Presentation is loading. Please wait.

Presentation is loading. Please wait.

The University of Pennsylvania Models for High-Frequency Macroeconomic Modeling Lawrence R. Klein Suleyman Ozmucur.

Published byGwen Beryl Armstrong Modified over 9 years ago

Similar presentations

Presentation on theme: "The University of Pennsylvania Models for High-Frequency Macroeconomic Modeling Lawrence R. Klein Suleyman Ozmucur."— Presentation transcript:

1 The University of Pennsylvania Models for High-Frequency Macroeconomic Modeling Lawrence R. Klein Suleyman Ozmucur

2 Table 1. Absolute values of forecasts of alternative models Absolute Errors (1997:1 - 2003:4) EXPEND._1INCOME_1PRINCOM_1AVERAGE_1NAIVE_1 Mean1.361.591.301.011.88 Median1.341.490.930.771.37 Maximum3.945.693.823.075.62 Minimum0.000.160.070.010.06 Std. Dev.1.191.281.110.921.44 Skewness0.821.510.951.091.05 Kurtosis2.775.762.793.073.40

3 EXPEND._2INCOME_2PRINCOM_2AVERAGE_2NAIVE_2 Mean1.711.581.541.392.13 Median1.491.431.321.011.87 Maximum4.527.294.853.926.19 Minimum0.000.020.03 0.31 Std. Dev.1.441.471.211.021.57 Skewness0.632.271.210.800.88 Kurtosis2.189.424.082.703.17

4 EXPEND._3INCOME_3PRINCOM_3AVERAGE_3NAIVE_3 Mean1.861.971.801.672.15 Median1.561.781.631.331.74 Maximum4.786.365.294.396.40 Minimum0.190.140.030.200.07 Std. Dev.1.331.671.431.251.55 Skewness0.671.120.650.631.08 Kurtosis2.303.952.582.363.60

5 Table 2. Correlation Coefficients Between real GDP growth rates and Model Estimates (numbers following the model name refer to number of months before the advanced estimate) Correlation Coefficients ADVANCEPRELIMINARY FINAL EXPENDITURE_10.670.620.63 INCOME_10.540.480.47 PRINCOM_10.58 0.57 AVERAGE_10.760.710.70 EXPENDITURE_20.480.450.47 INCOME_20.440.380.37 PRINCOM_20.430.40 AVERAGE_20.650.590.60 EXPENDITURE_30.400.300.29 INCOME_30.270.210.19 PRINCOM_30.260.180.15 AVERAGE_30.410.310.28

6 Sample: 1997:1 2003:4 IF ADVANCE<ADVANCE(-1) EXPEND._1INCOME_1PRINCOM_1AVERAGE_1 Mean 1.256 1.402 0.947 0.787 Median 1.225 1.555 0.585 0.705 Maximum 3.680 2.500 2.740 2.780 Minimum 0.000 0.160 0.070 Std. Dev. 1.123 0.738 0.881 0.707 Skewness 0.761-0.673 0.912 1.586 Kurtosis 2.709 2.371 2.555 5.545 Observations 14

7 Sample: 1997:1 2003:4 IF ADVANCE>ADVANCE(-1) EXPEND._1INCOME_1PRINCOM_1AVERAGE_1 Mean 1.456 1.780 1.655 1.234 Median 1.520 1.360 1.150 0.915 Maximum 3.940 5.690 3.820 3.070 Minimum 0.050 0.190 0.410 0.010 Std. Dev. 1.293 1.666 1.228 1.072 Skewness 0.803 1.218 0.702 0.638 Kurtosis 2.623 3.520 2.058 1.973 Observations 14

8 actualsurvey cornerCQMNaive 2003.01143-6-101 2003.02-3084143 2003.03-108-41-4-308 2003.04-48-83-72-108 2003.05-17-94-86-48 2003.06-30-510-17 2003.07-44-22-4-30 2003.08-93-8-19-44 2003.0957-2-24-93 2003.1126-252057 2003.115720113126 2003.12112011257 2004.01112151651 2004.022114479112 2004.033081877221 2004.04201167308 MAE748092

9 actualsurvey cornerCQMNaive 2003.010.73-0.01 2003.020.090.2 2003.03-0.54-0.370.150.09 2003.04-0.45-0.67-0.06-0.54 2003.050.180.09-0.14-0.45 2003.060.090.18-0.020.18 2003.070.460.160.040.09 2003.080.09 0.160.46 2003.090.360.090.160.09 2003.10.270.450.210.36 2003.110.890.450.210.27 2003.120.080.440.410.89 2004.010.790.440.280.08 2004.020.730.440.360.79 2004.030.440.56 2004.040.430.53 MAE0.230.350.4

10

11

12

13

14

15

16

17

Download ppt "The University of Pennsylvania Models for High-Frequency Macroeconomic Modeling Lawrence R. Klein Suleyman Ozmucur."

