## Econometric models and economic forecastsThis well known text helps students understand the art of model building - what type of model to build, building the appropriate model, testing it statistically, and applying the model to practical problems in forecasting and analysis. |

### From inside the book

Results 1-3 of 69

Page 451

HOj) at 300 Z 100 1965 1970 1975 1980 1985 1990 1995

1970 1975 1980 1985 1990 1995

nonresidential investment.

interest rate. 16. i oo

investment. 300 l 00 simulated . 1965 1970 1975 1980 1985 1990 1995 1970

1975 1980 1 985 1 990 1995

BEHAVIOR OF SIMULATION ...

HOj) at 300 Z 100 1965 1970 1975 1980 1985 1990 1995

**FIGURE**A1. 19651970 1975 1980 1985 1990 1995

**FIGURE**A1 4.4 Historical simulation ofnonresidential investment.

**FIGURE**A1 4.7 Historical simulation of short-terminterest rate. 16. i oo

**FIGURE**A1 4.5 Historical simulation of residentialinvestment. 300 l 00 simulated . 1965 1970 1975 1980 1985 1990 1995 1970

1975 1980 1 985 1 990 1995

**FIGURE**A14.11. CHAPTER 14: DYNAMICBEHAVIOR OF SIMULATION ...

Page 501

Robert S. Pindyck, Daniel L. Rubinfeld. 0 I '(M,

1980 1985 t99o 1995 Three-month Treasury bill rate.

Treasury bill rate: 5 io 15 20 25 30 35 40 sample autocorrelation function. -6 191,'

,

bill rate — first differences.

autocorrelation function. CHAPTER 16: PROPERTIES OF STOCHASTIC TIME ...

Robert S. Pindyck, Daniel L. Rubinfeld. 0 I '(M,

**FIGURE**16.7 1965 1970 19751980 1985 t99o 1995 Three-month Treasury bill rate.

**FIGURE**16.8 Three-monthTreasury bill rate: 5 io 15 20 25 30 35 40 sample autocorrelation function. -6 191,'

,

**FIGURE**16.9 r Three-month Treasury 1965 1970 1975 1980 1985 1990 1995bill rate — first differences.

**FIGURE**16.10 Interest rate — first differences: sampleautocorrelation function. CHAPTER 16: PROPERTIES OF STOCHASTIC TIME ...

Page 593

19.14. Observe that high-order correlations dampen toward 0, so that the residual

series can be considered stationary. The autocorrelation function does, however,

contain peaks at monthly lags which are multiples of 12, indicating annual

seasonality.

month difference of the original residual series, i.e., for the series (1 - B12)u,. This

autocorrelation function has a dampened sinusoidal shape which is indicative of

a purely ...

19.14. Observe that high-order correlations dampen toward 0, so that the residual

series can be considered stationary. The autocorrelation function does, however,

contain peaks at monthly lags which are multiples of 12, indicating annual

seasonality.

**Figure**19.15 shows the sample autocorrelation function for a 12-month difference of the original residual series, i.e., for the series (1 - B12)u,. This

autocorrelation function has a dampened sinusoidal shape which is indicative of

a purely ...

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

THE BASICS OF REGRESSION ANALYSIS | 1 |

A Review | 19 |

The TwoVariable Regression Model | 57 |

Copyright | |

18 other sections not shown

### Other editions - View all

### Common terms and phrases

2SLS alternative ARIMA model associated assume assumption autocorrelation function autoregressive behavior calculate Chapter coefficients confidence intervals consider consistent estimator consumption covariance critical value degrees of freedom demand dependent variable determine dynamic econometric endogenous variables equal error term error variance example exogenous explanatory variables F distribution F statistic F test FIGURE follows forecast error given heteroscedasticity income independent individual intercept interest rate least-squares estimation linear regression matrix maximum-likelihood estimation mean moving average nonlinear nonstationary normally distributed null hypothesis observations obtain ordinary least squares parameter estimates percent level period predetermined variables predict probit problem procedure random variable random walk reduced form regression equation regression model reject the null relationship residuals sample autocorrelation function serial correlation shown in Fig significant simulation model single-equation slope specification standard deviation standard error stationary statistic stochastic sum of squares techniques time-series model uncorrelated zero