Descriptions of the Spreadsheets for the Book
Note that a longer (full) description of these spreadsheets is available in the book.
If you see the following icon in the spreadsheet, it means that the example uses Monte Carlo simulation:
Pressing F9 will trigger a recomputation of results.
2.1 The Law of Large Numbers (LLN) is useful because it states that as more measurements N are taken, statistics will converge to “true” value, provided the random variable is i.i.d. Aim: illustrate LLN on three processes including a non-i.i.d. AR(1) process as N increases to 1000.
2.2 The Central Limit Theorem (CLT) is useful because it states that as more samples are taken from various i.i.d. distributions, the means of those samples will be normally distributed. Aim: illustrates CLT by sampling from a uniform distribution 500 times. The distribution of the means of those samples is plotted.
2.3 Linear correlation is known to have weaknesses when the relationship between variables is nonlinear. Rank correlation provides an alternative. Aim: illustrates the computation of rank correlations.
2.4 An autocorrelation function (ACF) plot is useful in visually identifying serial correlation. Aim: illustrates the computation of ACF plots of N(0,1) and AR(1) processes.
2.5 Standard deviation, ARCH, EWMA, and GARCH are four different ways to model the volatility (hence risks) of a financial ...