56Eviews+stata分析面板数据的理论与操作一个文件全搞定-第22页
上亿文档资料，等你来发现
56Eviews+stata分析面板数据的理论与操作一个文件全搞定-22
g3|-.；g4|..；g5|-.；output|.89013；fuel|.199127.；load|-1.69-5.3；_cons|9.662237；-----
-.1964526g4 |
.1631721g5 |
-.0154697output |
.9787565fuel |
.4477333load |
-.6690963_cons |
10.31761------------------------------------------------------------------------------ In LIMDEP, run the Regress$ command to fit the LSDV1. Do not forget to include ONE for the intercept in the Rhs subcommand. --& REGRESS;Lhs=COST;Rhs=ONE,G1,G2,G3,G4,G5,OUTPUT,FUEL,LOAD$ +----------------------------------------------------+| Ordinary
least squares regression
|| Model was estimated Aug 27, 2009 at 03:51:23PM
|| LHS=COST
Standard deviation
|| WTS=none
Number of observs.
|| Model size
Parameters
Degrees of freedom
|| Residuals
Sum of squares
Standard error of e
Adjusted R-squared
|| Model test
81] (prob) =3935.82 (.0000) || Diagnostic
Log likelihood
Restricted(b=0)
(prob) = 536.89 (.0000) || Info criter. LogAmemiya Prd. Crt. =
Akaike Info. Criter. =
|| Autocorrel
Durbin-Watson Stat.
Rho = cor[e,e(-1)]
|+----------------------------------------------------++--------+--------------+----------------+--------+--------+----------+|Variable| Coefficient
| Standard Error |t-ratio |P[|T|&t]| Mean of X|+--------+--------------+----------------+--------+--------+----------+Constant|
12.7703592LOAD
. What if we drop a different dummy variable, say g1, instead of g6? Since the differentreference point is applied, you will get different dummy coefficients. As shown in the above, the intercept 9.7059 in this model is the actual parameter estimate (Y-intercept) of g1, which was excluded from the model. The Y-intercept of airline 2 is computed to get 9.9-.0412. The Y-intercept of airline 2 (9.6647) is .0412 smaller than the reference point of 9.7059. Actual Y-intercepts of other dummies are computed in this manner. The other statistics such as parameter estimates of regressors and goodness-of-fit measures remain unchanged. That is, choice of a dummy variable to be dropped does not change a model. . regress cost g2-g6 output fuel load Source |
Number of obs =
90-------------+------------------------------
81) = 3935.79Model |
14.2185338
0.0000Residual |
0.9974-------------+------------------------------
Adj R-squared =
0.9972Total |
114.040893
.06011 ------------------------------------------------------------------------------cost |
[95% Conf. Interval]-------------+----------------------------------------------------------------g2 |
.0088722g3 |
-.1237652g4 |
.3054345g5 |
.1830387g6 |
.2545924output |
.9787565fuel |
.4477333load |
-.6690963_cons |
10.0902------------------------------------------------------------------------------ When you have not created dummy variables, take advantage of the .xi prefix command (interaction expansion) to obtain the identical result. The Stata .xi, like.bysort, is used either as an ordinary command or a prefix command. .xi creates dummies from a categorical variable specified in the term i. and then run the command following the colon. Stata bydefault drops the first dummy variable, while PROC TSCSREG and PROC PANEL in Section4.5.2 drop the last dummy. . xi: regress cost i.airline output fuel load i.airline
_Iairline_1-6
( _Iairline_1 omitted) Source |
Number of obs =
90-------------+------------------------------
81) = 3935.79Model |
14.2185338
0.0000Residual |
0.9974-------------+------------------------------
Adj R-squared =
0.9972Total |
114.040893
.06011 ------------------------------------------------------------------------------cost |
[95% Conf. Interval]-------------+----------------------------------------------------------------_Iairline_2 |
.0088722_Iairline_3 |
-.1237652_Iairline_4 |
.3054345_Iairline_5 |
.1830387_Iairline_6 |
.2545924output |
.9787565fuel |
.4477333load |
-.6690963_cons |
10.0902------------------------------------------------------------------------------ 4.3 LSDV2 without the Intercept LSDV2 reports actual parameter estimates of the dummies. You do not need to compute actual Y-intercept any more. Because LSDV2 suppresses the intercept, you will get incorrect F and R2 statistics. However, the SSE of LSDV2 is correct. In PROC REG, you need to use the /NOINT option to suppress the intercept. Obviously, the F value of 497,985 and R2 of 1 are not likely. However, SSE, parameter estimates of regressors, and their standard errors are correct. Make sure that the intercepts presented in the beginning of Section 4.2 are what we got here using LSDV2.PROC REG DATA=masil.MODEL cost = g1-g6 output fuel load /NOINT;RUN; The REG ProcedureModel: MODEL1
Dependent Variable: cost Number of Observations Read
90Number of Observations Used
90 NOTE: No intercept in model. R-Square is redefined. Analysis of VarianceSum of
MeanSource
Pr & FModel
0.00361Uncorrected Total
16192 Root MSE
1.0000Dependent Mean
1.0000Coeff Var
0.44970 Parameter Estimates Parameter
StandardVariable
Pr & |t|g1
&.0001output
&.0001fuel
&.0001load
&.0001Stata uses the noconstant option to suppress the intercept. Notice that noc is its abbreviation.. regress cost g1-g6 output fuel load, noc Source |
Number of obs =
90-------------+------------------------------
0.0000Residual |
1.0000-------------+------------------------------
Adj R-squared =
1.0000Total |
179.906633
.06011 ------------------------------------------------------------------------------cost |
[95% Conf. Interval]-------------+----------------------------------------------------------------g1 |
10.0902g2 |
10.06062g3 |
9.944618g4 |
10.37153g5 |
10.24919g6 |
10.31761output |
.9787565fuel |
.4477333load |
-.6690963------------------------------------------------------------------------------ In LIMDEP, you need to drop ONE out of the Rhs subcommand to suppress the intercept. Unlike SAS and Stata, LIMDEP reports correct R2 (.9974) and F (3,936) even in LSDV2.
REGRESS;Lhs=COST;Rhs=G1,G2,G3,G4,G5,G6,OUTPUT,FUEL,LOAD$ +----------------------------------------------------+| Ordinary
least squares regression
|| Model was estimated Aug 27, 2009 at 03:53:24PM
|| LHS=COST
Standard deviation
|| WTS=none
Number of observs.
|| Model size
Parameters
Degrees of freedom
|| Residuals
Sum of squares
Standard error of e
Adjusted R-squared
|| Model test
81] (prob) =3935.82 (.0000) || Diagnostic
Log likelihood
Restricted(b=0)
(prob) = 536.89 (.0000) || Info criter. LogAmemiya Prd. Crt. =
Akaike Info. Criter. =
|| Autocorrel
Durbin-Watson Stat.
Rho = cor[e,e(-1)]
|| Not using OLS or no constant. Rsqd & F may be & 0. |+----------------------------------------------------++--------+--------------+----------------+--------+--------+----------+|Variable| Coefficient
| Standard Error |t-ratio |P[|T|&t]| Mean of X|+--------+--------------+----------------+--------+--------+----------+G1
12.7703592LOAD
. 4.4 LSDV3 with Restrictions LSDV3 imposes a restriction that the sum of the dummy parameters is zero. PROC REG has the RESTRICT statement to impose restrictions. LSDV3 reports the correct ANOVA table and parameter estimates of regressors but produces different, compared to those of LSDV1 and LSDV2, dummy coefficients due to the different baseline (group average) used.PROC REG DATA=masil.MODEL cost = g1-g6RESTRICT g1 + g2 + g3 + g4 + g5 + g6 = 0;RUN;The REG ProcedureModel: MODEL1Dependent Variable: cost NOTE: Restrictions have been applied to parameter estimates. Number of Observations Read
90Number of Observations Used
90 Analysis of Variance Sum of
MeanSource
0.00361Corrected Total
114.04089 Root MSE
0.9974Dependent Mean
0.9972Coeff Var
0.44970 Parameter Estimates Parameter
StandardVariable
Pr & |t|Intercept
0.0532output
&.0001load
&.0001RESTRICT
3.01674E-15
7.82306E-11
1.0000* * Probability computed using beta distribution. A dummy coefficient means the deviation from the averaged group effect (9.714). The actual intercept of airline 2, for example, is 9.5+ (-.0488). Notice that the 3.01674E-15 of RESTRICT is virtually zero. In Stata, you have to use the .cnsreg command in stead of .regress. The command, however, does not provide an ANOVA table and goodness-of-fit statistics other than F and SEE (standard error of residual--error term, square root of MSE). . constraint define 1 g1 + g2 + g3 + g4 + g5 + g6 = 0. cnsreg cost g1-g6 output fuel load, constraint(1) Constrained linear regression
Number of obs
3935.79Prob & F
0.0000Root MSE
0.0601 包含各类专业文献、专业论文、行业资料、幼儿教育、小学教育、外语学习资料、56Eviews+stata分析面板数据的理论与操作一个文件全搞定等内容。　
