Scribd Logo
Upload

Welcome to Scribd!

  • 33 views

    Lab Assignment

    Uploaded by

    Yogendra Panwar
    This document describes a panel data analysis of factors that influence the total cost of U.S. airlines from 1970 to 1984. It introduces the variables in the panel dataset, which include airline, year, fuel price, load factor, output, and total cost. An ordinary least squares multiple linear regression model is fitted to identify the relationships between the predictors and total cost. The model results and diagnostics are analyzed using STATA software.

    Copyright:

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

    Lab Assignment

    Uploaded by

    Yogendra Panwar
    33 views7 pages
    This document describes a panel data analysis of factors that influence the total cost of U.S. airlines from 1970 to 1984. It introduces the variables in the panel dataset, which include airline, year, fuel price, load factor, output, and total cost. An ordinary least squares multiple linear regression model is fitted to identify the relationships between the predictors and total cost. The model results and diagnostics are analyzed using STATA software.

    Original Description:

    Lab assignment

    Original Title

    Lab assignment

    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 describes a panel data analysis of factors that influence the total cost of U.S. airlines from 1970 to 1984. It introduces the variables in the panel dataset, which include airline, year, fuel price, load factor, output, and total cost. An ordinary least squares multiple linear regression model is fitted to identify the relationships between the predictors and total cost. The model results and diagnostics are analyzed using STATA software.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    33 views7 pages

    Lab Assignment

    Uploaded by

    Yogendra Panwar
    This document describes a panel data analysis of factors that influence the total cost of U.S. airlines from 1970 to 1984. It introduces the variables in the panel dataset, which include airline, year, fuel price, load factor, output, and total cost. An ordinary least squares multiple linear regression model is fitted to identify the relationships between the predictors and total cost. The model results and diagnostics are analyzed using STATA software.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 7

    Lab assignment

    Yogendra panwar
    19HS20048
    DATE 29/03/2023

    Variables in Panel Data


    In this panel dataset variables used are:

     I = Airline,
     T = Year,
     PF = Fuel price,
     LF = Load factor, the average capacity utilization of the fleet.
     Q = Output, in revenue passenger miles, index number,
     C = Total cost, in $1000, the data
    Methodology
    To identify the factors that influence the total cost of U.S. airlines, a
    multiple linear regression model was fitted using the predictors
    available in the dataset.
    The model is of the form:
    Total cost = β0 + β1Airline + β2Year + β3Output + β4Fuel price +
    β5*Load factor + ε
    where β0 is the intercept, β1 to β5 are the coefficients for the
    predictors, and ε is the error term.
    The model was fitted using the OLS (ordinary least squares) method,
    and the significance of the coefficients was tested using t-tests and p-
    values.
    The model was also evaluated for goodness of fit using the R-squared
    value and the residual plots.

    If assumptions do not hold, OLS estimates are BIASED and/or


    INEFFICIENT
     Biased - Expected value of parameter estimate is different from true.
    Consistency. If an estimator is unbiased, or if the bias shrinks as the
    sample size increases, we say it is CONSISTENT
     Inefficient - (Informally) Estimator is less accurate as sample size
    increases than an alternative estimator. o Estimators that take full
    advantage of information more efficient
    OLS Bias Due to Endogeneity
     Omitted Variable Bias o Intervening variables, selectivity
     Measurement Error in the Covariates
     Simultaneity Bias o Feedback loops o Omitted variables Conventional
    regression-based strategies to address endogeneity bias
     Instrumental Variables estimation

    OLS Inefficiency due to Correlated Errors


    Many data structures are susceptible to error correlation:
     Hierarchical data sample multiple individuals from each unit, e.g.
    household members, employees in firms, multiple pupils from each
    school.
     Multistage probability samples often incorporate cluster-based
    sampling designs with errors that may be correlated within clusters.
     Repeated observations data often show within-unit error correlation.