Similar presentations

Class 14 Testing Hypotheses about Means Paired samples 10.3 p 419-425.

Class 14 Testing Hypotheses about Means Paired samples 10.3 p
McGraw-Hill/Irwin Copyright © 2007 by The McGraw-Hill Companies, Inc. All rights reserved. Nonparametric Methods Chapter 15.

McGraw-Hill/Irwin Copyright © 2007 by The McGraw-Hill Companies, Inc. All rights reserved. Nonparametric Methods Chapter 15.
Number of observations in the population The population mean of a data set is the average of all the data values. Sum of the values of the N observations.

Number of observations in the population The population mean of a data set is the average of all the data values. Sum of the values of the N observations.
Measuring Macroeconomic Variables

Measuring Macroeconomic Variables
Dependent Variable: INCOME Included observations: 30 Variable Coefficient Std. Error t-Statistic Prob. C -1001.869 520.7067 -1.924056 0.0654 AGE 8.846979.

Dependent Variable: INCOME Included observations: 30 Variable Coefficient Std. Error t-Statistic Prob. C AGE
Copyright © 2008 by the McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill/Irwin Managerial Economics, 9e Managerial Economics Thomas Maurice.

Copyright © 2008 by the McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill/Irwin Managerial Economics, 9e Managerial Economics Thomas Maurice.
BCOR 1020 Business Statistics Lecture 28 – May 1, 2008.

BCOR 1020 Business Statistics Lecture 28 – May 1, 2008.
Economics 240C Forecasting US Retail Sales. Group 3.

Economics 240C Forecasting US Retail Sales. Group 3.
GDP Published by: Bureau of Economic Analysis Frequency: Quarterly Period Covered: prior quarter Volatility: Moderate Market significance: very high Web.

GDP Published by: Bureau of Economic Analysis Frequency: Quarterly Period Covered: prior quarter Volatility: Moderate Market significance: very high Web.
Those who don’t know statistics are condemned to reinvent it… David Freedman.

Those who don’t know statistics are condemned to reinvent it… David Freedman.
Distribution Summaries Measures of central tendency Mean Median Mode Measures of spread Standard Deviation Interquartile Range (IQR)

Distribution Summaries Measures of central tendency Mean Median Mode Measures of spread Standard Deviation Interquartile Range (IQR)
8 THE DATA OF MACROECONOMICS. Copyright © 2006 Thomson Learning 23 Measuring a Nation’s Income.

8 THE DATA OF MACROECONOMICS. Copyright © 2006 Thomson Learning 23 Measuring a Nation’s Income.
Summarize and Compare Responses  Mean (Average)  Median  Standard Deviation  Mean (Average)  Median  Standard Deviation.

Summarize and Compare Responses  Mean (Average)  Median  Standard Deviation  Mean (Average)  Median  Standard Deviation.
In-Patient Costs for Neurological Disorders By Katherine Ammon.

In-Patient Costs for Neurological Disorders By Katherine Ammon.
Naive Extrapolation1. In this part of the course, we want to begin to explicitly model changes that depend not only on changes in a sample or sampling.

Naive Extrapolation1. In this part of the course, we want to begin to explicitly model changes that depend not only on changes in a sample or sampling.
CE 374K Hydrology Frequency Factors. Frequency Analysis using Frequency Factors f(x) x xTxT.

CE 374K Hydrology Frequency Factors. Frequency Analysis using Frequency Factors f(x) x xTxT.
Nonparametrics and goodness of fit Petter Mostad 2005.10.31.

Nonparametrics and goodness of fit Petter Mostad
The ECB Survey of Professional Forecasters Luca Onorante European Central Bank* (updated from A. Meyler and I.Rubene) October 2009 *The views and opinions.

The ECB Survey of Professional Forecasters Luca Onorante European Central Bank* (updated from A. Meyler and I.Rubene) October 2009 *The views and opinions.
Quantitative Research Methods Project 3 Group 4A Valerie Bryan Emily Leak Lori Moore UWG Fall 2011.

Quantitative Research Methods Project 3 Group 4A Valerie Bryan Emily Leak Lori Moore UWG Fall 2011.
Review of Econ424 Fall 2007. –open book –understand the concepts –use them in real examples –Dec. 14, 8am-12pm, Plant Sciences 1129 –Vote Option 1(2)

Review of Econ424 Fall –open book –understand the concepts –use them in real examples –Dec. 14, 8am-12pm, Plant Sciences 1129 –Vote Option 1(2)

Similar presentations

Ads by Google