|
Size: 394
Comment: Initial commit
|
← Revision 8 as of 2025-04-29 19:24:08 ⇥
Size: 807
Comment: Relabel
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 3: | Line 3: |
| In econometrics, '''homoskedasticity''' is an assumption about data used for statistical inference. | '''Homoskedasticity''' means that the variance of the error term is constant and not correlated to any predictors. |
| Line 11: | Line 11: |
| == Meaning == | == Description == |
| Line 13: | Line 13: |
| Homoskedasticity means that the variance of the error term is constant and not correlated to any treatment or control variable. | Mathematically, homoskedasticity and [[Statistics/Exogeneity|exogeneity]] together can be expressed as: {{attachment:exo.svg}} The full set of variables is independently and normally distributed about 0. The [[Statistics/CovarianceMatrices|covariance matrix]] is fully specified as the [[LinearAlgebra/SpecialMatrices#Diagonal_Matrices|diagonal matrix]] of variances. |
| Line 16: | Line 20: |
It can also be useful to express exogeneity as a [[Statistics/ConditionalExpectations|conditional expectation]] like: {{attachment:cond.svg}} |
Homoskedasticity
Homoskedasticity means that the variance of the error term is constant and not correlated to any predictors.
Contents
Description
Mathematically, homoskedasticity and exogeneity together can be expressed as:
The full set of variables is independently and normally distributed about 0. The covariance matrix is fully specified as the diagonal matrix of variances.
The opposite condition is heteroscedasticity.
It can also be useful to express exogeneity as a conditional expectation like:
