Academic Integrity: tutoring, explanations, and feedback — we don’t complete graded work or submit on a student’s behalf.

1. Run a regression of voteA (the percentage of votes received by candidate A) a

ID: 3206935 • Letter: 1

Question

1. Run a regression of voteA (the percentage of votes received by candidate A) against lexpendA, lexpendB, prtystrA, democA. By how many standard deviations would candidate A’s vote share increase if their log campaign expenditures increased by one standard deviation?

I ran the regression which I show below. Please show work to show me how to answer the second part of the question.

. regress voteA lexpendA lexpendB prtystrA democA

  

. regress voteA lexpendA lexpendB prtystrA democA

      Source |       SS           df       MS      Number of obs   =       173

-------------+----------------------------------   F(4, 168)       =    169.23

       Model | 38822.1774         4 9705.54436   Prob > F        =    0.0000

    Residual | 9635.07113       168 57.3516139   R-squared       =    0.8012

-------------+----------------------------------   Adj R-squared   =    0.7964

       Total | 48457.2486       172 281.728189   Root MSE        =    7.5731

------------------------------------------------------------------------------

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

-------------+----------------------------------------------------------------

    lexpendA |   5.779294   .3918197    14.75   0.000      5.00577    6.552819

    lexpendB | -6.237836   .3974596   -15.69   0.000    -7.022495   -5.453178

    prtystrA |   .2519176   .0712925     3.53   0.001     .1111729    .3926623

      democA |   3.792943    1.40652     2.70   0.008     1.016213    6.569674

       _cons |   37.66142   4.736036     7.95   0.000      28.3116    47.01123

------------------------------------------------------------------------------

Explanation / Answer

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

-------------+----------------------------------------------------------------

    lexpendA |   5.779294   .3918197    14.75   0.000      5.00577    6.552819

    lexpendB | -6.237836   .3974596   -15.69   0.000    -7.022495   -5.453178

    prtystrA |   .2519176   .0712925     3.53   0.001     .1111729    .3926623

      democA |   3.792943    1.40652     2.70   0.008     1.016213    6.569674

       _cons |   37.66142   4.736036     7.95   0.000      28.3116    47.01123

For candidate A the std error is 0.3918197 is the standard deviation error of the the coefficient , which means that there will be change of 0.3918197 SD if the  log campaign expenditures increased by one standard deviation

Without the actual data , it is really difficult to show you the workings and the question becomes merely the interpretation of the results