    STATA PART
    Notes:

    . *(6 variables, 90 observations pasted into data editor)

    . xtset i t
    panel variable: i (strongly balanced)
    time variable: t, 1 to 15
    delta: 1 unit

    .
    . summarize i t c q pf lf

    Variable Obs Mean Std. Dev. Min Max

    i 90 3.5 1.717393 1 6
    t 90 8 4.344698 1 15
    c 90 1122524 1192075 68978 4748320
    q 90 .5449946 .5335865 .037682 1.93646
    pf 90 471683 329502.9 103795 1015610

    lf 90 .5604602 .0527934 .432066 .676287

    . reg t c q pf lf

    Source SS df MS Number of obs = 90


    F( 4, 85) = 197.84
    Model 1517.05038 4 379.262594 Prob > F = 0.0000
    Residual 162.949622 85 1.91705438 R-squared = 0.9030
    Adj R-squared = 0.8984
    Total 1680 89 18.8764045 Root MSE = 1.3846

    t Coef. Std. Err. t P>|t| [95% Conf. Interval]

    c 1.37e-06 5.30e-07 2.58 0.012 3.14e-07 2.42e-06


    q -2.785735 1.116553 -2.49 0.015 -5.005742 -.5657278
    pf 9.37e-06 8.26e-07 11.34 0.000 7.72e-06 .000011
    lf 20.09563 3.790522 5.30 0.000 12.55906 27.63221
    _cons -7.698693 1.876634 -4.10 0.000 -11.42995 -3.967442
    . xtunitroot llc t, noconstant

    Levin-Lin-Chu unit-root test for t

    Ho: Panels contain unit roots Number of panels = 6


    Ha: Panels are stationary Number of periods = 15

    AR parameter: Common Asymptotics: root(N)/T -> 0


    Panel means: Not included
    Time trend: Not included

    ADF regressions: 1 lag


    LR variance: Bartlett kernel, 7.00 lags average (chosen by LLC)

    Statistic p-value

    Unadjusted t 0.0000 0.5000


    Adjusted t* -0.0229 0.4908

    . xtreg i c q pf lf
    the panel variable i may not be included as an independent variable
    r(198);

    . xtreg i t c q pf lf
    the panel variable i may not be included as an independent variable
    r(198);

    . xtreg t c q pf lf

    Random-effects GLS regression Number of obs = 90


    Group variable: i Number of groups = 6

    R-sq: within = 0.0000 Obs per group: min = 15


    between = 0.0000 avg = 15.0
    overall = 0.9030 max = 15

    Wald chi2(4) = 791.34


    corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0000

    t Coef. Std. Err. z P>|z| [95% Conf. Interval]

    c 1.37e-06 5.30e-07 2.58 0.010 3.29e-07 2.41e-06


    q -2.785735 1.116553 -2.49 0.013 -4.974139 -.5973306
    pf 9.37e-06 8.26e-07 11.34 0.000 7.75e-06 .000011
    lf 20.09563 3.790522 5.30 0.000 12.66635 27.52492
    _cons -7.698693 1.876634 -4.10 0.000 -11.37683 -4.020558

    sigma_u 0
    sigma_e 1.2755837
    rho 0 (fraction of variance due to u_i)
    Conclusion
    This report provides an analysis of a subset of a larger dataset
    containing cost data for U.S. airlines from 1970 to 1984. The subset
    consists of 90 observations on six firms for 15 years. The aim of this
    analysis is to identify the factors that influence the total cost of U.S.
    airlines and to build a predictive model for total cost based on the
    available predictors. The predictors include airline, year, output, fuel
    price, and load factor. The response variable is the total cost, measured
    in $1000.
    5.0e+06

    0 1 2 3
    5.0e+06

    4 5 6
    0

    0 5 10 15 0 5 10 15 0 5 10 15
    T
    I T
    C Q
    PF LF
    Graphs by I

    Thank You

    You might also like