o******e
发帖数: 1001 | 1 【 以下文字转载自 Statistics 讨论区 】
发信人: onehouse (万物皆势，无道常驻。), 信区: Statistics
标 题: Kernel Density Estimation
发信站: BBS 未名空间站 (Fri Feb 8 17:59:22 2013, 美东)
最近工作要用kernel density estimation.查了一下网上，发现好多都是讲如何
estmiate the density for points. 但是我目前的问题是，我在一个平面上有好多直
线，需要estimate这些线的density，网上好像有一个说法叫Kernel Density
Estimation for linear feature, 但是很难发现它的一些理论推导，有谁对这个有印
象吗？谢谢！ |
|
a***m
发帖数: 74 | 2 Hello,
I wonder if anyone have experience using Nolan 1997 'Numerical calculation
of stable densities and distribution functions" formula to calculate stable
densities.
I have some problem with the results when beta is non-zero. If beta is zero,
my limiting case agree with normal density and Cauchy densities, although
there are some discontinuity when x to be around +-6 (far extreme cases).
When beta is non-zero, in other words distribution is skewed, somehow my
code could not generate sensible |
|
a***m
发帖数: 74 | 3 Hello,
I wonder if anyone have experience using Nolan 1997 'Numerical calculation
of stable densities and distribution functions" formula to calculate stable
densities.
I have some problem with the results when beta is non-zero. If beta is zero,
my limiting cases agree with Normal density and Cauchy densities, though
there are some discontinuities when x to be around +-6. When beta is non-
zero/distribution is skewed, somehow my code could not generate sensible
results.
Does anyone have any expe |
|
a***m
发帖数: 74 | 4 Hello,
I wonder if anyone have experience using Nolan 1997 'Numerical calculation
of stable densities and distribution functions" formula to calculate stable
densities.
I have some problem with the results when beta is non-zero. If beta is zero,
my limiting cases agree with Normal density and Cauchy densities, though
there are some discontinuities when x to be around +-6. When beta is non-
zero/distribution is skewed, somehow my code could not generate sensible
results.
Does anyone have any expe |
|
o******e
发帖数: 1001 | 5 最近工作要用kernel density estimation.查了一下网上，发现好多都是讲如何
estmiate the density for points. 但是我目前的问题是，我在一个平面上有好多直
线，需要estimate这些线的density，网上好像有一个说法叫Kernel Density
Estimation for linear feature, 但是很难发现它的一些理论推导，有谁对这个有印
象吗？谢谢！ |
|
y*****t
发帖数: 186 | 6 【 以下文字转载自 Physics 讨论区 】
发信人: yjacket (yjacket), 信区: Physics
标 题: 一个关于packing density的问题。
发信站: BBS 未名空间站 (Fri Feb 17 12:04:25 2012, 美东)
如果版面不对，请帮忙转发一下。谢谢。
有10个大球，20个小球。所有的球都是理想状态球形，同样材料。小球是大球重量的一
半。（所以两种情况下，重量都是一样的。）
现在有一个容器，如果10个大球能够装下，20个小球是否也能装下？这两种情况的
packing density是否一样？我这里的packing density是重量/（球体积+球之间的空位
体积）。 |
|
m*********1
发帖数: 42 | 7 Does any one know where I can find a proof (in English or Chinese) of the
strong Chebotarev Density theorem? By "strong" I mean the version with
natural density rather than the one with Dirichlet density. |
|
A******u
发帖数: 1279 | 8 surface density of what? density of atoms? local electronic density of
states? or some other excitations? |
|
a***m
发帖数: 74 | 9 Hello,
I am wondering if anyone have experience with Nolan1997 paper" Numerical
calculation of stable densities and distribution functions" formula to
calculate stable density functions?
I have some problems with the results for non-zero beta (skewness parameter)
. For zero beta, my limiting cases agree with Normal and Cauchy density
functions, though when x is around +-6, there are some jumps in the results.
For non-zero beta, my results don't make sense when x is around zero.
Any experience or |
|
a***m
发帖数: 74 | 10 Hello,
I am wondering if anyone have experience with Nolan 1997 paper "Numerical
calculation of stable densities and distribution functions." in calculating
stable densities. I have some problems with the results when beta is non-
zero. For zero beta, my limiting cases agree with Normal and Cauchy
distribution, though there are some jumps when random variable is around +-6
. For non-zero beta, densities do not make sense when the random variable is
around zero.
Any experience or suggestion to sh |
|
h******5
发帖数: 58 | 11 Sorry can't type Chinese in my company.
I am working on a project to calculate VaR based implied Risk Neutral
Density. Firstly I calculate implied vols from deep in-the-money to deep-out
-money option chains, then smooth out the vol smile and calcualte Risk
Neutral Density based on BS model(esstentially RND is calculated by the
second derivative of option prics to strke). Finally fit a parametric
distribution to the densities based on least square method. I got some
chanellenges that 1) the shap... 阅读全帖 |
|
h******5
发帖数: 58 | 12 Sorry can't type Chinese in my company.
I am working on a project to calculate VaR based implied Risk Neutral
Density. Firstly I calculate implied vols from deep in-the-money to deep-out
-money option chains, then smooth out the vol smile and calcualte Risk
Neutral Density based on BS model(esstentially RND is calculated by the
second derivative of option prics to strke). Finally fit a parametric
distribution to the densities based on least square method. I got some
chanellenges that 1) the shap... 阅读全帖 |
|
A8
发帖数: 20 | 13 先谢过了.. 有包子奖励..
Two dependent continuous random variable X=h(W), Y=g(W), W is un underlying random
variable. Both X and Y have strictly positive density on R or the same valid domain. fx(x)>0, and fy(y)>0. I want to know if Z=X+Y have strictly positive density or not, fz(z)>0
on the domain???
I forgot to say that g and h are known functions. for example, both X and Y could be lognormals with different parameters, but with the same underlying normal random variable W.
While the density of Z=X+Y,... 阅读全帖 |
|
M*******a
发帖数: 1633 | 14 张是不是说两个prime number之间的间隔有个常数上限的是不是，也就是说每经过这个
间隔必有至少一个prime number，也就是[0, N]之间prime number的密度有个下限，不
管N多大。
然后有prime density理论说的prime number的密度是1/lnN，也就[0,N]之间prime
number个数大概是N/lnN，或者说[0,N]随机选一个数这数是prime的机率为1/lnN，但是
这个density是随着N下降的，N很大时候任何下限都会被突破。
谁来解释下。 |
|
a******g
发帖数: 318 | 15 【 以下文字转载自 ebiz 讨论区 】
发信人: asihuang (asihuang), 信区: ebiz
标 题: 10个包子弱弱问 这个概率密度函数(Probability density function)怎么求
发信站: BBS 未名空间站 (Mon Aug 4 18:18:55 2014, 美东)
实在不好意思问老板，来这里高手如云的地方问问？
假设有一个连续函数h：
h(x,y)=x^2+y^2+2x,
其中x=[0 1],y=[0,1].
(其实h是surface height，当然，它是什么不重要）
请问一下h的概率密度函数（Probability density function）怎么求？
我想知道理论解(closed-form expression)怎么求，不要让我用matlab离散方法做。
10包子准备奉上给第一个解答的，谢谢。 |
|
c********u
发帖数: 1608 | 16 【 以下文字转载自 Mathematics 讨论区 】
发信人: chasingyou (RUinlove), 信区: Mathematics
标 题: 数学的同学们，有啥好的软件做一个 charge density 的图
发信站: BBS 未名空间站 (Tue Jul 26 22:21:03 2011, 美东)
想做一个 charge density(x,y,z)的 图，就是通过颜色表示密度大小的图。
推荐个简单易用的吧，以前从来没做过。还有有没有入门级的matlab教程啊。谢谢。 |
|
y**c
发帖数: 133 | 17 we need high density, no-metallic liquid, at room temperature.
No metal like Hg. No glass, which is called liquid "scientifically".
The higher the density, the better. And the lower conductivity, the better.
Is there anyone know this kind of things? Thanks in advance! |
|
y*****t
发帖数: 186 | 18 如果版面不对，请帮忙转发一下。谢谢。
有10个大球，20个小球。所有的球都是理想状态球形，同样材料。小球是大球重量的一
半。（所以两种情况下，重量都是一样的。）
现在有一个容器，如果10个大球能够装下，20个小球是否也能装下？这两种情况的
packing density是否一样？我这里的packing density是重量/（球体积+球之间的空位
体积）。 |
|
l*****e
发帖数: 276 | 19 当球数量很大的时候会接近~60%，如果球非光滑一般会小一些，如果光滑就是64%了。
10个20个球的时候的packing density是比较难讲的，因为你可以摆出不同的结构而且
受容器形状影响。
如果你要问的是100000个和200000个随机的用同样的方法放进去，那packing density
应该是没区别。 |
|
b*******g
发帖数: 513 | 20 问题是找一个有两个mode的distribution的highest density region. 有个人写了个文
章和一个R package,链接是：http://robjhyndman.com/papers/hdrgraph.htm。要用的package is "hdrcde", subroutine is hdr.den for one dimension data. 用他的example data which is faithful$eruption，有结果.用自己的data, 总有一个error:Error in bw.SJ(x) : no solution in the specified range of bandwidths。在subroutine hdr.den 设定了bandwidth, "h=0.09", 得到一个还行的结果。而且用不同的bandwidth,得到的highest density region 不同。主要是自己对于一个mode的distribution,写了一个程序，有了一个不错的结果。用自己有一个mode的数据，用hdr.den 分析有同样err |
|
b**********e
发帖数: 795 | 21 R 新手，现在有一组数据x(60d），想用kernel density得到distribution。然后再有
新的数据来， predict新数据的probability。
想用class density，该怎么实现？
多谢了！ |
|
w*********a
发帖数: 156 | 22 搜了一下现有的R packages，好像都是已经预先定义好的proposal density，而且多是
normal proposal，但是我想用uniform proposal density，因为我的随机变量的取值
范围
是在一个有限区间内的。
多谢帮忙啊~ |
|
p*****4
发帖数: 366 | 23 density(x,bw=3,kernel="g")
怎么算出某一个点的kernel density呢？ say f(3) or f(5)
多谢 ！ |
|
b********r
发帖数: 37 | 24 以前在学校做的是kernel density estimation, 现在找工作的时候，好像很多面试官
不懂。我以前总是用kernel density estimation for point feature 为例子来说，但
是即使这样，也有人听不懂，该怎么描述？
谢谢！ |
|
w*******y
发帖数: 60932 | 25 Macy's is having a buy one get one free on their pillows.
Calvin Klein Bedding, Signature Down Alternative Density Pillows are reg. $
30 each. they are on sale for 50% off plus you if you buy one you get one
free. They have good reviews.
$14.99 for two pillows
$5.95 for shipping
$1.80 for tax
$22.79 total
Calvin Klein Down Alternative Density Pillows:
http://www1.macys.com/catalog/product/index.ognc?ID=374907&CategoryID=43293
|
|
w*******y
发帖数: 60932 | 26 Meritline has
3 Ports High Speed HDMI Super Mini Switch for Xbox 360 HDTV Cable STB PS3,
Intelligent Auto Switch, No AC Power Needed And 6 Feet High Speed HDMI Cable
Male to Male Digital A/V Cable - 3 Pack:
http://www.meritline.com/3-ports-high-speed-hdmi-super-mini---p
SKU:195-169-001 for $9.99 + FS after using w/Code: MLCK5EIY8PNL1 For First
700 Orders (This code also apply to some other items in this email. Get
more saving with just 1 code input
2 Sets (10 Pcs) of Canon CLI-8 (CLI8, CLI-8Bk... 阅读全帖 |
|
|
|
|
M*******a
发帖数: 1633 | 30 我说老张和prime density理论相矛盾，没有说什么孪生素数对 |
|
h*******i
发帖数: 4386 | 31 what is density functional ? |
|
a******g
发帖数: 318 | 32 实在不好意思问老板，来这里高手如云的地方问问？
假设有一个连续函数h：
h(x,y)=x^2+y^2+2x,
其中x=[0 1],y=[0,1].
(其实h是surface height，当然，它是什么不重要）
请问一下h的概率密度函数（Probability density function）怎么求？
我想知道理论解(closed-form expression)怎么求，不要让我用matlab离散方法做。
10包子准备奉上给第一个解答的，谢谢。 |
|
b*****e
发帖数: 1032 | 33 请问版友，房子地毯默认的padding是5 lb的，升级到6 lb要900， 升级到 8 lb 的
padding density要1500. 对这个没概念，这个升级有必要吗？我看到网上一些文章建
议买8 lb的，说是很firm 而且舒服，冬天踩上去也不冷，以前从没留意过地毯，不知
道各位有什么建议吗？网上有的文章提到升级完padding后，还要相应升级地毯的厚度
到7/16 inch. 有的也提到warranty 的事，有点不太明白，请指教！ |
|
|
k******a
发帖数: 678 | 35 室内摄影，用大光圈追求小景深，但是会曝光过度。有没有人在类似的情况下使用
Neutral density filter来解决曝光过度的问题。请问效果如何？ |
|
g******i
发帖数: 251 | 36 HW problem, ha.
