By M. Clements

Financial econometrics is likely one of the maximum on-going good fortune tales of contemporary a long time, because it has turn into the most lively parts of study in econometrics. during this e-book, Michael Clements offers a transparent and logical rationalization of the main suggestions and ideas of forecasts of monetary and fiscal variables. He indicates that forecasts of the one probably final result of an fiscal and monetary variable are of constrained worth. Forecasts that offer additional info at the anticipated most probably levels of results are extra suitable. This e-book presents a finished remedy of the overview of other kinds of forecasts and attracts out the parallels among the several ways. It describes the tools of comparing those extra advanced forecasts which offer a fuller description of the variety of attainable destiny outcomes.

Show description

Read or Download Evaluating Econometric Forecasts of Economic and Financial Variables PDF

Similar econometrics books

Handbook of Financial Econometrics, Volume 1: Tools and Techniques (Handbooks in Finance)

This number of unique articles―8 years within the making―shines a shiny gentle on fresh advances in monetary econometrics. From a survey of mathematical and statistical instruments for realizing nonlinear Markov strategies to an exploration of the time-series evolution of the risk-return tradeoff for inventory industry funding, famous students Yacine Aït-Sahalia and Lars Peter Hansen benchmark the present country of information whereas participants construct a framework for its progress.

Modelling Irregularly Spaced Financial Data: Theory and Practice of Dynamic Duration Models

From the stories of the 1st edition:"This publication regards monetary element strategies. … worthy probability and liquidity measures are built by means of defining monetary occasions when it comes to rate and /or the quantity strategy. numerous purposes are illustrated. " (Klaus Ehemann, Zentralblatt MATH, Vol. 1081, 2006)

Interest-Rate Management

The complexity of latest monetary items in addition to the ever-increasing significance of spinoff securities for monetary possibility and portfolio administration have made mathematical pricing versions and finished probability administration instruments more and more very important. This publication adresses the desires of either researchers and practitioners.

Dynamic Programming of Economic Decisions

Dynamic Programming is the research of multistage determination within the sequential mode. it really is now well known as a device of significant versatility and gear, and is utilized to an expanding quantity in all levels of financial research, operations learn, expertise, and in addition in mathematical conception itself. In economics and operations study its effect could sometime rival that of linear programming.

Extra resources for Evaluating Econometric Forecasts of Economic and Financial Variables

Sample text

MDM Harvey et al. (1997) propose modifications to DM aimed at improving its small-sample performance. For h = 1, as here: MDM = 1+ 1 × DM T and MDM is compared to a Student tT −1 distribution. SR Spearman’s rank correlation test. This is a distribution free test that determines whether there is a monotonic relation between two variables, here e1t and (e1t −e2t ). It is applicable when, as here with h = 1, it is reasonable to assume that drawings of {e1t , (e1t − e2t )} are independent. SR1 is the one-sided rank correlation test against the alternative of positive correlation, and SR2 is a two-sided test.

However, if positive errors are penalized more heavily than negative errors, it will be optimal (in the sense of minimizing the expected loss) to aim to make a negative expected forecast error, so that the stream of realized errors, {et+i|t+i−1 }, will be predominantly negative. Moreover, the greater the variablity of the process, the larger the variability of the forecast errors.

Given a squared-error loss function, the weight λ is chosen to minimize the MSFE of the combined predictor, fct . Assuming unbiasedness, this is equivalent to minimizing the forecast-error variance. 31) where ect ≡ yt −fct and eit ≡ yt −fit , i = 1, 2. The variance of the combined forecast error is: V (ect ) = (1 − λ)2 V (e1t ) + λ2 V (e2t ) + 2λ(1 − λ)C(e1t , e2t ). 32) Choosing λ to minimize V (ec,t ) leads to: λ∗ = V (e1t ) − C(e1t , e2t ) . 32) we can obtain the variance using λ∗ as the combination weight: V [ect ; λ∗ ] = (1 − ρ2 )V1 V2 , √ V1 + V2 − 2ρ V1 V2 Point Forecasts 17 √ where Vi = V [eit ], i = 1, 2, ρ = C(e1t , e2t )/ V1 V2 .

Download PDF sample

Rated 4.61 of 5 – based on 44 votes