Contents
What happens to the regression line when you add random noise?
As more noise is added, the regression line indeed flattens. Of course, when adding random noise to data, one expects to get a different result each time. In our case, each time we fit a regression line to a different version of our noisy data, we expect to get a slightly different line.
What happens if noise is independent of all?
In regression, we assume noise is independent of all measured predictors. What happens if it isn’t? A number of key assumptions underlie the linear regression model – among them linearity and normally distributed noise (error) terms with constant variance In this post, I consider an additional assumption: the unobserved noise is uncorrelated
Can a causal model assume all noise is created equally?
However, in a causal context, all noise may not be created equally. Consider these two different causal models: U U (the noise) is similar for the two processes … for each data generating process, based on 1000 replications of samples of 100 individuals. Again, pretty similar:
Is the noise of a model unobservable or stochastic?
By definition, the noise is unobservable and stochastic. But, if we are developing models that involve causal relations of unmeasured quantities, we have to be explicit about the causal nature underlying these unmeasured quantities. That way, we know if we should be concerned about hidden correlation or not.
How can linear regression be used to predict an outcome?
Statistical researchers often use a linear relationship to predict the (average) numerical value of Y for a given value of X using a straight line (called the regression line). If you know the slope and the y -intercept of that regression line, then you can plug in a value for X and predict the average value for Y.
Can you predict Y from the slope of a regression line?
If you know the slope and the y -intercept of that regression line, then you can plug in a value for X and predict the average value for Y. In other words, you predict (the average) Y from X.