A Practical Introduction to Econometric Methods: Classical by Patrick Kent Watson, Sonja Sabita Teelucksingh

By Patrick Kent Watson, Sonja Sabita Teelucksingh

Show description

Read or Download A Practical Introduction to Econometric Methods: Classical and Modern by Patrick Kent Watson (2002-01-31) PDF

Best econometrics books

Regression Analysis of Count Data (Econometric Society Monographs)

Scholars in either social and common sciences frequently search regression the right way to clarify the frequency of occasions, comparable to visits to a physician, car injuries, or new patents offered. This e-book presents the main complete and updated account of versions and techniques to interpret such info. The authors have carried out examine within the box for greater than twenty-five years.

Modelling the Riskiness in Country Risk Ratings (Contributions to Economic Analysis)

The significance of nation hazard is underscored through the life of numerous widespread state danger ranking organizations. those businesses mix information about replacement measures of monetary, monetary and political hazard into linked composite possibility rankings. because the accuracy of such nation danger measures is open to query, it will be significant to examine the business enterprise score structures to permit an assessment of the significance and relevance of company threat scores.

Applied Macroeconometrics

Until eventually the Seventies, there has been a consensus in utilized macroeconometrics, either concerning the theoretical beginning and the empirical specification of macroeconometric modelling, generally called the Cowles fee procedure. this is often not the case: the Cowles fee technique broke down within the Seventies, changed through 3 sought after competing tools of empirical study: the LSE (London university of Economics) procedure, the VAR strategy, and the intertemporal optimization/Real company Cycle process.

Additional info for A Practical Introduction to Econometric Methods: Classical and Modern by Patrick Kent Watson (2002-01-31)

Example text

49 Some Issues in the Application of the General Linear Regression Model We can show the biased nature of this OLS estimator in the following manner – replace yt in this expression by its value: n ∑ x (β x 1t βˆ 1 = 1 1t + β2 x 2 t + u t ) t =1 n ∑x 2 1t t =1 n β1 = ∑x n 2 1t + β2 t =1 n ∑x x + ∑x u 1t 2t 1t t =1 n t t =1 ∑x 2 1t t =1 n = β1 + β ∑ n x1t x 2 t ∑x 1t + t =1 n 2 ∑x u t t =1 n ∑x 2 1t t =1 2 1t t =1 Therefore: n ( ) ∑x x 1t E βˆ 1 = β1 + β 2 2t t =1 n ∑x + 0 ≠ β1 2 1t t =1 implying that E( βˆ 1) differs from β1 by the amount ⎛ ⎜ ⎜β ⎜ 2 ⎜ ⎝ n ∑x x 1t t =1 n ∑x t =1 2 1t 2t ⎞ ⎟ ⎟ ⎟ ⎟ ⎠ which is a measure of the bias.

Error T-Statistic Prob. D. E. 71113 Sum squared resid 6517534. 83 on imports). Furthermore, the R2 and F-statistics leave us in no doubt that this is a good fit. What then do we do? It is very difficult to answer this question at this stage of our study of econometrics but at least one word of warning is in order: the conclusions about the significance of this or that variable under the conditions of multicollinearity shown here are very tenuous and great caution should be exercised in using any of the results shown.

Consider a random vector X whose elements are X1, X2, ... , Xn and define E(Xi) = μi. Define E(X) = μ, then: ⎡ μ1 ⎤ ⎢μ ⎥ 2 E (X) = μ = ⎢ ⎥ ⎢%⎥ ⎢ ⎥ ⎣μ n ⎦ Define var(Xi) = σ 2i , and Cov (Xi, Xj) = σij, i ≠ j. Consider the following “covariance table” showing the moments of second order of the n random variables: X1 X2 ........ Xn X1 σ12 σ12 ............. σ1n X2 σ21 σ22 ........... σ2n Xn σn1 σn2 ......... σn2 The tableau clearly shows, in an ordered way, the variances (along the principal diagonal) and the covariances (the nondiagonal elements).

Download PDF sample

Rated 4.04 of 5 – based on 19 votes