Scribd Logo
Upload

Welcome to Scribd!

  • 115 views

    QCH 3

    Uploaded by

    lightknow
    This document contains 7 questions related to forecasting techniques including linear regression, moving averages, exponential smoothing, and seasonal decomposition. Specifically: - Question 1 analyzes stock price data using linear regression, moving averages, and forecasting. - Question 2 further examines forecasting accuracy using mean squared error on different techniques. - Question 3 repeats the analysis for another stock price series. - Question 4 again compares forecasting methods on this second series. - Question 5 uses seasonal decomposition and trend removal to forecast seasonal time series data. - Question 6 forecasts labor productivity using moving averages. - Question 7 compares proposed regression models to data using sums of squared errors.

    Copyright:

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

    QCH 3

    Uploaded by

    lightknow
    115 views2 pages
    This document contains 7 questions related to forecasting techniques including linear regression, moving averages, exponential smoothing, and seasonal decomposition. Specifically: - Question 1 analyzes stock price data using linear regression, moving averages, and forecasting. - Question 2 further examines forecasting accuracy using mean squared error on different techniques. - Question 3 repeats the analysis for another stock price series. - Question 4 again compares forecasting methods on this second series. - Question 5 uses seasonal decomposition and trend removal to forecast seasonal time series data. - Question 6 forecasts labor productivity using moving averages. - Question 7 compares proposed regression models to data using sums of squared errors.

    Original Description:

    khlkh

    Original Title

    qch3

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document contains 7 questions related to forecasting techniques including linear regression, moving averages, exponential smoothing, and seasonal decomposition. Specifically: - Question 1 analyzes stock price data using linear regression, moving averages, and forecasting. - Question 2 further examines forecasting accuracy using mean squared error on different techniques. - Question 3 repeats the analysis for another stock price series. - Question 4 again compares forecasting methods on this second series. - Question 5 uses seasonal decomposition and trend removal to forecast seasonal time series data. - Question 6 forecasts labor productivity using moving averages. - Question 7 compares proposed regression models to data using sums of squared errors.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    115 views2 pages

    QCH 3

    Uploaded by

    lightknow
    This document contains 7 questions related to forecasting techniques including linear regression, moving averages, exponential smoothing, and seasonal decomposition. Specifically: - Question 1 analyzes stock price data using linear regression, moving averages, and forecasting. - Question 2 further examines forecasting accuracy using mean squared error on different techniques. - Question 3 repeats the analysis for another stock price series. - Question 4 again compares forecasting methods on this second series. - Question 5 uses seasonal decomposition and trend removal to forecast seasonal time series data. - Question 6 forecasts labor productivity using moving averages. - Question 7 compares proposed regression models to data using sums of squared errors.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    BA 3352: Forecasting Questions

    1. Use the monthly average stock price of the United Defense to answer the following questions.
    Month 01/00 02/00 03/00 04/00 05/00 06/00 07/00 08/00 09/00 10/00 11/00 12/00
    Price 45 48 46 55 57 62 58 57 66 71 72 75
    Month 01/01 02/01 03/01 04/01 05/01 06/01 07/01 08/01
    Price 76 72 79 81 81 88 83 87
    a) Plot the data. Show your graph.
    b) Fit a linear regression line to the data using the least squares method. Draw the line on your graph
    of a) and write down the eqution of the line. Report

    xy,

    x,

    y,

    x
    2
    ,

    y
    2
    .
    c) Can the trend be explained well by the regression? Comment by making necessary computations.
    d) Based on your linear regression, estimate stock prices for September 01, March 02 and September 02.
    2. Refer to the previous question.
    a) Estimate stock price for the 21st month (September 01) by using 2 and 5 period-moving-averages.
    b) Estimate stock prices by using exponential smoothing with = 0.2 and = 0.6. You may start up
    with naive forecasting for the initial month(s).
    c) Use the forecasts for the last 12 months only to compute MSE for all four methods used in a) and
    b) above.
    3. Use the monthly closing stock price of the Lockheed Martin Corp. (LMT on NYSE) in 2001 and 2002,
    respectively below, to answer the following questions.
    Month 01/01 02/01 03/01 04/01 05/01 06/01 07/01 08/01 09/01 10/01 11/01 12/01
    Price 34.7 37.5 35.7 35.2 38.3 37.1 39.6 39.9 43.8 48.8 46.5 46.7
    Month 01/02 02/02 03/02 04/02 05/02 06/02 07/02 08/02
    Price 53.0 56.4 57.6 62.9 62.1 69.5 64.1 63.3
    a) Plot the data. Show your graph.
    b) Fit a linear regression line to the data. Note that the frequently used linear regression method
    minimizes the sum of the squares of errors. Draw the line on your graph of a) and write down the
    equation of the line. Report

    xy,

    x,

    y,

    x
    2
    ,

    y
    2
    . These sums are computed in the process of
    regression. For example, computation of these sums are illustrated in regression.xls.
    c) Can the trend be explained well by the regression? Comment by making necessary computations.
    This requires the computation of correlation, see the formula in the textbook.
    d) Based on your linear regression, estimate stock prices for September 02, March 03 and September 03.
    4. Refer to the previous question.
    a) Estimate stock price for the 21st month (September 02) by using 2 and 5 period-moving-averages.
    b) Estimate stock prices by using exponential smoothing with = 0.2 and = 0.6. You may start
    up with naive forecasting for the initial month(s).
    c) Use the forecasts for the last 12 months only to compute MSE for all four (two moving averages
    and two exponential smoothing) methods. An example of how MSE is computed can be found in the
    second sheet of regression.xls.
    1
    5. Quarterly demand data are given below for SwimWear of Plano.
    Wi99 Sp99 Su99 Fa99 Wi00 Sp00 Su00 Fa00 Wi01 Sp01 Su01 Fa01
    Demand 14 38 76 23 21 33 87 36 32 61 103 44
    Given that the data are seasonal and have trend, obtain seasonal indices and make quarterly forecasts
    for year 2002. You may want to use a spreadsheet similar to seasonalforecast.xls as they both rst
    remove the seasonality from the data and then nd the trend.
    6. SOM is cleaned by a cleaning crew every night, the table below shows the number of people per crew
    and the number of oce rooms cleaned.
    Day Crew size Number of oces cleaned
    Monday 2 28
    Tuesday 3 39
    Wednesday 1 15
    Thursday 5 48
    Use moving averages of the last three days to forecast the labor productivity on Friday. On Thursday,
    if we had used moving averages of the last three days to forecast thursdays labor productivity, what
    would the value of MAD have been?
    7. For the given weekly demand data below
    Week (t) 1 2 3 4
    Demand (D
    t
    ) 4 11 17 18
    two regression lines are proposed: D
    1
    t
    = 4 + 6t and D
    2
    t
    = 5 + 5t. Compute the sum of the square of
    the errors
    SS
    1
    :=
    4

    t=1
    (D
    t
    D
    1
    t
    )
    2
    and SS
    2
    :=
    4

    t=1
    (D
    t
    D
    2
    t
    )
    2
    for both lines. Determine which line ts better to the data. If you do linear regression starting only
    with the data, can you guarantee that the line D
    1
    t
    = 4 + 6t or D
    2
    t
    = 5 + 5t would be the outcome?
    2

    You might also like