s******e
发帖数: 493 | 1 Oh man. I am just wasting my time...
PLEASE read my post CAREFULLY. Did I ever say that inner class has to keep a
local reference to the enclosing class variables? Here is what I said:
let me give you a better example to help you understand
public class A
{
private int i;
Class B
{
public int getI()
{
return i;
}
}
}
in this case, since once compiled, class A and B will be independent (not
mean that they are not coupled) classes, if we allow B to access A's private
var... 阅读全帖 |
|
s******y
发帖数: 352 | 2 With ODS, you can request the data objects that created from the SAS
procedures. When you specify NLEVELS option in proc freq, data object
nlevels will be generated. wihtin the dataset, you can get the number of
levels for the varaibles specified in the table statement.
if a varaible dosen't have any value, the Nnonmisslevels (number of non-
missing levels) is 0. otherwise it will be the number of the disticnt value
the variable has. |
|
P******0
发帖数: 9787 | 3 这个不是集成的问题，不是Varaible cost下不来，是有大量的Fixed Cost需要分摊。 |
|
x********4
发帖数: 405 | 4 there is a varaible called acquisition attitude or something like it... it
is in sdc m&a database
assume that if an acquiror is not a White Knight, then it must be a hostile
bidder? 这个assumption好像too strong |
|
p********r
发帖数: 30 | 5 when you apply for school, you are requierd to disclose your asset and
income , 529 is included, but life insurance is not. So life insurance will
not affect your qualification for scholarship but 529 will.
cash value life insurance include VUL ( varaible universal life) and IUL (
Index universal life) |
|
l****x
发帖数: 60 | 6 第一轮电话面试
CS 45分钟
1.先聊以往经历 从简历开始问起 了解做过什么 喜欢用哪种programming language
2.C 语言细节 static varaible, static function 以及其深度应用和为什么需要
static
3.讨论 Java garbage collector 的细节 什么时候分配和回收资源 怎么运作 对象建
立之后什
么时候 内存什么时候被回收
4.如何用C++ 实现简单的 garbage collection，不用实现 主要是讲想法
5.reverse a linked list
答得太乱了 面试官很nice 但自己答中间3个问题的时候很紧张 发挥不好，最后一个以
前做过 电话面
试的时候基本什么都没说出来 哎 只能 move on 了~~
请各位大侠 帮我深度分析一下static 还有java garbage collection，和如何用C++实
现的思想
我当时真的不知道要答些什么东西~ T_T |
|
t*********h
发帖数: 941 | 7 assume X is a random varaible, then E(X)=int( X F(X)DX ). (this is so ugly.
see http://en.wikipedia.org/wiki/Expected_value)
e.g. for first train:
X is your waiting time, then we have
E(X) = int(X*1/10)DX = X*X/20, X from 0 to 10. plug in we have E(X)=5. |
|
d***i
发帖数: 597 | 8 请把所谓统计数据and source引用一下，我也学习学习
and统计的paper，每个作为predictable varaible的都需要给出定义和量化标准，我好
奇，要看看这个variable究竟如何定义的。
我虽然没有作过自闭症方面，我们中心做这方面的人海真是很多了，从来没听说过把外
貌作为predictable variable来做分析的。 |
|
t******y
发帖数: 949 | 9 那我买的斯巴鲁的Legacy是CVT（continues varaible transmission)是不是油耗
ijiumeiyou所谓的磨合期了？根本没齿轮。 |
|
qm
发帖数: 27 | 10 you still don't understand what i mean. i didn't misunderstand the parameter
passing. i am talking about the syntax surgar. the extra 'ref' keyword in the
function call with reference parameter is very important.
in c#, when you read some source code like this,
f(ref value);
you know the varaible 'value' could be changed by function 'f'. but there's no
such 'syntax surgar' allows a c++ programmer to specify this.
in c++, when you read this,
f(value);
you have to check the header file to make sur |
|
c*****t
发帖数: 1879 | 11 只要记住一点，所谓的 pattern 其实就是如何将 code, varaible,
object 等参数化。
delegate void CodeBlock ();
void myExec (CodeBlock block11, CodeBlock block2)
{
...
block1 ();
...
block2 ();
...
