Linear and Generalized Linear Models
Confidence Intervals
CI: Mean
CI: Variance
CI: Regression Coefficients
Hypothesis Testing
\[ PE \pm CV \times SE \]
\[ (LB = PE - CV \times SE, UB = PE + CV \times SE) \]
A critical value is a cutoff point on a probability distribution used to:
It corresponds to a chosen significance or confidence level.
For a confidence level \(1 - \alpha\):
Interpretation:
“We are 95% confident that the true mean lies between A and B.”
Confidence Intervals
CI: Mean
CI: Variance
CI: Regression Coefficients
Hypothesis Testing
A (1 – α) confidence interval is:
\[ \bar{x} \pm Z_{\alpha/2} \cdot \frac{\sigma}{\sqrt{n}} \]
\[ \bar{x} \pm t_{\alpha/2; df} \cdot \frac{s}{\sqrt{n}} \]
Confidence Intervals
CI: Mean
CI: Variance
CI: Regression Coefficients
Hypothesis Testing
We want a confidence interval for the population variance \(\sigma^2\).
\[ \frac{(n-1)s^2}{\sigma^2} \sim \chi^2_{(n-1)} \]
This allows us to form a confidence interval for \(\sigma^2\) (variance) and then take the square root for \(\sigma\).
A (1–α) confidence interval is:
\[ \left( \frac{(n-1)s^2}{\chi^2_{\,\alpha/2,\;df}},\ \frac{(n-1)s^2}{\chi^2_{\,1-\alpha/2,\;df}} \right) \]
Confidence Intervals
CI: Mean
CI: Variance
CI: Regression Coefficients
Hypothesis Testing
\[ \frac{\hat\beta_j - \beta_j}{\mathrm{se}(\hat\beta_j)} \sim N(0,1) \]
\[ \frac{\hat\beta_j-\beta_j}{\mathrm{se}(\hat\beta_j)} \sim t_{n-p} \]
\[ \hat \beta_j \pm CV \times SE \]
Confidence Intervals
CI: Mean
CI: Variance
CI: Regression Coefficients
Hypothesis Testing
The confidence interval approach can evaluate a hypothesis test where the alternative hypothesis is \(\beta\ne\beta^*\). The confidence interval approach will result in a lower and upper bound denoted as: \((LB, UB)\).
If \(\beta^*\) is in \((LB, UB)\), then you fail to reject \(H_0\). If \(\beta^*\) is not in \((LB,UB)\), then you reject \(H_0\).