3
votes
Failing to get correct results for GLS regression
By default, glm for a gaussian family will use
$$\widehat{\mathrm{cov}}[\hat\beta]=\hat\sigma^2\left(X^TV^{-1}X\right)^{-1}$$
To use a known dispersion parameter ...
- 46.8k
2
votes
What does $\hat{\beta}_i = 0$ signify for OLS?
In the scatterplot of any $(x,y)$ data, the least squares fit (red line in the figure) will pass through the point of averages $(\bar x,\bar y),$ located at the intersection of the dotted axes.
When ...
- 334k
2
votes
Accepted
IV Estimation, Direct and Indirect Effects
Let $Y$ and $X$ represent the outcome and exposure variables, respectively, with the true data-generating process described by:
$$
\begin{aligned}
Y &= \alpha + \beta X + \gamma Z + \epsilon, \\
X ...
- 3,051
1
vote
Reducing extreme behavior in linear-exponential decay hybrid function
Without knowing what is the non-linear regression method and the numerical calculus you used to compute and draw your graphs it is difficult to determine the cause of the failures that you mention.
...
- 825
Only top scored, non community-wiki answers of a minimum length are eligible