} |
|
h****e
发帖数: 2125 | 12 比如有个local varaible “stack”，怎么在gdb里面看stack.top()的返回值？
谢谢。 |
|
j*****k
发帖数: 1198 | 13 来自主题: Programming版 - 问个问题 你的意思是说如果const A a的情况下？在一般情况下（不用const function和mutable)
也可以只修改想修改varaible呀 |
|
c*****z
发帖数: 182 | 14 ///subtraction: input varaibles are small and big
/// i assume we already know small < big
result = big;
loop(small)
result = decrement(result);
end loop |
|
b***i
发帖数: 3043 | 15 suppose "is" is the istreamstring varaible, which contains the whole line:
txt1 txt2 , 1, 2, 0, 3 ,
what I did was, to use is>>string1; to read first string, because space is
the delination char, then I use getline(is, sring2, ","); to read the second
string, such as txt2. then, I use a while loop to read the numbers
while(getline(is, ss, ','))
{
cout<
istringstream(ss)>>i;
cout<
}
but string thing is, the last number, was 0 if I use ato |
|
I**R
发帖数: 1309 | 16 let C stands for claim payment
C=0 if X<=1000
C=X-1000 otherwise
here, C obviously is a random varaible. hope this helps.
0.
of |
|
c**b
发帖数: 474 | 17 比如Li Hongbin和Chen yuyu关于母亲教育对儿童健康的影响，好像在journal of
Health Econ 2009年的某一期。领养儿童数据可以控制ability，基因这样的omitted
varaible。 |
|
c**b
发帖数: 474 | 18 比如Li Hongbin和Chen yuyu关于母亲教育对儿童健康的影响，好像在journal of
Health Econ 2009年的某一期。领养儿童数据可以控制ability，基因这样的omitted
varaible。 |
|
s******r
发帖数: 1524 | 19 proc sql;
select distinct compress(name||'='||name||'_v') into :M_Var_list separate by
' ' from
dictionary.columns
where libname='WORK' and memname='TEST';
%put &M_Var_list;
proc datasets lib=work;modify test;rename &M_Var_list;run;quit;
If your variable name is too long, probably you should need use %do to
rename varaible one by one.
加个v？该 |
|
D******n
发帖数: 2836 | 20 在 songkun (告别棒球场) 的大作中提到: 】
ya, thats what i meant.
You can do it but it looks ugly.
But i guess most of the time we dont come across this problem or we can copy
the varaible
g<-function(x)
{ a<-x;
a[1]<-1;
return(a);
}
a <- c(0,1,2),
a<-g(a);
cat(a);
but this is very slow. and yes, we can use your method.
Anyway, if we can use pass by reference in R, it would be much more straight
forward . Even perl has pass by reference, although as far as i know matlab
doesnt have pass by reference eithe |
|
l****g
发帖数: 304 | 21 For example:
value of name: zhang
value of Birthday: 090225 (format as yymmdd6.)
New value for the new variable: zhang090225; for the new variable, the birthday keeps yymmdd format(two digits year, two digits month, two digits day).
Thank you! |
|
s*****n
发帖数: 2174 | 22 you need to specify:
1. what is your input file like
2. what platform do you want to use
3. what output format do you want.
keeps |
|
l****g
发帖数: 304 | 23 Thank you, SongKun.
1. what is your input file like
Sas data file with:
Birthday format as yymmdd6.
Name format as $20.
2. what platform do you want to use
Windows?
3. what output format do you want.
I want to create another character variable which concatenate variable name
and variable Birthday.
The example:
name: zhang
Birthday: 090225
I want to create a new value: zhang090225 based on the name and birthday of
that record. |
|
s*****n
发帖数: 2174 | 24 I don't know much about SAS.
