H O M E / I N F O / P R O D U C T S / O R D E R / S U P P O R T

Contents / Getting started / FAQ / Recent changes

Pindyck & Rubinfeld TSP Supplement errata

Due to a printer's error, five pages of the TSP supplement to the new edition Pindyck & Rubinfeld lacked equations. Versions of these pages with the correct equations are now available:

• page 26
• page 81
• page 83
• page 84
• page 114

There are also some minor typos and errata in all editions, as follows:

p. 44 - delete alpha from equation (1)

p. 66 - the second SET F1 command needs another / , and more parentheses in the denominator, or change the last / to * . It should read as follows:

SET F1 = (SSRr-SSRur)/q/(SSRur/(@NOB-@NCOEF)) ;

or, more simply:

SET F1 = (SSRr-SSRur)/q/@S2 ;

p. 67 - the SET F1 command needs more parentheses in the denominator, or change the last / to * . It should read as follows:

SET F1 = (SSRr-SSRur)/@NCOEF/(SSRur/(N2*@NCOEF)) ;

p. 67 - there is a note box explaining @variables. It should read as follows:

Note: TSP saves some values after performing each regression under reserved names (@variables). When you run another regression the @variables are replaced with new values.

p. 74 - in the example computing the Chow test (second batch of code), it should read

SET CHOW =

rather than

SETCHOW=

(insert a space between SET and CHOW).

p. 220 - The last paragraph of page 220 states that "Consumption and income appear to be cointegrated." However, the p-valAsy on pages 230 and 231 are 0.23469, 0.64099, and 0.76598, which indicates that the null of I(1) for the residual in the cointegrating regression cannot be rejected. Therefore, these variables do NOT appear to be cointegrated.

If you have any questions or comments about TSP please send an email to info@tspintl.com.

Comments or questions about this website should be sent to news@tspintl.com.