35

I can only talk about quantitative trading. As a rule of thumb, the lower frequency you work in, the more econometrics is important, whereas for a higher frequency, the more econometrics becomes useless. (I would still recommend a top econometrician for HFT since they have what it takes to succeed, it's just the models aren't out-of-the-box applicable.) But ...


17

Here are some resources that I found useful when learning about this subject, in which I'm very interested. (Some may be more general ESG than just just climate.) Citigroup. Environmental and Social Policy Framework (March 2021) UBS. Suni Harford. Investing in an ESG world - A practitioner’s guide (2020) AQR. Clearing the Air: Responsible Investment (...


14

Upon close reading, this appears to be 3 (interesting) questions, not one. I'm not sure if the mods have the tools needed to split it up, so I'm just going to write down the three questions as I see them and then deal with them one by one. Note, it is simpler for me to talk about variance instead of volatility. This has no material impact on the answer. ...


8

@user2763361 has a very thorough list of useful econometric topics for quantitative finance. I would add missing, mixed frequency, and irregular data as major issues that I'm either constantly dealing with or begrudgingly ignoring. Seasonal adjustment is important too for some data (like electricity futures), though the subject is also related to his ...


6

Risk-free rate is that you get for letting someone else use your money in a riskless manner. Suppose we live in a world where there is no risk whatsoever. In particular, if you lend someone \$100 there is 100% certainty that he will pay you back in a year. Before the pay date, he can do whatever he wants with your $100, while you have no access to it. Even ...


5

I think what you are missing is simply the Vega-Gamma relation in the Black-Scholes model. Namely: $$ Vega = \frac{\partial v}{\partial \sigma} = \sigma(T-t)S^2 \frac{\partial^2 v}{\partial S^2} = \sigma \tau S^2 \Gamma $$ Plugging this into your coverage error, you get its expression in terms of the Vega which is the most natural measurement of your ...


5

Firstly, the use of the logit models to estimate the PDs is particularly appreciated in some credit industries, as, for instance, the credit retail one. The logit model predicts pretty well the PD on loans, consumer credit, credit cards, ... and all concerns the retail consumer world. Mainly, those listed are the principal sub-industries in the credit ...


5

Let the $n-$dimensional vector of returns $\mathbf{r}$ have a multivariate t distribution with $\nu$ degrees of freedom. The marginal distribution of any component $r_i$ has a univariate t distribution also with $\nu$ degrees of freedom. To see this, assuming mean returns have been subtracted, the multivariate t distribution decomposes as the distribution ...


4

First, I am quite sure that this is a typo and it should be $$ 0 < VaR_1 < VaR_0 $$ then $$ -VaR_0 < -VaR_1 $$ and the plot is correct. Second, the put strategy does not change only the expected profit but the whole distribution of the P&L. If you buy a put with strike $K_1 = -VaR_1$ then you get compensated for losses below $K_1$. But you ...


4

Reuters uses a proprietary model defined StarMine structural/SmartRatios Credit Risk model that has been developed by themselves and provided with the Reuters data service. It does not exist a formal definition or paper about the model, in which it is explained how to get that score; Reuters simply explains roughly what is in its website without going into ...


4

EDITED You are right. We have to look town to the "leaves" in each iteration. I would do it the following way: If $L_i^{(j)}$ is the set of indices in the $j$ branch ($j \in \{1,2\}$), then we define $s_i^{(j)}=\sum_{n \in L_i^{(j)}w_n}$, the weight of the branch before scaling and $n_i^{(j)}=\left|L_i^{(j)}\right|$ the number of leaves in the branch. ...


4

The book "Managing Energy Risk An Integrated View on Power and Other Energy Markets" by Burger et al. (2014) may be very helpful as it not only introduces the relevant notions, but does so directly from an energy perspective.


3

As an overview, Expected Returns, by Antti Ilmanen, was recommended to me. He has a preference for data over theory, so it will appeal to quants. The book is longish, and got a bit heavy at times, but he covers all the investment products and all styles of investing. The biggest problem might be that it is now 3 years old, and was heavily influenced by ...


3

The risk free rate is important and the reason for the inclusion and consideration of the risk free rate is that investors do not get compensated for not taking on risk. Now, we can argue whether the risk free rate truly provides risk free returns (we all should know that it does not, but ...) but it is important in the context of pricing risky assets that ...


3

Quant finance is about finding prices of illiquid assets in terms of more liquid assets. So if you have the the data for liquid small house prices you should be able to come up with a reasonable guess for less liquid larger houses, for example. That's basically what's been done all the time - replication of complicated derivatives wrt more liquid assets. ...


