g*****p
发帖数: 3403 | 1 哪位牛人做过starndfood 的Ozone 的non-parametric estimate, 下面是description
。 给个r code 或者整个paper 就更好了 呵呵
Use three different non-parametric regression methods to predict ozone
concentration. Additive models, regression trees and projection pursuit or
linear regression could be any of the three starting methods in your
analysis. Summarize your findings and present them, along with supporting
evidence, in your report which should be organized as stated above. Be sure
to evaluate the validity of your final mo... 阅读全帖 |
|
q**j
发帖数: 10612 | 2 打算得到比较smooth (stable)的mean and covariance estimates。现在mean用了baye
sian model，已经相对比较smooth了。但是Bayesian的covariance也不smooth，而且牵
涉到wishart distribution，在mle的时候非常volatile。请问这方面的大侠有什么指教
么？
当然还是要efficient的estimator。多谢了。 |
|
q**j
发帖数: 10612 | 3 sorry. There are T years and N observation with K independent variables in e
ach year. I can get a set of K estimates each period. My problem now is the
get a smooth estimate for the covariance of the K parameters, ie. a K by K m
atrix.
Sample covariance is not stable. Most Bayesian model innovate on the mean, w
ith less attention on covariance. When they actually focus on covariance, th
ey use Wishart distribution, which is very hard to optimize due to the gamma
function, when I try to find the... 阅读全帖 |
|
y*****y
发帖数: 98 | 4 the K variables are independent, why do you need a covariance matrix?
anyway. the covariance estimation could be very hard due to large K and
small N. the Bayesian approach is to put a prior structure (conjugate
Wishart or objective prior etc.). but i don't think that the Wishart prior
is difficult if there is no constraint. everything is conjugate. estimation
should be pretty straightforward.
by the way, you have time associated. the model should be temporal. |
|
f***c
发帖数: 301 | 5 最简单的比如 Yi= a + bXi + ei
这样一个线性模型 如果假设 Xi 也是一个random variable,服从正态分布不知道mean
和variance, 怎么estimate a,b还有X的mean,variance，用ML可以么
找了找相关的文献 似乎有人把这个算作measurement error model可是又没有讲怎么
estimate,希望有人可以指点一下 谢谢 |
|
o******e
发帖数: 1001 | 6 用Maximum Likelihood estimation预测样本数据的时候（都是正态分布），如果有两
组不同的数据，怎么才能知道那组fit的比较好呢？Maximum Likelihood estimation有
没有比较常用的goodness of fitting的方法？是用deviance吗？谢谢！ |
|
r*****y
发帖数: 199 | 7 What is defined as "better"? To me, a simular idea would be, do you prefer a
unbiased estimator or a minimal variance estimator? |
|
l*********s
发帖数: 5409 | 8 1. expectation and variance estimates are unbiased and asymptotically
efficient, as promised by the weak law of large number, unless the
underlying distributions are of certain special cases, such as cauchy.
2. that being said, mles are derived from the density functions and the result is only valid for a correctly specified distribution family; otherwise, it is going to be garbage no matter how
accurate parameter estimates are. |
|
l*********g
发帖数: 177 | 9 向各位请教一下：
本人在sas中进行gmm estimation，用的是proc model的功能。但是现在有个麻烦的问
题就是， 根据我需要estimate的model，在我写gmm 的每个moment condition
equations 的时候会需要用到matrix的计算（比如inverse， multiplication等）。然
而似乎在proc model中写那些moment condition equations 只能写成用1维的量表达的
式子，这就造成我的问题：如果把比如matrix inverse之类的计算用1维的式子表示会
变得极为繁琐和庞大。
我知道sas中有个iml进行矩阵运算的，但是那个iml并没有和proc model联系在一起。
请问有没有人知道根据我的情况，能怎样在proc model中实现gmm还能用矩阵来方便描
述我的moment condition equations 啊？
谢谢帮助！ |
|
h**********1
发帖数: 155 | 10 what do you mean can't get true value? based on one simu? or 1000? usually
you run 1000 simu and check whether your estimators are unbiased. check
whether each run is converged. use function hist to see the distribution of
your estimators, they should approximately follow normal distribution if you
've large sample (n=1000).
also if you likelihood is very flat, it's hard to converge and sensitive to
the initial value.
try to supply a gradient function which could help a lot.
try different optimi... 阅读全帖 |
|
|
y*c
发帖数: 247 | 12 如果在mixed model 里adjusting for baseline factors的话，estimate treatment
group means can be done. But what if I have a time-varying covariate
adjusted in the model? What should I do (in proc mixed) to estimate the
treatment group mean? 非常感谢。 |
|
b********r
发帖数: 37 | 13 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！ |
|
|
|
l*****y
发帖数: 5 | 16 Hi, all,
I am sorry for not being able to come here for a long time.
Here I have a topic that seems to me interesting, for you guys' discussion:
Motion Estimation Techniques for Video Coding
Here is a brief story about how I got to this topic: I'm working on totally
different topic, yet I happened to have to work out some algorithms for
estimating motion flows in a time sequence of images. That is how I had a
"video" animation in my work. Otherwise, most of time I am working on static
images. |
|
s***i
发帖数: 10182 | 17 Qin Dynasty 秦朝 221–206 BC
GDP per capita: Unknow
The share of Qing and the dynasties before are too aged to calculate, no
relevant data is available, so we only start from the Han dynasty.
