Ten fold

CrossValidated's general room for gossip, grumbles, and idle c...
Aug 18, 2020 21:39
Just a quick question that I don't think is worth asking a question. If $z ~ Bin(\pi, y)$ and $y ~ Poisson(\lambda)$, then is it true that $z ~ Poisson(\pi * \lambda)$ and $y - z ~ Poisson((1-\pi)*\lambda)$
 

 Mathematics

Associated with Math.SE; for both general discussion & math qu...
Apr 11, 2016 17:29
Any thoughts?
Apr 11, 2016 17:29
Hey guys, I am looking for some clarification on Lipschitz functions. I have two functions $f_1(x) = x*\cos(\frac{1}{x})$ and $f_2(x) = x^2 \cos(\frac{1}{x})$ and $f_i(x) = 0$ defined on $(-1, 1)$. Initially I thought that $f_1$ is Lipschitz, but after taking the derivatives, I see that $f_1$ derivative blows up at $|x|->0$.
Feb 19, 2016 01:51
Hi Guys, hope someone can help me with a 1st/2nd year problem.

Consider the linear homogeneious system $x' = A(t) x$ with $A(t)$ continuous on some domain. By our general uniqueness/existence theorem, we know there exists a unique solution to the initial value problem $x' = A(t)x$ with $x(t_0) = x_0$ on an open interval containing $t_0$ (In fact, this open interval is the domain of $A(t)$ but I digress).

Now I get confused when we start talking about fundamental solution sets and linear independence of solutions. The next part in the textbook talks about $n$ solutions of the system $x' =
Feb 12, 2016 01:29
Thanks! I hope you never quit chat.
Feb 12, 2016 01:29
oh, right, that my function is identically 0?
Feb 12, 2016 01:29
0 for all t
Feb 12, 2016 01:28
0
Feb 12, 2016 01:26
the first version in which the derivative is included has the $f(0)$ constant, but the second version dosnt. (in particular, the textbook that's asking the question is in the context of the second version)
Feb 12, 2016 01:25
not really. I can't type latex in here, but the two inequalities are given here
Feb 12, 2016 01:24
Hmm I am not sure @TedShifrin, I don't see what we can conclude from the fact f(0) = 0
Feb 12, 2016 01:21
well its clear that its zero
Feb 12, 2016 01:21
@TedShifrin There are a few different versions of it. But yes there is a $f(0)$ in it
Feb 12, 2016 01:17
Maybe something to do with the growth of the function being slower than exponential?
Feb 12, 2016 01:15
The question is just saying "what can you say about the function"
Feb 12, 2016 01:15
Oh yes, forgot to mention. For Gronwall's inequality, $f$ is non negative
Feb 12, 2016 01:14
@TedShifrin This is indeed true from the textbook.
Feb 12, 2016 01:10
if $f(x) \leq \int_0^x f(t) dt$
Feb 12, 2016 01:10
Hey guys! looking from the context of Gronwalls inequality, I am trying to answer "What can I say about a continuous function $f \colon \mathbb{R} \rightarrow [0, \infty]$
Aug 2, 2015 21:30
Does such an identity hold and if so, can someone point me to a quick proof of it
Aug 2, 2015 21:29
Does anyone know if the following identity holds: Suppose $F$ is the CDF of some RV. So $F(x) = \Pr(X < x)$. I am reading a paper, where they come across the inverse of the survival function $[1 - F(x)]^{-1}$ and reduce it to $F^{-1}(1 - x)$
 
Aug 30, 2015 19:35
@Johannes_B Thanks.
Aug 30, 2015 19:18
Do I need to run latex classfile.class?
Aug 30, 2015 19:18
I can just replace the \spacing command in the class file (say with \masfenix) and replace all occurrences of it?
Aug 30, 2015 19:18
Ahh, you learn something new everyday. Okay so back to the current question.
Aug 30, 2015 19:16
test*
Aug 30, 2015 19:15
Okay sorry haha.
Aug 30, 2015 19:15
@Johannes_B This is a set.
Aug 30, 2015 19:13
There are a few questions I have. Do you think its better to ask you directly here or start new threads on the main website? (ofcourse, after tinkering with it myself)
Aug 30, 2015 19:12
the formatting and stuff can be done until September 17th.
Aug 30, 2015 19:12
I am currently finishing my thesis which is due tomorrow.
Aug 30, 2015 19:12
It doesn't show up in my PDF output. Actually, do you mind if I can keep this chat open for a few hours/days?
Aug 30, 2015 19:10
Yeah, I've actually read a great Tex.SE thread on the @ symbol
Aug 30, 2015 19:09
I have no idea how to do this, but I am guessing something to do with starting the counter a bit early.
Aug 30, 2015 19:09
Okay. There are a few bits of new regulation. For example, I have to actually the TOC page number TO the TOC itself .
Aug 30, 2015 19:08
@Johannes_B Thanks. Last question: So a latex template is purely defined by its class file? Is a class file merely commands to keep the actual document cleaner, and that all the commands from the class file can actually be put in the .tex file itself?
Aug 30, 2015 19:08
I am fairly certain it was developed by a student at some point. Since the official university faculty website has no mention of it. I pasted the CTAN link below. After I finish my thesis, I do plan on cleaning up the class file (and learning some deep latex). Hopefully I can submit my work to the faculty and they can start using it as the official template.
Aug 30, 2015 19:08
@Johannes_B I will keep that in mind. My department buddy's thesis actually got rejected and they told him make several revisions. I am not sure how one would go about making those revisions without editing the class file though.
 
Jul 27, 2015 01:29
I will modify the cost function of cv.glm from 0 to 1 (my threshold) so that the delta values I get for each threshold, should match my FPR.
Jul 27, 2015 01:29
2) I will also use cv.glm() to do cross validation. This gives me a delta value which is the percentage of misclassified. I will replicate this 10 times (since each time cv.glm samples different groups of data, giving me a different delta value).
Jul 27, 2015 01:27
@MattKrause So based on what I've research so far, this is how I am going go to about it:

1) I will first use the entire dataset to fit a model. The package ROCR allows me to assess the performance of this model, and plot the goodness-of-fit by a ROC graph. Here, I was hoping to split my data to test and training, but all examples I look at consider the entire dataset. (I will be posting another question on this on the main SE).
Jul 27, 2015 01:06
but I cant find any information combining CV and ROC curves anywhere, nor even a succinct description of what CV does
Jul 27, 2015 01:06
Thanks. I also found the package ROCR which can give me ROC curves
Jul 27, 2015 00:46
Also, the delta (which is the MSE) from the CV function represents the misclassifications. Is this the false positive rate (ie, the x axis on the ROC curve)? It really dosnt give me the TPR so it would be hard to draw the curve
Jul 27, 2015 00:42
@MattKrause Unless that's a better thing. I was under the impression that to get accuracy of a model, one should fix that model
Jul 27, 2015 00:42
After thinking about it, I am not sure if the cost function can predict ROC curves. Because everytime I change the threshold, it will run my glm again K times
Jul 26, 2015 23:46
whoa, error bars? That's new to me. I don't see how the cost function in cv.glm() will provide error bars.
Jul 26, 2015 23:45
Suppose I wanted to do this step manually. Would it make sense to do split my dataset $Z = A + B$ and then fit the model on A and assess performance on B? To me this seems like a k = 1 CV and probably a very naïve way of doing it
Jul 26, 2015 23:43
@MattKrause Thanks, so the threshold needed for the ROC curve can be implemented in the cost function of the CV function?