Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
E
Evaluating Networked Systems
Project
Project
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Commits
Issue Boards
Open sidebar
Robert Ricci
Evaluating Networked Systems
Commits
8ec5a9ff
Commit
8ec5a9ff
authored
Mar 12, 2015
by
Robert Ricci
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Remove some stuff I won't talk about this time
parent
6af97bef
Changes
1
Hide whitespace changes
Inline
Sidebyside
Showing
1 changed file
with
8 additions
and
13 deletions
+8
13
lecturenotes.tex
lectures/lecture16/lecturenotes.tex
+8
13
No files found.
lectures/lecture16/lecturenotes.tex
View file @
8ec5a9ff
...
...
@@ 15,7 +15,7 @@
\begin{outline}
\1
Today: How well does your data fit a line?
\2
More complicated regressions exist, of course, but we'll stick with this one for now
\2
Talk about linear in detail, look at some more complicated ones in R
\2
Eyeballing is just not rigorous enough
\1
Basic model:
$
y
_
i
=
b
_
0
+
b
_
1
x
_
i
+
e
_
i
$
...
...
@@ 74,17 +74,6 @@
\3
For example: How sure are we that two slopes are actually different
\2
\textit
{
When would we want to show that the confidence interval for
$
b
_
1
$
includes zero?
}
\1
Confidence intervals for predictions
\2
Confidence intervals tightest near middle of sample
\2
If we go far out, our confidence is low, which makes intuitive sense
\2
$
s
_
e
\big
(
\frac
{
1
}{
m
}
+
\frac
{
1
}{
n
}
+
\frac
{
(
x
_
p

\overline
{
x
}^
2
)
}{
\sum
_{
x
^
2
}

n
\overline
{
x
}^
2
}
\big
)
^
\frac
{
1
}{
2
}$
\2
$
s
_
e
$
is sttdev of error
\2
$
m
$
is how many predictions we are making
\2
$
p
$
is value at which we are predicting (
$
x
$
)
\2
$
x
_
p

\overline
{
x
}$
is capturing difference from center of sample
\2
\textit
{
Why is it smaller for more
$
m
$}
?
\3
Accounts for variance, assumption of normal distribution
\1
Residuals
\2
AKA error values
\2
We can expect several things from them if our assumptions about regressions are correct
...
...
@@ 94,6 +83,11 @@
\2
QQ plot of error distribution vs. normal ditribution
\2
Want the spread of stddev to be constant across range
\1
Switch to R
\2
Show example of linear fitting (good fit)
\2
Show example of linear fitting (bad fit)
\2
Show example of polynomial fit (intercept and 3 coefficients)
\1
For next time
\2
I won't be here week after spring break
\2
papers3 due Tuesday of spring break week
...
...
@@ 102,7 +96,8 @@
\2
lab2 now due Friday after spring break
\3
I want some more from you now, so be sure to update your fork
\3
Mainly, I want to know how you will improve the graph you
are reproducing
are reproducing, and to actually look a bit at the code you
find
\end{outline}
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment