Best Answer

While compound correlation is the correlation found by calibrating the Gaussian copula model to the price of a CDO tranche (for example 3-6%), base correlation is found by calibrating to the price of a first loss tranche, i.e. to the sum of all tranches up to an attachment point (for example 0-6%, the sum of 0-3% and 3-6%). The curve of correlations obtained by calibrating to first loss tranches turns out to be much smoother and more stable than that obtained by calibrating to plain tranches.

Q: What is the base correlation in a credit derivative pricing model?

Write your answer...

Submit

Still have questions?

Continue Learning about Math & Arithmetic

multiple correlation: Suppose you calculate the linear regression of a single dependent variable on more than one independent variable and that you include a mean in the linear model. The multiple correlation is analogous to the statistic that is obtainable from a linear model that includes just one independent variable. It measures the degree to which the linear model given by the linear regression is valuable as a predictor of the independent variable. For calculation details you might wish to see the wikipedia article for this statistic. partial correlation: Let's say you have a dependent variable Y and a collection of independent variables X1, X2, X3. You might for some reason be interested in the partial correlation of Y and X3. Then you would calculate the linear regression of Y on just X1 and X2. Knowing the coefficients of this linear model you would calculate the so-called residuals which would be the parts of Y unaccounted for by the model or, in other words, the differences between the Y's and the values given by b1X1 + b2X2 where b1 and b2 are the model coefficients from the regression. Now you would calculate the correlation between these residuals and the X3 values to obtain the partial correlation of X3 with Y given X1 and X2. Intuitively, we use the first regression and residual calculation to account for the explanatory power of X1 and X2. Having done that we calculate the correlation coefficient to learn whether any more explanatory power is left for X3 to 'mop up'.

b) Binomial pricing model doesnt provide for the possibility of price of the underlying remaining the same between two consecutive time points (it assumes that either the price could go up or could come down; it completely ignores the possibility of the price not changing at all) a) Binomial pricing model breaks up the time to the expiry of option in to a limited number of time intervals and hence, the price calculated through binomial trees is more of a broad approximation of the actual price. (Compare this with Black Scholes (BS) Model which gives a more accurate approximation because the BS model involves breaking the time to expiry into infinitesimaly small time intervals).

The 3 C's model for setting pricestakes into account the customer, our costs, and the competition. Customer's perception about the various attributes of the products, competitor's pricing and our own total costs.

From Laerd Statistics:The Pearson product-moment correlation coefficient (or Pearson correlation coefficient for short) is a measure of the strength of a linear association between two variables and is denoted by r. Basically, a Pearson product-moment correlation attempts to draw a line of best fit through the data of two variables, and the Pearson correlation coefficient, r, indicates how far away all these data points are to this line of best fit (how well the data points fit this new model/line of best fit).

It gives a measure of the extent to which values of the dependent variable move with values of the independent variables. This will enable you to decide whether or not the model has any useful predictive properties (significance). It also gives a measure of the expected changes in the value of the dependent variable which would accompany changes in the independent variable. A regression model cannot offer an explanation. The fact that two variables move together does not mean that changes in one cause changes in the other. Furthermore it is possible to have very closely related variables which, because of a wrongly specified model, can show no correlation. For example, a LINEAR model fitted to y=x2 over a symmetric range for x will show zero correlation!

Related questions

An arbitrage pricing theory is a theory of asset pricing serving as a framework for the arbitrage pricing model.

The Capital Asset Pricing Model is a pricing model that describes the relationship between expected return and risk. The CAPM helps determine if investments are worth the risk.

The main references are:David X. Li "Pricing Basket Credit Derivatives"Hull-White "Credit Default Swap II"However, pricing a multiname credit derivative product basically boils down to efficiently implementing a MonteCarlo simulation for correlated random variables. The main decision to be taken is how to model correlations. A Gaussian copula is at the moment the market standard. Most practioners use it, although many of them dislike it. Research in this field is still at a very preliminary stage. The fact is that the Gaussian copula model is easy to calibrate and allows for straightforward comparative statics (e.g. calculation of the delta) while other more realistic and complicated models (such as Darrel Duffies' affine models) are still very difficult to calibrate and use.

Haim Levy has written: 'Relative effectiveness of efficiency criteria for portfolio selection' -- subject(s): Investments, Mathematical models, Stocks 'Investment and portfolio analysis' -- subject(s): Investment analysis, Portfolio management 'Research in Finance' 'The capital asset pricing model' 'The capital asset pricing model in the 21st century' -- subject(s): Capital assets pricing model, Capital asset pricing model

It's a measure of how well a simple linear model accounts for observed variation.

Product line pricing is a pricing strategy that uses one product with various class distinctions. An example would be a car model that has various model types that change with performance and quality. This pricing process is evaluated through consumer value perception, production costs of upgrades, and other cost and demand factors.

The capital asset pricing model (CAPM) is the dominant model for estimating the cost of equity.

Edward M. Rice has written: 'Portfolio performance, residual analysis and capital asset pricing model tests' -- subject(s): Capital assets pricing model

The noun 'archetype' is a Greek derivative. Its origins trace back to the ancient Greek language of the classical Greeks. The root words are archein, which means 'old'; and typos, which means 'model'. The combined meaning is 'original pattern or model'.

An APM is an abbreviation for an arbitrage pricing model or an advanced power management.

The pricing depends on the model.

Copulas are important in statistics because they are used to model the dependency structure between random variables. They help characterize the joint distribution of variables and are essential in risk management, option pricing, and portfolio optimization. Copulas allow for more flexible modeling of dependencies compared to traditional correlation measures.