Wait for SAS people to answer.
name |
|
l****g
发帖数: 304 | 25 Thank you for clairyong what I am asking, Songkun. |
|
q**j
发帖数: 10612 | 26 try this, it may or may not work:
compress(name||input(put(birthday,YYMMDD6.),$6.))
if II does not work cats() might do. |
|
l****g
发帖数: 304 | 27 Thank you, QQZJ, it works!!
If I ingore the input funcion here as:
compress(name||put(birthday,YYMMDD6.)), it works also.
Thanks again! |
|
y****1
发帖数: 400 | 28 Right, coz the compress function removes spaces by default. |
|
q**j
发帖数: 10612 | 29 good to know. i am kind of surprised. learned sth new too. |
|
s*****n
发帖数: 2174 | 30 你确定你newdata里面的变量名和object里面用的是一样的吗?
90%的可能是你newdata 里面的变量名(列名) 和 object里面的不一样.
不一样的话, R会认为缺失prediction varaible, 于是使用默认的
原object里面的variable, 得到的结果是object里面的1000 个 fitted values. |
|
c****s
发帖数: 63 | 31 现在在建一个model, 里面有200多个ccs的individual varaibles, 老板要获得这些
variables的weighting。 我说将model 中的Beta(coefficent) 做为weighting factor
不可以吗？但老板说这还不够。要我考虑怎样获得这些weighting factor, 或者考虑怎
样将beta 转为weighting factor。
还望各位大牛给出出主意，先谢谢了！ |
|
D******n
发帖数: 2836 | 32 its awkward. lets say pass a varaible from one step to another step.... |
|
d*******1
发帖数: 854 | 33 ok, here is what i am doing:
result<- lapply(split(all,all$CHIPEXP_NAME),function(x) lm(logvalue~
treatment,x))
用lapply拿到result(是个 vector)
再用：
res<- sapply(result, function(x)
{fs<- summary(x)$fstatistic;pf(fs[1],fs[2],fs[3],lower
.tail=F)}
)
拿到每个by variable 的 p value, 我的问题是怎样拿到其他stat呢？比如parameter
estimtate, parameter stderr, degree of freedom.....etc? 如何看到result 的结
构呢？
用names(result)只是得到所有by variable的值， 因为我这个result是由lapply产生
的一个vector, 每个by varaible的值都成了colum |
|
s******r
发帖数: 1524 | 34 My coworker created a dataset with varaibles name as
00-70%.
Anyone has idea how to read it by data step and proc sql?
Thanks, |
|
r********3
发帖数: 2998 | 35 1. Varaibles比较多的话，处理方法首先是人工选择一些相关的出来。另外，有一些
PCA啊，clustering之类的办法可以reduce dimensions.
2. records比较多的话，处理办法，一个是sample。另外你得用数据库，database。然
后通过SQL的分页查询来提取数据。至于数据处理，如果规模真的很大，可以考虑分布
式计算，比如MapReduce之类的平台。 |
|
w*****t
发帖数: 49 | 36 俺很笨，不会说话，2-3句就说完了。
比如logistic regression。
俺就描述一下binary response variable，
然后fit data，
然后选variable，
然后解释一下选出的varaible。
哪位大侠给指出一下，比较好的描述project的方式呢？
谢谢！ |
|
d******e
发帖数: 7844 | 37 我觉得数据大不大取决于你的model。
你要是只算mean和variance，做做T－test，上千万也不回觉得大。
你要是做个lasso，几百万个数据，几十万个variable就很强大了。
你要是做个graphical lasso，几十万个varaible的话那就无敌了。。 |
|
p***l
发帖数: 1775 | 38 电面结束,表现很失败
主要问2个问题
一个是一群不懂统计的人(你的领导)在交给你project前,你要问他们什么问题
这个问题我胡扯了一下,说问以前失败的案例,其他实在想不起问什么
另一个是给你data了,你用什么model
我答了logistic
他问我怎么判断哪些variable重要
我说我会建立个full model,做varaible selection
然后pay attention to 一些诸如income,每个月是否按时还钱的记录
10分钟不到就结束了,感觉很糟糕
希望版上同仁能点评一下 |
|
v*********0
发帖数: 941 | 39 Did you give the season that you choose logistic model?
I mean the data include both categorical and numerical variables? or other
points to support choosing logistic?
AND how did you express " how to do variable selection" -->
did you mention criteria : p-valule or other ; method: stepwise or other
-->另一个是给你data了,你用什么model
我答了logistic
他问我怎么判断哪些variable重要
我说我会建立个full model,做varaible selection |
|
|
g**********t
发帖数: 475 | 41 use GLM and assume response follows beta distribution. |
|
g****8
发帖数: 2828 | 42 这个可以选不同的link func，不一定要assume那个beta dist吧？ |
|
a*z
发帖数: 294 | 43 I heard that industry only accepts logistic. I am not sure if it is true. |
|
L*****2
发帖数: 66 | 44 I am building a survival model with few indepdent varaible being time
dependent. The values of these variables are not known in the future, for
instance, Bureau Score. In other words, when predicting the responses over
time starting at a certain point, we only know the values at that point,
not the values after that. My question is: should we use values at the
observation time for these variables or use the updated values over time in
the model development? |
|
i*********e
发帖数: 783 | 45 If I have a data: 1500 records: 50 records with the depenedent varialbe's
vlaue of 1.
In this condition, if I use spss, should I just select only 50 records with
the dependent varaible's value of 0 and put the other 50 records with the
dependent variable's value of 1 together.
SPSS has no function of K fold cross validation, as far as I know.
Thanks! |
|
i*********e
发帖数: 783 | 46 I have 20 independent varaibles.
Now discuss 3 independent variables: A continuous
B categorical
C categorical
the dependent variable is categorical.
I know B, C and A reflects the same thing. For example, A is income, B and C
is the house type or sth else, just categorical reflection of A.
My guess is that finally I only need A. But how do I use a statistical
method to eliminate B and C?
Thanks! |
|
e***w
发帖数: 1160 | 47 I am spliting a large data sets into two data sets, below is my code.
data a1 a2;
set a;
if _n_<=5000 then output a1;
else output a2;
run;
Suppose data A has 10000 records, I end up get two data sets A1 and A2, each
contains 5000 records and same varaibles as a.
But the problem is the filesize of A1 and A2 is much larger than A.
Does anybody know what is going on here?
Thanks |
|
S*******u
发帖数: 727 | 48 我想请教一个问题:
我在做LOGISTIC PREDICTION. 我有CONTINOUS 的 INDEPENDENT PREDICTOR,我要TEST
这个CONTINUOUS PREDICTOR 是否与BINARY OUTCOME 有RELATED.但是我不想把
CONTINUOUS 的VARAIBLE 变成CATEGORICAL,用哪个TEST 测CONTINUOUS VARIABLE 与
BINARY OUTCOME 的相关性?
谢谢了 |
|
c********1
发帖数: 60 | 49 不知道版上各位大牛对第三题有什么想法没？我有一个比较粗浅的想法，也不太肯定是
否make sense:建立一个数据库，退货率是其中一个variable，还有其他的varaible像
是商品的相关信息和客户的相关信息。以退货率之外的其他所有变量对退货率做一个
regularized regression，选取其中显著的变量，然后进一步研究被选取变量和退货率
的关系。到了这一步多半得用business sense了。 |
|
c********1
发帖数: 60 | 50 不知道版上各位大牛对第三题有什么想法没？我有一个比较粗浅的想法，也不太肯定是
否make sense:建立一个数据库，退货率是其中一个variable，还有其他的varaible像
是商品的相关信息和客户的相关信息。以退货率之外的其他所有变量对退货率做一个
regularized regression，选取其中显著的变量，然后进一步研究被选取变量和退货率
的关系。到了这一步多半得用business sense了。 |
|
