Doh! Thanks very much. sg
On 11/6/23 5:17 PM, John Fox wrote:
Dear Spencer,
You need the t distribution with correct df, not the standard-normal
distribution:
> pt(-z.confInt/2, df=13)
1 2 3 4 5 6 7 8 9 10 11
0.025 0.025 0.025 0.025 0.025 0.025 0.
Hello, All:
I am unable to manually replicate predict.lm, specifically comparing
se.fit with (fit[,3]-fit[,2]): I think their ratio should be
2*qnorm((1-level)/2), and that's not what I'm getting.
Consider the following slight modification of the first example in
help('predict.lm'):
2 matches
Mail list logo
