek9bfpdq … Note the observations column... Stocks go in and out of the index so some stocks have lots of observations and others much fewer.

1 reply 0 retweets 1 like

Matt Hollerbach‏ @breakingthemark 17 Mar 2021

Replying to @therobotjames @macrocephalopod and

Thanks. I've done two things. I calculated the OL for each stock and then averaged them, weighted by the # of observations. Its 1.16 And I calculated the weighted avg of return and st. dev. (my st. dev was a bit lower than yours, return was same). and then the OL. Its 0.85pic.twitter.com/xFIGI5Ol6M

1 reply 0 retweets 0 likes

Matt Hollerbach‏ @breakingthemark 17 Mar 2021

Replying to @breakingthemark @therobotjames and

So somewhat near 1. I'm not sure if 20 years is enough to get a full convergence. I used 70 years of data in my post. I think its a coincidence that the two meathods nearly equally flank 1 on each side.

1 reply 0 retweets 0 likes

Adam Goldstein‏ @goldstein_aa 17 Mar 2021

Replying to @breakingthemark @therobotjames and

Well, using your method of corroborating a theory CAPM has been corroborated 100% perfectly. Weighted average beta for all stocks=1, weighted average excess return = market excess return. But that's not how people judge CAPM, and it's not how people will judge your theory.

3 replies 0 retweets 1 like

Matt Hollerbach‏ @breakingthemark 17 Mar 2021

Replying to @goldstein_aa @therobotjames and

"Weighted average beta for all stocks=1, weighted average excess return = market excess return" Are either of these true? I sent you a screen last week which made is seem like the first certainly wasn't true.

2 replies 0 retweets 0 likes

macrocephalopod‏ @macrocephalopod 17 Mar 2021

Replying to @breakingthemark @goldstein_aa and

They are both true by definition if the weights are market cap weights and the index you are measuring beta to is a market cap weighted index. No data analysis required, it is just math.

2 replies 0 retweets 2 likes

Matt Hollerbach‏ @breakingthemark 17 Mar 2021

Replying to @macrocephalopod @goldstein_aa and

Oh, I'm wasn't trying to say to use market cap weights, just average them so each observation of a return is weighted equally. Is the average beta of a stock is greater than 1?

1 reply 0 retweets 0 likes

macrocephalopod‏ @macrocephalopod 17 Mar 2021

Replying to @breakingthemark @goldstein_aa and

It’s true no matter what the weights are, as long as the weights for the index you measure beta to are the same as the weights you use for calculating weighted beta. The average (equal weighted) beta to an equal weighted index is still 1.

7:15 AM - 17 Mar 2021

1 Like

1 reply 0 retweets 1 like

1. Matt Hollerbach‏ @breakingthemark 17 Mar 2021
  Replying to @macrocephalopod @goldstein_aa and
  
  I was referencing CAPM beta, not beta at different weights. CAPM needs to compare to the market. I don't care about that comparison.
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo

Loading seems to be taking a while.

Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

Tweets

macrocephalopod