[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]
2023-11: Warosu is now out of extended maintenance.

/sci/ - Science & Math

View post   
File: 51 KB, 700x648, 1279810571870.jpg [View same] [iqdb] [saucenao] [google]
2986732 No.2986732 [Reply] [Original]

Anyone here with an Economics degree? I need some help with a few T/F econometrics questions.

1)If we apply Zellner Efficient Least Squares to a set of equations that are not simultaneous, the resulting estimates are not any better than ordinary least squares.


2) If we apply Zellner Efficient Least Squares to a set of equations that are not simultaneous, and one equation has an omitted variable, then all the estimated coefficients in all the equations are biased and inconsistent.

3) Omitting relevant variables increases the efficiency of the ols estimates of the remaining variables.

in return, stencils

>> No.2986762
File: 63 KB, 614x598, 1279443966812.jpg [View same] [iqdb] [saucenao] [google]
2986762

bumpinggg

>> No.2986785
File: 57 KB, 533x650, 1279444251542.jpg [View same] [iqdb] [saucenao] [google]
2986785

bump

>> No.2986852
File: 60 KB, 1727x1092, 1279444328302.jpg [View same] [iqdb] [saucenao] [google]
2986852

>> No.2987026
File: 48 KB, 1216x684, 1279444294535.jpg [View same] [iqdb] [saucenao] [google]
2987026

>> No.2987545
File: 44 KB, 540x510, 1279444501791.jpg [View same] [iqdb] [saucenao] [google]
2987545

bumps

>> No.2988106
File: 13 KB, 300x333, 1279018313799.jpg [View same] [iqdb] [saucenao] [google]
2988106

>> No.2988229

of god wtf. I thought economics was just a whole lot of sociology with some graphing involved.

definitely the most scientific business degree

>> No.2988379

Never heard aboud Zellner ELS and I've done advanced econ.
I'm not sure for number 3, but if you remove relevant variables, then their effect will be shifted in the error terms and there will be a correlation between error terms and explanatory variables. Efficiency if I recall correctly means that the estimator is unbiased and converges to the FDCR bound.
Don't know if it helps but you may find something useful in my post :)