Han dynasty 汉朝 (206 BC–220 AD)
GDP per capita: $450
Han Dynasty accounted for 26% of the global wealth, at that time the Roman
Empire dominated western world. Han Dynasty is the economic center of the
eastern world.
Tang Dynasty 唐朝 618 – 907 AD
GDP per capita:$480
China’s feudal society gets to its peak in T... 阅读全帖 |
|
s***i
发帖数: 10182 | 18 Qin Dynasty 秦朝 221–206 BC
GDP per capita: Unknow
The share of Qing and the dynasties before are too aged to calculate, no
relevant data is available, so we only start from the Han dynasty.
Han dynasty 汉朝 (206 BC–220 AD)
GDP per capita: $450
Han Dynasty accounted for 26% of the global wealth, at that time the Roman
Empire dominated western world. Han Dynasty is the economic center of the
eastern world.
Tang Dynasty 唐朝 618 – 907 AD
GDP per capita:$480
China’s feudal society gets to its peak in T... 阅读全帖 |
|
z*****1
发帖数: 130 | 19 An estimated 6.6-magnitude earthquake has struck Nagano and Niigata
prefectures in Japan, Kyodo news service reports. |
|
z*******h
发帖数: 346 | 20 把佛山小女孩事件作为一个random sample from binomial distribution B(19, p),
where drawing a 道德败坏 person means success, and drawing a 好人 means
failure. Since 18 out of 19 people are 道德败坏, maximum likelihood
estimation of p is then 18/19, which is far greater than 1/10000 as claimed
by some 50c ID here. |
|
i***a
发帖数: 4718 | 21 http://www.bbc.com/news/business-29105542
Japan's economy contracted by 7.1% in the three months to June, more than
initial estimates, and revised from 6.8% reported in August.
Most forecasts were for the economy to shrink by about 7%.
The contraction during the second quarter has been widely attributed to a
hike in the nation's sales tax, which rose from 5% to 8% in April.
The official gross domestic product (GDP) figure of 7.1% is an annualised
number.
In quarterly terms, Japan's economy, whic... 阅读全帖 |
|
|
H*********S
发帖数: 22772 | 23 一些懂英文的聪明人一看estimate，喔，明白了，就是CDC主任一拍脑袋随便写个数字 |
|
b*********3
发帖数: 1709 | 24 estimate = observed - true parameter |
|
e****e
发帖数: 418 | 25 TOKYO, March 16, Kyodo
An estimated 70 percent of the nuclear fuel rods have been damaged at the
troubled No. 1 reactor of the Fukushima No.1 nuclear power plant and 33
percent at the No. 2 reactor, Tokyo Electric Power Co. said Wednesday.
The reactors' cores are believed to have partially melted with their cooling
functions lost after Friday's magnitude 9.0 earthquake rocked Fukushima
Prefecture and other areas in northeastern and eastern Japan.
专家点评一下situation. |
|
n******7
发帖数: 5678 | 26 the Environmental Protection Agency on Monday announced new testing
procedures that will better reflect the way people actually drive, cutting
fuel economy estimates on new-car stickers by an average of 8 to 12 percent
beginning next year.
也就是说现在 sticker上说EPA 30 mpg 的车到明年sticker可能变成27-28mpg. |
|
h********F
发帖数: 484 | 27 为什么estimate里面的人工算得那么低？只有$45一小时，可是大多body shop都差不多
是90到100/小时（以前去换油的时候看到的）。 |
|
i****a
发帖数: 36252 | 28 get your own estimate from body shops then |
|
s******s
发帖数: 13035 | 29 09 crv, 左后车门被其他的车在parking lot开门擦伤，上下两个spot,
上面重的spot明显dent进去。对方保险给了一张支票大概$500不到点。
大家说是差不多我直接deposit了，还是找车铺再做estimate？ |
|
r*******e
发帖数: 7583 | 30 你都没estimate，对方根据什么给的check？ |
|
|
z********r
发帖数: 313 | 32 need to replace the hood, front bumper, 2 front H lamp lights, and paint the
hood.
The total cost (part+labor+ tax) estimation is around $2500
is this reasonable?
thanks!
my car is 2001 Mazda 626, total value is about $4000. Is this worth to do the repairment?
details:
bumper parts: $220;
Grille $125
H Lamp*2: $95 *2
hood: $435
paint: $380
total labor: $1000
including:
bumper: 4.4 hours
lamp: 0.7 hours
hood:4.3 hours
Fender: 1.6 hours
clear coat: 2.2 hours (by the way, what is clear coat? )
Radi... 阅读全帖 |
|
z********r
发帖数: 313 | 33 is this estimation reasonable? I mean, do you think they over chage the
price?
