**Confidence Intervals**Hello all,
Does anybody have any experience in calculating confidence intervals
(CIs) on the output of the neural network? I'm stuck in one part of it
and desperately looking for help.
A reference would be:
Confidence Interval Prediction for Neural Network Models,
George Chryssoloiuris, Moshin Lee, and Alvin Ramsey,IEEE TRANSACTIONS
ON NEURAL NETWORKS, VOL. I, NO. 1, JANUARY 1996 229
This paper describes the calculation of the CIs using least squares
estimation. I'm stuck in the calculation of the Jacobian matrix,
partial derivative matrix of the output w.r.t. the weights.
Any help...

**Confidence Interval**Is it possible to calculate 2-sided exact 95% confidence intervalse based on
the Blyth-Still-Casella method in SAS?
Thanks
...

**confidence intervals**I have a matrix A with random values as elements. How can I calculate the mean m, standard deviation s and the confidence intervals s+m and s-m?.I have no other information about the kind of didtribution
nk=rand(1000,1);
A=-log(nk);
Sn=sum(A);
p=A/Sn;
b=0;
for i=1:100
for N=100:100:1000
b=b+(i/N)*(b(i)/Sn); %just sth I want to calculate
end
end
And then, how can I plot s,m+s,m-s in the same graph with b in the y-axis and N in the x-axes??
I'm really stuck! Any help would be appreciated...
"Konst " <konstance1@hotmail.com> wrote in message ...

**confidence intervals**Can I build a query expression to calculate confidence intervals on a
set of data? Excel has this function built-in, but I think Access
does not.
thanks in advance
John
...

**confidence interval**can any one tell me if there is any command in matlab to find the
confidence interval of a data set.
regards
hrushi
hrushi wrote:
> can any one tell me if there is any command in matlab to find the
> confidence interval of a data set.
How do you define
"confidence interval of a data set" ?
Hope this helps.
Greg
please elaborate.
regards
hrushi
...

**glmfit output**Thanks to anyone who tries to help!
I am using glmfit to get the coefficients and stats for a generalized
linear model with a one-column response variable (y) and a 3-column
predictor variable (x). In other words,
[B,D,STATS] = glmfit(x,y,'normal');
My question is: Which variable in the STATS struct can be used to
understand the proportion of variability in y that is accounted for
by each of the three columns of x, and whether they are significant.
If the answer can be found in STATS.coeffcorr, what are the rows and
columns of this array (in my case a 4x4). I tried exploring this
...

**Matlab Confidence Intervals**I have non-normal data. How do I go about calculating the 60% confidence interval about the mean? I assume just summing up the area under the curve and outputing the values at 0.2 and 0.8 would be around the median, but what about the mean?
I should add that it's really a non-normal probability distribution and not data.
...

**confidence interval periodogram**Hi!
I would like to know how to compute the confidence interval for a
power spectrum computed with the periodogram method and to plot it in
the graph.
Thank you.
...

**GRNN and Confidence Interval**Has anyone stumbled on this subject? I'm reading a thesis where the author
has modified GRNN so that it gives
the confidence interval for the output, but I really don't understand the
equation that the author has given (there isn't any description for it).
An article that contains the formula can be read from following address
icsl.marc.gatech.edu/papers/ISSV-2003.pdf
If someone understands how the confidence interval is calculated in GRNN, I
would be grateful if he could clarify the subject.
Best Regards,
- Sami
Sami Lakka wrote:
> Has anyone stumbled on this subject?...

**Computing confidence intervals**Hi all.
I have this application where I have several minutes of
acoustic recordings at a few tens of kHz sampling frequency.
I need to compute power spectra from these data with
confidence intervals.
I use a one-pass variance estimator (pseudo code):
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
X1=3D 0; % Nfft x 1 data vectors
X2=3D 0;
for k=3D1:K
Xk=3Dabs(fft(xk)); % Magnitude spectrum of k'th data frame
X1=3DX1+xk; % Accumulate magnitude spectra
X2=3DX2+xk.^2; % Accumulate power spectra
end
Xmean =3D X1/K; % Compute the mean magnitude...

**confidence interval for proportions**i have a sample of of 100 subjects, of them, 2 are over 50 years old.
Now i want to construct a 95% confidence interval for the mean of
number of subjects age>50 for the whole population. how can i do this
in sas?
also,how do i do one-sided C.I. in sas?
one last quesiton, how do i use sas to construct C.I. for the
differences of two means of two different population (each with a
different sample size )
Thanks a lot!!
...

**confidence interval #7**hi friends,
I need some quick help.I am a sas programmer from IT background.I was
asked be a
pharmaco kinetist in our company to find the confidence intervals and
ratio of least squares mean on Cmx,Tmax,AUC and t1/2-
male vs female and weightas covariate.Can anybody pl help me How can I
do this.
your hep is really appreciated.
...

**Confidence intervals in rstool**I am using rstool Quadratic Response Surface Models (Stasistics
Toolbox) and I would like to know if 95% Confidence Interval (CI) for
predicted value is equal to
CI = +- 2*s / sqrt(n)
where s is standard deviation, and n is number of measurements. I
would also like to know if the definition of CI used in rstool is
written somewhere in the manuals.
Henri Seppanen wrote:
> I am using rstool Quadratic Response Surface Models (Stasistics
> Toolbox) and I would like to know if 95% Confidence Interval (CI) for
> predicted value is equal to
>
> CI = +- 2*s / sqrt(n)
>
> wher...

