You are developing a linear regression model and notice that despite a high R-squared value, none of your independent variables are statistically significant. What might be the potential issue here?
- Data leakage
- High variance
- Multicollinearity
- Underfitting
This could be due to multicollinearity. Multicollinearity inflates the variances of the parameter estimates, which might lead to none of them being statistically significant. Despite this, the overall model might still be significant, leading to a high R-squared value.
Loading...
Related Quiz
- When data is normally distributed, approximately 95% of the data falls within ________ standard deviations of the mean.
- For data with outliers, the _____ is typically a better measure of central tendency as it is less sensitive to extreme values.
- Why is standardization (z-score) often used in machine learning algorithms?
- When the outlier is a result of a data entry error, the best approach would often be ________.
- Multicollinearity can make the regression coefficients _________.