Scribd Logo
Upload

Welcome to Scribd!

  • 21 views

    Measuring The Business Cycle

    Uploaded by

    lauralauraa01
    The document discusses methods for characterizing the business cycle by extracting the cyclical component from GDP data. It introduces the Hodrick-Prescott filter, which uses a mathematical equation to minimize deviations between GDP and its trend value, estimated as changing slowly over time. The filter separates GDP into trend and cyclical components based on the smoothing parameter lambda. Graphs and tables then show the cyclical components extracted from various economic data using this method.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Measuring The Business Cycle

    Uploaded by

    lauralauraa01
    21 views13 pages
    The document discusses methods for characterizing the business cycle by extracting the cyclical component from GDP data. It introduces the Hodrick-Prescott filter, which uses a mathematical equation to minimize deviations between GDP and its trend value, estimated as changing slowly over time. The filter separates GDP into trend and cyclical components based on the smoothing parameter lambda. Graphs and tables then show the cyclical components extracted from various economic data using this method.

    Original Title

    2. Measuring the Business Cycle

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses methods for characterizing the business cycle by extracting the cyclical component from GDP data. It introduces the Hodrick-Prescott filter, which uses a mathematical equation to minimize deviations between GDP and its trend value, estimated as changing slowly over time. The filter separates GDP into trend and cyclical components based on the smoothing parameter lambda. Graphs and tables then show the cyclical components extracted from various economic data using this method.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    21 views13 pages

    Measuring The Business Cycle

    Uploaded by

    lauralauraa01
    The document discusses methods for characterizing the business cycle by extracting the cyclical component from GDP data. It introduces the Hodrick-Prescott filter, which uses a mathematical equation to minimize deviations between GDP and its trend value, estimated as changing slowly over time. The filter separates GDP into trend and cyclical components based on the smoothing parameter lambda. Graphs and tables then show the cyclical components extracted from various economic data using this method.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 13

    Characterizing the Business Cycle

    Hodrick-Prescott Filter
    First-differencing eliminates the trend component but it
    amplifies the effect of high frequency noise
    • Y(t) denotes the actual GDP at time t, the trend component is
    denoted Ytg and the cyclical component Ytc.
    • The mean value of the cyclical component is 1 (an assumption
    that is convenient as will be seen below). In other words,

    Yt = Yt g × Yt c
    E[Yt ] = Yt g
    ln(Yt ) = ln(Yt g ) + ln(Yt c )
    E[Yt c ] = 1
    y t = ln(Yt ) g t = ln(Yt g ) ct = ln(Yt c )
    y t = g t + ct
    There are, potentially, many different models that can be
    used. For example, we may assume that the growth rate is
    constant over time. This implies that the trend is a straight
    line (a linear trend). The cyclical component is then current
    GDP growth minus a constant growth term.

    But, we know that (or we may assume that) the long-term


    growth rate varies slowly over time. If this is the case,
    with a straight line as the trend we obtain a poor
    estimate of the cyclical component. We, then, need
    another model that we can use to extract the cyclical
    component from GDP.
    A bit of mathematics
    Yt = Yt g × Yt c
    ln(Yt ) = ln(Yt g ) + ln(Yt c )
    yt = g t + ct
    ct = yt − g t
    Y g
    + Y − Y g
    Yt +∆
    g
    ∆
    ct = ln(Yt ) − ln(Yt g ) = ln( t t t
    ) = ln( ) ≈
    Yt g Yt g Yt g

    The cyclical component represents the relative deviation


    of the GDP from its long-run growth path.
    T
    HP Filter
    min ∑ ( yt − g t ) 2 + λ[( g t − g t −1 ) − ( g t −1 − g t − 2 )]2
    t =1
    If λ=0, the trend component coincides with the original time series.
    The cyclical component is zero.

    If λ tends to infinity, the HP filter ends up to be a linear trend, i.e


    the growth rate would be constant over time.

    The value of λ is
    • Yearly data λ=100
    • Quarterly data λ=1600
    • Monthly data λ=14400
    Figure 1.2
    Natural Logarithm of Per Capita Real
    GDP
    Yt = Yt g × Yt c
    ln(Yt ) = ln(Yt g ) + ln(Yt c )
    yt = g t + ct

    1-7 © 2014 Pearson Education, Inc.


    Figure 1.3
    Natural Logarithm of Per Capita Real GDP
    and Trend
    Yt = Yt g × Yt c
    ln(Yt ) = ln(Yt g ) + ln(Yt c )
    yt = g t + ct

    1-8 © 2014 Pearson Education, Inc.


    Figure 1.4
    Percentage Deviations from Trend in
    Per Capita Real GDP

    Yt = Yt g × Yt c
    ln(Yt ) = ln(Yt g ) + ln(Yt c )
    yt = g t + ct
    ct = yt − g t

    1-9 © 2014 Pearson Education, Inc.


    Figure 3.9
    Percentage Deviations from Trend in
    Real Consumption and Real GDP
    Figure 3.10
    Percentage Deviations from Trend in
    Real Investment and Real GDP
    Table 3.1
    Correlation Coefficients and Variability of
    Percentage Deviations from Trend
    Table 3.2
    Summary of Business Cycle Facts

    You might also like