a**n
发帖数: 3801 | 1 normal和lognormal不可能是equivalent measure啊 |
|
h*********7
发帖数: 23 | 2 个人觉得这道题目的意思就是真是的underlying 是normal 但是在市场上我们quote
的时候我们按照B- S 来quote 问你 Digital 的价格怎么变化 |
|
k*****y
发帖数: 744 | 3 Q2.18 Suppose we price a digital call in both normal and lognormal models in
such a way that the price of call option with the same strike is invariant.
How will the prices differ?
the price of call option with the same strike is invariant是什么意思？
解答也没看懂，哪位来稍微解释一下？谢谢~ |
|
A*****s
发帖数: 13748 | 4 觉得很ft
不知道怎么用normal model来price
感觉是个杜撰出来的题目，直接忽略了
in
invariant. |
|
A*****s
发帖数: 13748 | 5 你说easy and fair是因为这个option是binary么？
那倒是。。。换一个别样的option就没这么简单了吧。。。
另外从来就没搞明白过所谓的normal model神马样子？
ds = u dt + vol dW?
面试的时候为神马要问这种根本不valid的model呢？ |
|
A*****s
发帖数: 13748 | 6 另外从来就没搞明白过所谓的normal model神马样子？
ds = u dt + vol dW?
面试的时候为神马要问这种根本不valid的model呢？ |
|
A*****s
发帖数: 13748 | 7 那怎么假设的？
比如知道今天的价格是S_0
那未来的价格变化S_T-S_0符合Normal(uT,vol^2*T)这样一个分布？ |
|
A*****s
发帖数: 13748 | 8 我就是问问normal model到底是怎样的啊
我刚才写的那个对不对啊?
连model都不知道肿末推啊 T_T |
|
A*****s
发帖数: 13748 | 9 另外对于binary随便一个distribution不就是 Exercise Pay-off 乘上在RN下的
Exercise Probability么？ 这是binary所以pay-off是常数啊？唯一需要求的就是
Exercise Probability啊？
我理解错了么？所以我一直问所谓的normal model到底神马样子啊。。。 |
|
m*********g
发帖数: 646 | 10 所以我一直告诉你有了DIST就够了，不用管什么NORMAL MODEL阿。 |
|
A*****s
发帖数: 13748 | 11 我就是对normal model百闻不得一见，表示好奇啊 lol |
|
a**n
发帖数: 3801 | 12 normal和lognormal不可能是equivalent measure啊 |
|
h*********7
发帖数: 23 | 13 个人觉得这道题目的意思就是真是的underlying 是normal 但是在市场上我们quote
的时候我们按照B- S 来quote 问你 Digital 的价格怎么变化 |
|
w******i
发帖数: 503 | 14 what is the answer?
my feeling is that lognormal digital call is less expensive than that in
normal model. |
|
k*****y
发帖数: 744 | 15 书上说把normal近似看成lognormal with volatity \sigma/S，lognormal就会小点。
怎么理解？ |
|
s***l
发帖数: 2236 | 16 seminconductor laser is not pumped by light. and no laser nowadays can be
pumped by sun light yet.
normal
can |
|
F****r
发帖数: 151 | 17 请问在C/C++ 里算normal cumulative probability 的function 是什么？ 还有，在那
里可以查到这类信息呢？ 谢谢！ |
|
t******n
发帖数: 21 | 18 I used matlab to generate a normal distribution with 0 as mean and 1 as
standard deviation. But if I used function 'normfit' to fit the generated
dataset, the new mu and sigma values do not match the original data. Is this
right?
normpdf: 0, 1
normfit: 9.9900e-02,1.3498e-01 |
|
H*******e
发帖数: 726 | 19 Please recommend any books or papers that deal with normal density when the
covariance matrix is rank deficient. Thanks in advance. |
|
p********6
发帖数: 1339 | 20 google Lyapunov's central limit theorem
如果满足 limit (sum(mu3_i)/sum(sigma_i^2)) -> 0 (这里mu3_i是每个Xi的三阶中心
矩，sigma_i^2是每个Xi的variance)
那么 sum(Xi) asymptotically belong to Normal(M, V), M=sum(mean_i), V=sum(
sigma_i^2)/n |
|
w****s
发帖数: 4430 | 21 是不是要求DATA是NORMAL才能用？
另外还有一个愚蠢问题，怎么把这个SCORE变为[0， 1] 是不是(Z+1)/2 即可？谢谢。 |
|
q*******t
发帖数: 18 | 22 The residual plot showed non-normality. Will the inference from Proc mixed
still O.K to use?
Does "diff=sattherth" can handle unequal variance?
Thanks |
|
s*****e
发帖数: 422 | 23 levislicn, thanks.
Let it be U.
U is between (0,1) because it's a CDF. U is continuous because a CDF of a
standard normal r.v. is continuous. OK for now.
If U is uniform(0,1), the density of U should be 1. But where should I get
this?
Thanks. |
|
c******3
发帖数: 18 | 24 Hi,
I have 10 values. I assume that they are iid from std normal. I am wondering
how I can check this assumption, that is, what test quantity can be used.
Thanks a lot! |
|
z****e
发帖数: 2024 | 25 what i know is a qqplot to see if the sample is from a normal distribution. |
|
a********a
发帖数: 346 | 26 Is there a way to get residual from mixed model just like from a linear
model to have a qq plot to see the normality of the data?
Thanks |
|
h***i
发帖数: 3844 | 27 sas的 glimix如果random effect不是normal，应该 fit的很烂吧。
Y- |
|
D*********2
发帖数: 535 | 28 The ratio of two independent standard normal random variables is a standard
Cauchy variable. |
|
C******t
发帖数: 72 | 29 I don't know how to post the pdf file. By recogonizing the truncated normal
distribution, the solution is not very difficult. |
|
R*******s
发帖数: 136 | 30 发信人: RedLeaves (Red Leaves), 信区: JobHunting
标 题: Re: X，Y iid normal, 请问X/Y的pdf如何求？ (转载)
发信站: BBS 未名空间站 (Thu Apr 15 18:36:56 2010, 美东)
不太确定对不对啊，取很多 （x,y)，画在二维平面内，感觉就是一个而为高斯分布。y
/x=k=tan(theta). 很明显，对角度的概率密度是个常数f(theta)~constant. 然后有一
个公式可以从f(theta)转到f(k)，好像是这个形式f(theta)*d(theta)=f(k)*dk, 然后f
(k)=constant*d(theta)/dk,这里theta=atan(k).这里面没有考虑角度在第二和第三象
限，但是应该差不多就这样子了 |
|
t**g
发帖数: 1164 | 31 but X2 is normal, not chi-square? |
|
O*****y
发帖数: 222 | 32 That's not right.
sqrt(X2) is not normal. |
|
l*********s
发帖数: 5409 | 33 the question did not specify standard normal. |
|
d******e
发帖数: 7844 | 34 如果不指定Standard normal那啥都算不了。 |
|
l*********s
发帖数: 5409 | 35 If this is normal with mu=0, then it is too easy. |
|
H******e
发帖数: 333 | 36 就是我现在做一个东西，必须要用paired T-test和one-way repeated measured ANOVA
来做（因为要check一些对应数据的mean是不是相同）。
做之前要check assumptions，但是我有2、3组数据算出来的关于difference的结果，不是normally
distributed。
那个Shapiro-Wilk的p-value是<0.05的。
但是从qq plot来看，observations对应的点还是大致成直线的。
这个该怎么办呀？
谢谢 |
|
j*****e
发帖数: 182 | 37 Don't worry too much about the p-value. Even if your data is normal. when
the sample size is large, p-value will be small.
Looking at the qq-plot might be good enough. |
|
s*****e
发帖数: 3954 | 38 ２个treatment的longitudinal data
test normality的时候是 test by treatment and time
还是overall 就好了？
thanks |
|
b**********i
发帖数: 1059 | 39 谢谢。 multivariate normal 发觉容易对付，不用 proc iml 也可以用cholesky
transformation。现在问题是怎么弄multivariate uniform distribution。 这个proc
iml也可以吗？ |
|
w*****n
发帖数: 375 | 40 independent variable 不需要是normal distributed. |
|
D******n
发帖数: 2836 | 41 Wrong.
I think the assumptions for discriminant analysis is u have two
populations and they are normal.
means I
to
nearly |
|
s******y
发帖数: 435 | 42 产生1000 observation with means(0,0), variances (10,10), and covariance 9
.
the SAS data step to accomplish task
data k;
seed = 1283470;
do i = 1 to 1000;
z1 = rannor(seed);
z2 = rannor(seed);
z3 = rannor(seed);
x = 3*z1 + z2;
y = 3*z1 + z3;
output;
end;
drop seed;
run;
请问产生三个随机normal变量z1, z2,z3后用x,y的两个公式怎么理解？ 能否详细解释
一下背后的机理？
谢谢。 |
|
|
f**********t
发帖数: 1001 | 44 它应该assume error项是Normal distribution的。那么它对于数据有没有这
个assumption呢？
我猜测，如果有这个assumption的话，可能是不希望有outliner。比如long
tail distribution就有很多outliner。
望指教！ |
|
a*****3
发帖数: 601 | 45 你确定？ 比如红太阳想知道身高v.s.体重有什么回归关系？抽样身高从五尺5寸，6寸
，....不就行了？ 还非要满足正太分布？
upon parameters; when there is outlier, some inference may be invalid
based: on the normal assumption... |
|
d******g
发帖数: 130 | 46 I think that's the reason why we have large number theorem and t test. The
normality assumption for error is more related to statistical inference for
beta since the distribution of beta depends on the distribution of errors. |
|
D*********2
发帖数: 535 | 47 kirklanda正解。
Y 也 normal. |
|
|
f**********t
发帖数: 1001 | 49 嗯。error和Y|X normal。
X无所谓。 |
|
D*********2
发帖数: 535 | 50 ...那您让兄弟姐妹们回答了一圈simple linear regression的问题。
OLS的假设应该就只是关于error term的，or, to be specific, E[\epsilon|X]=0,
Var[\epsilon|X]=\sigma^2 I_n。normality 都不用。 |
|
