Skip to content

Interpreting ANOVA / quantile regression results

2 messages · Yunqi Zhang, Bert Gunter

#
Hi all,

I think this is probably a very simple question related to ANOVA or
quantile regression.

Let's say if I'm doing ANOVA on 2 factors (f_a and f_b) and trying to
figure out whether they have an impact on the output. The result shows me
that f_a has a significant impact while f_b does not as following, where
the std. error (confidence interval) is

         estimate    std. error      p-value
f_a    10              0.2               0.001
f_b    0.5             2                  0.56

If I take this result, and I want to make my best guess for the output of a
pair of f_a and f_b values. Should I calculate the output using both f_a
and f_b or only the f_a because f_b is statistically insignificant? And
what the std. error (confidence interval) would be?

Specifically, should I do

guessed output = 10 * f_a + 0.5 * f_b and the std. error is 0.2 + 2 = 2.2

or

guessed output = 10 * f_a and the std.err is 0.2

Thank you very much!

Yunqi
#
This is off topic here.Post to a statistics forum like
stats.stackexchange.com instead -- or talk to your professor or TA (if
you're a student).

Cheers,
Bert

Bert Gunter
Genentech Nonclinical Biostatistics
(650) 467-7374

"Data is not information. Information is not knowledge. And knowledge
is certainly not wisdom."
Clifford Stoll
On Fri, Nov 21, 2014 at 8:56 PM, Yunqi Zhang <yqzhang at ucsd.edu> wrote: