f***a
发帖数: 329 | 1 我胡乱提下问，希望能跟大家讨论讨论哈 :D
=======================================
Suppose
y_i = response data， i = 1,2,...,n
X_i = covariate data
b_i = coefficient
然后开始set up model， 大概可以写成
y_i \sim p( |g(X_i*b_i)) （或者再复杂点，加些random effects之类的）
p() is some distribution
g() is some function
或者p()也是some kind of function (in data mining perspective)
再或者是hierarchical model
y_i \sim p( |??), ?? \sim f( |!!), !! \sim q( |@@), ...
covariates看具体model，随便插在??/!!/@@ 的位置
那么一般做residual analysis的话，首先基本是estimate parameters
然后deriv... 阅读全帖 |
|
m*****u
发帖数: 19562 | 2 PVC damage is caused by storing coins in soft plastic flips that contain polyvinyl chloride (PVC.) PVC most commonly manifests as a light-to-dark greenish residue, although it can appear as milky or light grey in color. It has a distinctive "plastic" odor which can range from subtle to strong. I recommend treating coins for PVC residue whenever you can smell PVC on them, even if you don't see the greenish residue yet, because if the coin has a plastic stink, the PVC breakdown process has begun. ... 阅读全帖 |
|
k*****a
发帖数: 1518 | 3 在表面处理后如shot penning后，材料表面会有residual stress存在。
利用试验办法可以比较准确的确定这residual stress的值。
如果用数值模拟，如何加上这个residual stress? 想想可以用加temperature
gradient的办法加上，不过如何match试验结果还是个问题，需要很多次的
test and try.
另外residual stress redistribution 也是个大问题，看着简单，想了一段
时间，还没有想出的办法。 |
|
f***a
发帖数: 329 | 4 恩，linear model下我觉得就是看你model的时候怎么规定error term的distribution。
residual follows the same distribution if model is true。
glm的话，fit完model之后得到，E(y_i|X_i)=g^-1(X_i*bhat)，where g() is link
function。然后怎么弄呢？
计算 y_i-E(y_i) follow的distribution，然后residual follows the same
distribution if model is true？
repeated measure的时候，是不是非要在model里加random effect了？不然形成对于一个
object，有m个measurements of response variable and 1 estimate value of
response mean。这样的话，如果每一个measurement都和E(y_i|X_i)做一次计算得出
residual，那么对于每一个object就能得出m个re... 阅读全帖 |
|
a***r
发帖数: 420 | 5 做助教，本来只是想做个教学demo，show一下confounding 和 partial correlation的
概念，结果纠结了。。。
我simulate了三个variable: outcome, var1, var2。其中outcome是binary; var1 有
三个category 1/2/3; var2 continuous。三者之间都有correlation，我的目的是show
var2对var1和outcome之间association的confounding
R code如下：
> table(outcome)
outcome
0 1
52 48
> table(var1)
var1
0 1 2
19 44 37
> summary(var2)
Min. 1st Qu. Median Mean 3rd Qu. Max.
0.002583 0.053960 0.105000 0.122800 0.184200 0.392700
> cor(outcome,var1)
[1] 0.2854862
> cor(outcome,var... 阅读全帖 |
|
b******2
发帖数: 13 | 6 A between-Subject psychology experiment: distant tie vs. close tie. The
close tie condition is further broken down into "brother" and "son." My
ultimate goal is to test tie---M---DV mediation. So seems I should pool "
brother" and "son" into one "close tie" condition, but pooling test(i.e.,
chow test) is significant meaning that they can not be pooled together using
raw data values. This is because "brother" and "son" differ significantly
regarding the DV. So, seems using residuals as the new DV... 阅读全帖 |
|
E*E
发帖数: 52 | 7 【 以下文字转载自 Statistics 讨论区 】
发信人: EFE (EFE), 信区: Statistics
标 题: help!! about residual scale
发信站: BBS 未名空间站 (Wed Sep 17 20:01:26 2008)
when I use Splus "lmRobMM" method to do regression, it can return a output-
"scale" as for example "Residual scale estimate: 4.513 on 101 degrees of
freedom"
Can any one please tell me the definition and formula of this "Residual
scale"?
I saw something like "sqrt(deviance/df)"
what is the formula for "deviance"?
Thanks a lot! |
|
m********r
发帖数: 811 | 8 Jump to: navigation, search
This article does not cite any references or sources. Please help
improve this article by adding citations to reliable sources. Unsourced
material may be challenged and removed. (June 2009)
2-pole residual current device
A residual current device (RCD), similar to a residual current circuit
breaker (RCCB), is an electrical wiring device that disconnects a circuit
whenever it detects that the electric current is not balanced between the
energized conductor and |
|
BR
发帖数: 4151 | 9 土鳖的问题在于用法律规定外国国籍优先于本国国籍,中国国籍是个 residual。按国籍
法，绿卡子女有没有中国国籍取决于其出生时是否获得了所在国国籍，如果没有就还是
中国国籍。这就是用中国法律规定一个人是否有中国国籍，首先看外国法律怎么规定，
外国没有说这个人是他们国籍的，我们才认这个人的中国国籍，外国说这个人是他们国
籍的，我们就不敢认。中国就是个residual,外国人不要的，我们才要。这像是个所谓
泱泱大国、厉害国做的事吗？
都别说什么剩女剩男了。咱整个国家就是个剩国。
更别说单方绿卡子女不是中国国籍，这个绿卡人加入外国国籍后其子女反而是中国国籍
这种荒唐事了。 |
|
T*******x
发帖数: 8565 | 10 我不知道tan定理是什么。这题怎么都要用到residue theorem，或者等价形式，或者是
把residue定理展开。 |
|
T*******x
发帖数: 8565 | 11 residue定理就是讲解析函数沿着一个环路积分的方法。解析函数环路积分等于零，除
非是环绕singularity，而且是一阶singularity。解析函数在singularity附近的
laurent展开的负一阶项就是它的一阶singularity，这个系数就是它的residue，把它
求出来环路积分就有了。 |
|
S********5
发帖数: 753 | 12 Residual 都是按照MSRP算的。所以lease经常会有好deal。BMW当年就有过Z4 70%多的
residual, 考虑到真实sale price, lease就相当值。
★ 发自iPhone App: ChineseWeb 8.6 |
|
s*****o
发帖数: 459 | 13 actually many luxury cars can't be sold at/above residual after lease, say 6
.5w MSRP after 3 yr, residual about 4w, no one would pay 4w for a 3yr old
car, 3.5w maybe
So, someone will probably eat the cost, but they have made lots of money
from lease anyway, who offsets this loss is a mystery overall. Majority of
luxury cars are sold by lease. So, the car maker have to figure out a
formula for all parties involved: buyer, dealer, leaser, and itself
able |
|
m********2
发帖数: 3732 | 14 我艹，老蔫jb萎缩男的逻辑真不是人能理解的。 人家上来问个residual方便算lease
payment都能扯到八杆子打不着的地方，服了。
新XC90现在的residual大约在58%～61%之间，取决于年份和里程。 |
|
m********2
发帖数: 3732 | 15 58%的residual算很低的了，bmw经常有66%的residual，而且考虑到XC90基本上sale
price=msrp，lease不是很划算。 |
|
w*********h
发帖数: 664 | 16 上个月月底看到很多车型，折旧率只有34%，就是residual percentage可以到66%。这
个月看，同一款车型同一配置，residual percentage降到62%了。不知道这个
percentage是不是每个月都是固定的，还是会浮动，比方说月初的时候低，越靠近月尾
或者年末这个比例会上升？ |
|
l**********1
发帖数: 5204 | 17 Here you go
Deramaudt TB et al. (2011)
FAK phosphorylation at Tyr-925 regulates cross-talk between focal adhesion
turnover and cell protrusion.
Mol Biol Cell. 22: 964-75.
Abstract
Cell migration is a highly complex process that requires the coordinated
formation of membrane protrusion and focal adhesions (FAs). Focal adhesion
kinase (FAK), a major signaling component of FAs, is involved in the
disassembly process of FAs through phosphorylation and dephosphorylation of
its tyrosine residues, but ... 阅读全帖 |
|
c******x
发帖数: 438 | 18 I cannot input chinese now, I saw the thread below discussing how to remove
the residual solvent.
http://www.mitbbs.com/article_t1/Chemistry/31280475_0_2.html
I have a silmiar problem, and the solvent is encapuslated inside polymer.
Here is what I did:
A polymer (Tg ~ 270C) with 1% N-methyl pyrrolidone (NMP) solvent residue.
This polymer can dissolve in THF, but not in water, methanol and acetone. We
tried purification of this polymer by dissolving it in THF, then
precipitated the solution in an |
|
J*******3
发帖数: 1651 | 19 【 以下文字转载自 Physics 讨论区 】
发信人: Jerry0803 (Jerry and Tom), 信区: Physics
标 题: 谁有Rigaku 的Residual stress measurement插件？
发信站: BBS 未名空间站 (Tue May 5 10:41:14 2015, 美东)
谁有Rigaku Ultima的Residual stress measurement插件？
谢谢 |
|
J*******3
发帖数: 1651 | 20 【 以下文字转载自 Physics 讨论区 】
发信人: Jerry0803 (Jerry and Tom), 信区: Physics
标 题: 谁有Rigaku 的Residual stress measurement插件？
发信站: BBS 未名空间站 (Tue May 5 10:41:14 2015, 美东)
谁有Rigaku Ultima的Residual stress measurement插件？
谢谢 |
|
J*******3
发帖数: 1651 | 21 【 以下文字转载自 Physics 讨论区 】
发信人: Jerry0803 (Jerry and Tom), 信区: Physics
标 题: 谁有Rigaku 的Residual stress measurement插件？
发信站: BBS 未名空间站 (Tue May 5 10:41:14 2015, 美东)
谁有Rigaku Ultima的Residual stress measurement插件？
谢谢 |
|
E*E
发帖数: 52 | 22 when I use Splus "lmRobMM" method to do regression, it can return a output-
"scale" as for example "Residual scale estimate: 4.513 on 101 degrees of
freedom"
Can any one please tell me the definition and formula of this "Residual
scale"?
I saw something like "sqrt(deviance/df)"
what is the formula for "deviance"?
Thanks a lot! |
|
B****n
发帖数: 11290 | 23 R裡面對於Regression是有residuals這個命令的 你在r裡用help查查residual |
|
L*****2
发帖数: 66 | 24 Does standardized deviance residual asymtotically follows normal
distribution with mean zero?
Is the mean of deviance residuals equal to zero?
Thanks! |
|
f***a
发帖数: 329 | 25 One possibility: irrelevant predictors could cause such problem.
naive example:
y = random error + irrelevant terms + relevant terms
=> residual = y - y_hat = random error + irrelevant terms
if your fitted irrelevant terms are linear, then linear residuals will be
produced for observations whose irrelevant attributes contribute (non-zero). |
|
b*****e
发帖数: 5 | 26 Simple linear regression EYi=alpha+beta*xi
如果a和b是alpha与beta的MLE, N为sample size
Sum of square residual是sum(Yi-a-b*xi)^2, 如何证明它等于
sum(Yi-alpha-beta*xi)^2-N*(Y.bar-alpha-beta*x.bar)^2-(b-beta)^2*sum(xi-x.bar
)^2，相当于SS residual除以sigma^2能拆成三个chi-sq
我想的是先拆成ANOVA的形式：Sum(Yi-Yi.hat)^2=sum(Yi-Y.bar)^2-sum(Y.bar-Yi.hat
)^2, 第二项与要证的最后一项类似，但是相差一个beta. 第一项sum(Yi-Y.bar)^2可拆
成sum(Yi-mu.i+mu.i-Y.bar)^2. 可是因为Yi不是iid,不能像普通的sample variance那
样化简为sum(Yi-mu)^2-N*(mu-Y.bar)^2,我就不知道往下如何进行了， 哪位能指点一
下吗？谢谢！ |
|
发帖数: 1 | 27 题目是integrate{1/(x^4+1),x,0,infinity}
我的方法是residue theorem
f(z)=1/(x^4+1)
Resf(z)=-z/4
Resf(z0)+Resf(z1)=-(e^(i Pi/4)+e^(-i Pi/4))/4=-i/2 Sin(Pi/4)
integrate{1/(x^4+1),x,0,infinity}=1/2 integrate{1/(x^4+1),x,-infinity,
infinity}=1/2 2 Pi i (Resf(z0)+Resf(z1))=2^(1/2)*Pi/4 |
|
发帖数: 1 | 28 TheMatrix叔叔tan定理是什么？这题目不用residue theorem怎么写？ |
|
发帖数: 1 | 29 叔叔能详细讲解一下residue theorem吗？
白老头教我的时候我没学好，当时太小了LOL |
|
o*******y
发帖数: 1076 | 30 怎样能查到一辆车lease3年的residual value?
谢谢！ |
|
f****e
发帖数: 590 | 31 you are right, i didn't realize residual is calculated this way, so this
option to buy cost more than I expected.. however on the other hand it makes
your lease a better deal. I got 10% off MSRP of a ML350 with RV 63% over 30
months, so the real RV becomes 70%. Consider I can choose to return 4-8
months earlier if lease another MB, RV is even higher.
needed
doesn |
|
B*Z
发帖数: 7062 | 32 如果害怕车不可靠，先lease几年，一切满意的话，lease结束买下来。这种情况下，买
价是否必须等于计算lease时的residual value？请大侠指导。另外lease车的时候，除
了车的价格，年里程，以外还有什么可以negotiate的？ |
|
|
n***s
发帖数: 163 | 34 The magic word is CPO.
Remember price wise, CPO > private party > trade-in, by a large margin. The
car company just needs to set the residual value somewhere between CPO and
trade-in to lure enough people into leasing. Then it can make money again on
the returned cars through the CPO stamping.
6 |
|
f*******7
发帖数: 1019 | 35 dealer说MF=0.00141,
36 months residual:
10k/year: 63%
12k/year: 62%
这些数字靠谱么？
还有就是说Acura不能用MSD来降MF. |
|
a******t
发帖数: 3 | 36 MF不记得了。我的不是通过acura，反正记得6%以上。
但是
residual 73% @ 7500/yr
看起来像made up number
没MSD。 |
|
B*Z
发帖数: 7062 | 37 residual 73%, after how many years? |
|
T****e
发帖数: 222 | 38 我在NJ, 昨天去Costco旗下的一个dealer,看看CRV的价格，遇到好几个新鲜事：
1. 给的价格确实比Truecar上面还要便宜1000，这个合理么？还是大家其实卖的都不贵
，因为存货太多了？
2. 我说想租，一年12k miles, 人家就给了个money factor: .00165.我根据咱们版上
的知识，直接就说要是我付7次payments,不是就能降下来？人家说怎么可能？全都是一
样的。
3. 然后我又问，那residual呢？他们说63%,我说能商量么？他们说怎么可能，全都是
一样的。
我这个晕啊，大家有经验的，指点一二则个？第一次谈租车，就跟版上学的不一样，咋
回事啊？
当时我说能不能trade in,人家说当然了,网上3980刀，我说太便宜，不成，他们问那你
要多少，我说最少5000(实际上private party是5400），经理说，行！让我看看你的车
，我争取给你5000块，咱们今天能把车卖了么？
我直接傻了，关键是以上的3个问题困扰，实在不想落入陷阱，就撤了。 |
|
T****e
发帖数: 222 | 39 没人帮着回答这个问题么？租honda的MF 和 residual变不变呢？ |
|
h*******k
发帖数: 4412 | 40 residual不会变吧，mf好像没听说Honda能靠押金降低 |
|
T****e
发帖数: 222 | 41 那不就是说，哪里租车的价格都是一样的么?既然money factor 定了，residual也定了
，还有什么商量余地啊？
真心的不明白啊！ |
|
v****n
发帖数: 100 | 42
也是第一次租车，也正在做功课，我的看法儿是，现在你在跟滴乐讨论的是他可以给你
的adjusted sell price,这个价格拿到的越低，其他的都是固定的，月费也就下来了
举个大栗子：
monthly payment = (Sell price - MSRPx63%)/36 + (Sell price + MSRP)*0.00165
所以如果residual和MF定了，那就剩下Sell price可以跟滴乐讨论了
0.00165是全国统一数么？ 为啥我们这的MF上次问貌似是0.00125 |
|
g********y
发帖数: 461 | 43 从来没有lease过车，最近两天才学会一点。听说新出的车最好lease，就去dealer咨询
一下。
2017年的新 audi q7 premium,很爽快6% off msrp， 65%的 residue value，0.00159
的money factor，算下来连ttl一起是$681一个月。
问了monthly security deposit，说因为不是通过audi的Finance，所以不能用，是这
样吗？
这个对于全新的来说是不是已经很好的deal了。
谢谢大家指点。 |
|
M*****n
发帖数: 282 | 44 今天下班把车换了，MSRP 减了3000，2.79% APR
[在 gummybeary (gummybeary) 的大作中提到：]
：从来没有lease过车，最近两天才学会一点。听说新出的车最好lease，就去dealer咨
询一下。
：2017年的新 audi q7 premium,很爽快6% off msrp， 65%的 residue value，0.
00159
：........... |
|
M*****n
发帖数: 282 | 45 俩车真是好兄弟，斯洛伐克同一个厂组装，弄不好连工人都是相同的几个人
[在 gummybeary (gummybeary) 的大作中提到：]
：从来没有lease过车，最近两天才学会一点。听说新出的车最好lease，就去dealer咨
询一下。
：2017年的新 audi q7 premium,很爽快6% off msrp， 65%的 residue value，0.
00159
：........... |
|
p****2
发帖数: 518 | 46 想统计整理下iihs TSP SUV的lease价格 -- 包括residual value(24月和36月),
rebates, monthly factor
2016 Chevrolet Equinox
2016 GMC Terrain
2016 Honda Pilot
2017 Hyundai Santa Fe
2017 Hyundai Santa Fe Sport
2017 Kia Sorento 4-door SUV
2016 Kia Sorento 4-door SUV
2016 Nissan Murano
2016 Toyota Highlander
2016 Subaru Forester
Assume :
10,000 miles per year
$0 down payment
only first month's payment, document fee, and government fees due at signing
sales tax not included
acquisition fee rolled into lease
top tier cre... 阅读全帖 |
|
q****h
发帖数: 77 | 47 三年和两年的标准residual value一般都是多少？不同的mileage limit呢？ |
|
发帖数: 1 | 48 请教 现在2016 bmw 528 xi 能拿到多少折扣 lease residual 多少？ |
|
c*****e
发帖数: 1538 | 49 打算lease touring L plus
问了一圈，发现lease 3年的residual vue 都在55%左右
比bmw 的65% 差远了呀。
你们lease都是多少钱搞定的？ |
|
f*****h
发帖数: 4489 | 50 现在哪款bmw还有65%?
：打算lease touring L plus
：问了一圈，发现lease 3年的residual vue 都在55%左右 |
|