3

@Noob2’s comment above is “spot” on. Across the natural resource and energy value chains there are significant price risks that: A. Market prices will fall below price takers’ unit costs; and, B. Market prices will exceed price setters’ unit prices. In either case, if you assume that log price changes are a martingale, and that expected profit is the ...


3

I assume that you calculate ECL in the context of IFRS9 -correct? market practice often follows the following appraoch: estimate a TTC PD/LGD (TTC = through the cycle). This corresponds to your lifetime estimate (e.g. one marginal PD value for each year of the life of your exposure) in the average of the economic cycle. But for IFRS9 provisioning you have ...


3

I would give GitHub a try. Searching for option pricing or machine learning or anything like that yield a ton of repositories with implementations that you can look through and learn from. Here are 2 search links: GitHub Search for C++ machine learning GitHub Search for C++ option pricing After gaining some level of comfort, I would look to improve the ...


3

Take a look at these: Bauke Maarse. Master Thesis: Backtesting Framework for PD, EAD and LGD (2012) https://essay.utwente.nl/61905/1/master_B._Maarse.pdf Fábio Yasuhiro Tsukahara, Herbert Kimura, Vinicius Amorim Sobreiro, Juan Carlos Arismendi Zambrano. Validation of default probability models: A stress testing approach (2016) https://doi.org/10.1016/j.irfa....


3

Let us suppose for concreteness that the 10y swap rate is 0.5% today and was 7% a year and and 6.5% a "year minus a day" ago... reprice the swaps for each historical scenario and calculate returns as the difference between the swaps PV from each scenario and the today's PV This won't help you at all, really. Take a step back and consider your ...


3

Adding to Dimitris' answer (this is a too long for a comment) Proceed as follows: Identify risk factors $r^{(i)}$, $i=1\ldots n$. Say the absolute returns of the pillars 1Y,2Y,...30Y of the discounting and forwarding zero rate term structures. Make sure that you have no gaps in your observations. Based on the time series of each risk factor, run a GARCH ...


2

Unsystematic risk of a single stock can be calculated as follows: $$\sigma_\lambda-\rho_{\lambda,m}\sigma_\lambda=\sigma_\lambda(1-\rho_{\lambda,m})$$ where $\sigma_\lambda$ is the volatility of the stock $\lambda$ and $\rho_{\lambda,m}$ is the correlation between this stock and the market. Written differently this is the same as: $$\sigma_\lambda-\...


2

I have studied unsystematic risk [USR] for more than two decades. In fact, I wrote a book (which is here) whose central focus is how to deal with USR in the valuation of non-public companies. It is a multifaceted, complex, and difficult issue. Modern Portfolio Theory did professionals in my line of work no favors when it assumed away the existence of USR ...


2

This can for example be seen in modern portfolio theory (Harry Markowitz, William Sharpe) As an example consider a two asset portfolio with a full investment constraint ($w_1+w_2=1$) so we can write the proportion in asset 1 as $w_1=w$ and in asset 2 as $1-w$ The expected portfolio return $E[R_p]=wE[R_1]+(1-w)E[R_2]$ And variance $\sigma_p^2 = w^2\sigma_1^...


2

as vanguard2k points out the prolem is dealt with e.g. in Scaling portfolio volatility and calculating risk contributions in the presence of serial cross-correlations and references therein. It turns out that correlations are lowered while lag one cross-correlations increase. E.g. you can probably see a correlation of Japan today to US yesterday due to the ...


2

This is a not a theoritcal/academic answer relating the two by an equation. But from a practicioners stand point. The relationship between vol and gamma depends on the strategy your putting on. For example. In a Short Straddle/Strangle/Butterfly/Iron Condor. Your short theta and the risks your taking are gamma risk, even though your delta neutral, and ...


2

It is not as simple as changing a value. You need to replace the current factor loadings by feasible values. Furthermore, factor loadings have dependencies between them, that means that when you change one of them, the other factors are affected by this change. In the CCruncher Technical Document there is a proposal to do so. It propose to estimate the ...


2

The technique is sometimes referred to as full information maximum likelihood. It is more general than the technique you describe, but it is similar. Basically you start with the data with the longest horizon and get the covariance matrix, then for the data with the next longest horizon you regress them against the data with the longest horizon, finally you ...


2

From the Basel II accord: For corporate and bank exposures, the PD is the greater of the one-year PD associated with the internal borrower grade to which that exposure is assigned, or 0.03%. So it is 0.03%


2

Look at the process of estimating your $\beta$ (since if you ask about significance, you have an estimation viewpoint): you try to fit a linear model between your returns $r$ and a factor returns $F$ like $$r = \beta \cdot F + \epsilon,$$ where $\epsilon$ is your tracking error around the factor (or more accurately around the part of your returns explained ...


Only top voted, non community-wiki answers of a minimum length are eligible