if not, I may ask them to only 修到能开
thanks! |
|
M***s
发帖数: 8769 | 34 bodyshop的人一般都是老手，奸诈的很
保险公司会先给你做个estimate，然后给你2份估价，去bodyshop的时候千万别把估价
单给dealer，如果给了他们肯定不给你检查，因为他们想把你留住，他们修的时候发现
还有额外的损失的话会直接给保险公司要钱
你可以做的是：
告诉他们保险公司还没来股价，你只是想先让他们看看大概多少钱，免得被保险公司骗
。你一定要告诉他们希望在他们这修。
这种股价一般是免费的 |
|
t*********r
发帖数: 2558 | 35 所以都below EPA estimated了 |
|
n*******t
发帖数: 1296 | 36 truecar上给的estimated TrueCar Price是OTD还是不包括TTL的价格？ |
|
m**********y
发帖数: 670 | 37 无辜被一个78岁的老大娘撞了正脸！报了她的保险，保险公司说要先调查事故责任，让
我去做个estimate,这个估价可以跟他要求查哪些项目呢？除了保险杠，要不要查什么
动平衡之类的？
一点都不懂啊！请版上大侠指教一下！ |
|
m*********0
发帖数: 1139 | 38 直接问dealer能否给true care estimate 的价格，可以吗？ |
|
k********e
发帖数: 400 | 39 我想用一个不在 state farm network 的 body shop 来修车, 因为它说可以省掉 500
块的 deductible. State farm 说我需要先让 state farm 做 estimate. 请问 how
it works? 会不会很麻烦？
是不是最好还是直接用 state farm network 的 body shop? |
|
F*******4
发帖数: 2874 | 40 body shop给你省掉deductible是什么意思？如果estimate大于500，无论在哪修都有
500 deductible吧。
500
★ 发自iPhone App: ChineseWeb 13 |
|
发帖数: 1 | 41 当然是选1。把车拖到你自己挑的修车店，修车店会联系保险公司跟他们扯皮做
estimate的，都不用你操心。关键是把车放到你自己挑的，而不是保险公司指定的修车
店。 |
|
e******e
发帖数: 1098 | 42 二手交易风险自负！请自行验证是否合法和一手卡！:
我想卖的物品:
wii 期货 @$218 (shipping estimate 2/25)
单张面值:
可接受价格(必须明码标价！):
$218
物品新旧要求:
new
邮寄方式要求:
yl
买卖双方谁承担邮寄损失(Required if not code only):
default
付款方式说明:
boa, ing or non-cc paypal
其他补充说明:
广告的有效期:
till gone
物品来源(Required for All Cards!):
az
我的联系方式:
mit
Warranty期限:
能否证明是合法的一手卡?(Required for All Cards!): |
|
c*****9
发帖数: 1166 | 43 不会把
我这里显示Delivery Estimate: February 24, 2010 |
|
|
n*******y
发帖数: 3337 | 45 发信人: newjersey (NJ furniture dealer), 信区: EasyMoney
标 题: Re: Pay Taxes With a Credit Card
发信站: BBS 未名空间站 (Mon Apr 16 10:59:03 2012, 美东)
呵呵，大家可以尽量让IRS少扣税，自己用5%-10%off GC付每个季度的estimated tax。 |
|
d*******h
发帖数: 5065 | 46 什么GC这么厉害！
发信人: newjersey (NJ furniture dealer), 信区: EasyMoney
标 题: Re: Pay Taxes With a Credit Card
发信站: BBS 未名空间站 (Mon Apr 16 10:59:03 2012, 美东)
呵呵，大家可以尽量让IRS少扣税，自己用5%-10%off GC付每个季度的estimated tax。 |
|
n*******y
发帖数: 3337 | 47 http://www.mitbbs.com/clubarticle_t/EasyMoney/31378361.html
发信人: newjersey (NJ furniture dealer), 信区: EasyMoney
标 题: Re: Pay Taxes With a Credit Card
发信站: BBS 未名空间站 (Tue Apr 17 00:36:55 2012, 美东)
cool, I successfully paid estimated tax with visa gift card
hehe,用GIFT CARD交税是debit.
Visa® Gift Card
Available Gift Card Balance $0.00
2 transactions found, displaying all transactions.1
Transaction Date Transaction Pending Amount
04/17/2012 12:21 AM VALUE PAYMENT SYST
VALUE ... 阅读全帖 |
|
t*****y
发帖数: 8155 | 48 You do not have to pay estimated tax for the current year if you meet all
three of the following conditions.
You had no tax liability for the prior year
You were a U.S. citizen or resident for the whole year
Your prior tax year covered a 12 month period |
|
n*******y
发帖数: 3337 | 49 呵呵，大家可以DEPENDENT写多点，尽量让IRS少扣税，自己用GC付每个季度的
estimated tax多好。为什么要让IRS预先扣很多税？ |
|
c**0
发帖数: 9331 | 50 Revenue in the three months ended in March rose 34%, year over year, to $13.
2 billion, while net income fell 35%, yielding EPS of 28 cents.
Analysts on average were expecting $12.91 billion and 6 cents share.
For the current quarter, the company sees revenue of $11.9 billion to $13.3
billion, which is below the average $12.85 billion estimate |
|