A intrinsic semiconductor is terminated with H. We need to estimate the change
of electron affinity because of the chemisorption of H, and the way we use is
to mode the surface in terms of the parellel plate capacitor. But we need make
an approximation of surface charge density. What's the order of it? |
|
w*s
发帖数: 7227 | 37 买回来不能用，然后ebay跟我说我的机器只能用low density的。
请问现在这ram在什么电脑上可以用？ |
|
c******n
发帖数: 16666 | 38 上次记得有内存不兼容还是上世纪的事情
最近帮老电脑升级
随便查了下频率就买了几对
结果回来直接蓝屏 找到以前的类似型号试了下没问题
觉得是条子有问题就rma了
结果今天换的到了 装上去又蓝屏了额。。
尼玛一查 居然还有low density之说。。
可是网上买啥都看不到 难道来回rma abuse这个系统吗 |
|
t******x
发帖数: 89 | 39 你们都用什么软件来定量统计Western Blot Band Density？ 可以的话，麻烦分享一下
，或者告诉我在哪里可以下载？
先谢谢了！ |
|
|
y***k
发帖数: 57 | 41 perfluorinated liquid such as Krytox from Dupont, HT series from Solvay.
Density around 1.8 and totally no conductive, low volatile and low toxic. |
|
S******n
发帖数: 17 | 42 Hi,
有没有人知道哪里可以弄到厚度尺寸是2.25",2.5" or 3"*5'*10' 的medium density
fiberboard,用来造弥拟模型.我查了中国好象有很多制造商,或者美国其他城市有什么
大的MDF ditribution company介绍一下.哪位牛人能帮帮忙.万分感谢!!
thanks |
|
|
b*****k
发帖数: 80 | 44 yes,it's a block code
the parity check matrix is very sparse,or said differently, low density.
Gallegar discovered this in 60s and people rediscover this code
in late 90s which shows performance(w/ 10^7 block length)
very close to shannan capacity.
This code and another popular codes--turbo codes use similiar
iterative decoding stragety. A new tool--factor graph
(or normal graph in Forney's vocabulary)
is also formulated to anaylize the behavior of those codes.
LDPC code has lower decoding compl |
|
h******v
发帖数: 30 | 45 Assume the power transmitted is p(W), the distance between the transmitter a
nd the receiver is r(m), then the power flux density at the location of the
receiver is
S=p/[4*3.14*r^2] (W/m^2).
Assume the effective length of the antenna of the receiver
is l(m). My question is how to caculate the voltage v(V)generated in the ant
enna? Is the following equation correct?
(v/l)^2/367=S=p/[4*3.14*r^2]
My second question is about noise limited sensitivity (abbreviated NLS bello
w).In th |
|
|
y****y
发帖数: 179 | 47 如果有一个随机信号f(t),该怎么求他的Power spectral density S(f)呢？
是直接fft(f(t))吗？ |
|
|
c****e
发帖数: 252 | 49 Hi, does anyone know the density of PBT at different temperatures? or how can
I get these data?
Thanks |
|
b**s
发帖数: 589 | 50 Chemical Name Density (g/cc)
Acrylonitrile/butadiene copolymer-21% acrylonitrile 0.97
Acrylonitrile/butadiene copolymer-22% acrylonitrile 0.97
Acrylonitrile/butadiene copolymer-27% acrylonitrile 0.99
Acrylonitrile/butadiene copolymer-29% acrylonitrile 0.97
Acrylonitrile/butadiene copolymer-31% acrylonitrile 0.99
Acrylonitrile/butadiene copolymer-33% acrylonitrile 0.98
Acrylonitrile/butadiene copolymer-38% acrylonitrile 0.99
Acrylonitrile/butadiene copolymer-41% acrylonitrile 1.00
Acrylonitrile/b |
|