**Confidence Interval #2**I have written a MATLAB program to line a linear line of best fit. I
know need to produce error bars for every x meters that indicates the
confidence interval. What would be the best method?
Peter wrote:
>
>
> I have written a MATLAB program to line a linear line of best fit.
> I
> know need to produce error bars for every x meters that indicates
> the
> confidence interval. What would be the best method?
if you don't want to use your own program you could use the second
output of <polyfit>
if you want to use your own program, take a look at <bootstrp>
a...

**confidence intervals regress**
Hi there,
Suppose I have the simple linear model y=b0+b1*x1+b2*x2+e.
I want to estimate b0,b1,b2 and calculate a confidence
interval for them. Then I want to see how many times the CI
contains the true parameter. If I was making everything
right, for 1000 repetitions, that should be approximately
950 times. But I am getting 1000 times as a result. What
wrong with my code?
And another question. The formula used for estimating 95%
CI in the regress function is b0_hat-Za*SE(b0_hat) where
Za=1.96 right? But nor this formula, nor the more precise
Za=1.95996398454002 seems to agree exactl...

**Asymptotic confidence interval**How do i compute a 90 % asymptotic confidence interval for t, where
binomial distribution is (n C t)*(L^t)*(1-L)^(n - t).
Many Thanks
"Georgina " <georgina.cocker08@imperial.ac.uk> wrote in message <hl1nnt$khm$1@fred.mathworks.com>...
> How do i compute a 90 % asymptotic confidence interval for t, where
> binomial distribution is (n C t)*(L^t)*(1-L)^(n - t).
>
> Many Thanks
1) looks like homework
2) asymptotic means "for large n"?
...

**confidence interval #4**Hi,
I am a bit clue less on how to put a 95% Confidence interval on some coherence estimate I have done.
Any help is GREATLY appreciated
Thanks
A
Atreyee Bhattacharya wrote:
> Hi, I am a bit clue less on how to put a 95% Confidence interval on
> some coherence estimate I have done. ...
Bendat & Piersoll, Engineering Applications of Correlation and Spectral
Analysis, Wiley
--
...

**rloess confidence interval**Hello.
I am using smooth.m with the 'rloess' -option. As far as I
can tell there is no way I can get hands on the confidence
interval? Does anybody have a suggestion / function /
alternative approach to fitting / smoothing with a rloess
and actually getting the confidence interval ?
Thanks, Jonas.
...

**Bootstrap confidence interval**Hi,
"bootci" from statistics toolbox can find the confidence interval for
a parameter.
I have an older version of statistics toolbox, which do not have this
command. Is there any other way to find the confidence interval.
Thanks in advance,
Raj
raj wrote:
>
>
> Hi,
>
> "bootci" from statistics toolbox can find the confidence interval
> for
> a parameter.
>
> I have an older version of statistics toolbox, which do not have
> this
> command. Is there any other way to find the confidence interval.
>
> Thanks in advance,
> Raj
I ...

**Empirical Confidence Interval**Hi,
Does anyone know how to obtain an empirical confidence interval?
Michael
...

**Confidence Interval #5**Hello everyone,
I have to calculate the Confidence Interval and i m not sure what am i
doing wrong coz when i put it in PROC MEANS i get nothing.
I have to compute the CI for just a number. This number is a the
percentage of people who took the test out of all the students.
So say i have
perc=took_test/all*100;
Now i have to calculate its Confidence interval.
I was doing
proc means data=calc CLM alpha=0.05;
var perc;
output out=cintv;
run;
But this doesn't give me the CI.
Can someone plz help me out.
Thanks in advance.
SUBSCRIBE SAS-L Anonymous ,
Try the following:
proc means
...

**confidence intervals for percentages?**I have a big sample dataset that includes a raked weight variable for
the whole file. I am using PROC FREQ with a WEIGHT statement, and this
gives me weighted percentages. How do I calculate 95% confidence
intervals around these estimates?
Sarah Carroll, PhD
Research Coordinator
DHS - Immunization Branch, MS 7313
2151 Berkeley Way, Room 723E, Berkeley CA 94704
tel: 510.540.2484 fax: 510.883.6015
email: scarroll@dhs.ca.gov
Sarah,
Look at the 'Exact. statement for proc freq.
Toby Dunn
From: "Carroll, Sarah (DHS-DCDC-IMM)" <SCarroll@DHS.CA.GOV>
Reply-To: &qu...

**confidence interval #2**Hi, Dear All:
Is there a SAS procedure that can calculate the confidence interval of a
percentage?
Thanks
Jianying
On 3 Sep 03 17:14:56 GMT, Jianying.Zhang@UMASSMED.EDU (Zhang,
Jianying) wrote:
>Is there a SAS procedure that can calculate the confidence interval of a
>percentage?
proc freq with the /bin option in the tables statement.
JW
Not to my knowledge. However, it is a really simple function of the
percentage p and complement (1-p), along with n.
You can write a simple macro
%macro _cip(_p=,_lev);
q=1-&_p;
zval=probit(1-&_lev/2);
cihigh=&_p+sqrt(&_p*q/n)...

**confidence interval #3**Dear all,
I have a program as the following, it will generate the chi-square and p.chisq of (b1 + b2), How can I also get confident interval of (b1 + b2)?
Thanks very much.
proc genmod data=test;
model y = x1 x2 /link=log dist=gamma scale=p;
output out=exp p=yhat;
contrast "b1 + b2=0"
b1 1
b2 1 /wald;
---------------------------------
Do you Yahoo!?
Protect your identity with Yahoo! Mail AddressGuard
If you want a confidence interval for b1+b2, then use an ESTIMATE
statement instead of a CONTRAST statement. The syntax of the
...