　Eviews6.0 面板数据操作 一、数据输入 1、创建工作...打开后,跳出工作文件 双击 , 然后分别进行变系数、...3) 、回归分析 若检验结果表明应采用变系数模型,... 　一个良好的习惯 2、建立面板数据工作文件 workfile (1)最好不要选择 EViews ...截面变截距模型的设置 截面变截距模型的估计结果 15、建立时期变截距模型,分析没... 　Eviews6.0 面板数据操作 1.数据输入 1.1 创建工作...也可以通过重新打开工作文件,如下图操作。 选择自己...3) 、回归分析 若检验结果表明应采用变系数模型,... 　eviews面板数据模型详解_经管营销_专业资料。eviews面板....1 (1)建立面板数据工作文件 ) 首先建立工作文件...。 综上分析, 年中国东北、华北、 综上分析,1996... 　一个良好的习惯 2、建立面板数据工作文件 workfile (1)最好不要选择 EViews ...截面变截距模型的设置 截面变截距模型的估计结果 15、建立时期变截距模型,分析没... 　Eviews6.0 面板数据操作 一、数据输入 1、创建工作...打开后,跳出工作文件 双击 , 然后分别进行变系数、...3) 、回归分析 若检验结果表明应采用变系数模型,... 　Eviews和stata处理panel data的简单比较_金融/投资_经管营销_专业资料。这两天来的小结,因为都是些皮毛,博大家一笑。 使用的案例是论坛里张晓峒老师的面板数据模型 ... 　计量经济面板数据模型及EVIEWs软件的实现_经管营销_专业资料。面板数据模型的分析及...模型数据估计的 Eviews 实现 (1) 建立合并数据库(pool)对象 首先建立工作文件...Eviews+stata分析面板数据的理论与操作一个文件全搞定_图文_百度文库
两大类热门资源免费畅读
续费一年阅读会员，立省24元！
评价文档：
Eviews+stata分析面板数据的理论与操作一个文件全搞定
E​v​i​e​w​s​+​s​t​a​t​a​分​析​面​板​数​据​的​理​论​与​操​作​一​个​文​件​全​搞​定
阅读已结束，如果下载本文需要使用
想免费下载本文？
下载文档到电脑，查找使用更方便
还剩171页未读，继续阅读
你可能喜欢基于EViews 6的面板数据计量分析1_百度文库
两大类热门资源免费畅读
续费一年阅读会员，立省24元！
评价文档：
基于EViews 6的面板数据计量分析1
阅读已结束，如果下载本文需要使用
想免费下载本文？
下载文档到电脑，查找使用更方便
还剩7页未读，继续阅读
你可能喜欢扫扫二维码，随身浏览文档
手机或平板扫扫即可继续访问
计量经济学Eviews讲义2
举报该文档为侵权文档。
举报该文档含有违规或不良信息。
反馈该文档无法正常浏览。
举报该文档为重复文档。
推荐理由：
将文档分享至：
分享完整地址
文档地址：
粘贴到BBS或博客
flash地址：
支持嵌入FLASH地址的网站使用
html代码：
&embed src='/DocinViewer-4.swf' width='100%' height='600' type=application/x-shockwave-flash ALLOWFULLSCREEN='true' ALLOWSCRIPTACCESS='always'&&/embed&
450px*300px480px*400px650px*490px
支持嵌入HTML代码的网站使用
您的内容已经提交成功
您所提交的内容需要审核后才能发布，请您等待！
3秒自动关闭窗口苹果/安卓/wp
苹果/安卓/wp
积分 38, 距离下一级还需 7 积分
道具: 彩虹炫, 雷达卡, 热点灯, 雷鸣之声, 涂鸦板, 金钱卡下一级可获得
道具: 显身卡
购买后可立即获得
权限: 隐身
道具: 金钱卡, 雷鸣之声, 彩虹炫, 雷达卡, 涂鸦板, 热点灯
本帖最后由 wanghaidong918 于
19:24 编辑
在网上发现好多童鞋问关于怎么用EVIEWS 做VR TEST，正好这次大作业有用到，所以写个简单的guide~
在eviews软件里面选file/open/programs. 打开附件里的这个vrtest.prg。程序就会自动打开一个源代码的窗口。
下面我们要在这个源代码的窗口改两个地方：
1）在step1-input里面有一行series x =ret_CHS_m ，把这个等号后面的名字改成你要做VR TEST的series的名字。
' Step1 - Input
series x =ret_CHS_m （改这里）& && && && && &' set basic series to be tested. . (Create a new series called x, containing the series to be analysed by the variance ratio test.)
!q=16& && && && && && && && && && && &&&' set variance ratio return horizon q periods
' %first is first data obs to be used of basic series x
' %last is last data obs to be used of basic series x
' NO MORE INPUT REQUIRED FOR FOLLOWING CALCULATIONS
' *******************************************************************************
2）在Step 2 - Calculate Variance Ratio里有这行for %first %last 0M12，把后面的这个时间段改成你要检验的时间段。具体格式你可以随便做个test或者regression看eviews自动生成的那个时间段的格式是怎么写的
'Step 2 - Calculate Variance Ratio
for %first %last 0M12（改这里）
' start of sample adjusted for 1 period to calculate one-period returns, and !q periods for !q period horizon
好啦，然后就点run，你的eviews里面就自动会出现一个叫vrtest的table了
& && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && && &&&N(0,1) 2-sided& && && && && && && && && && &N(0,1) 2-sided
Data period& && && && & Nr base obs nq& && & Horizon q& && && &&&VRq& && && && &test stat Zq& &&&sign-level& && && && &test stat Zq*& && & sign-level
0M12& &35& && && && && && && && && &&&16& && && && && && && &&&0.0600& && &&&-1.2634& && && &0.20646& && && && && &-0.9494& && && && &&&0.34242
载入中......
19:30:42 上传
售价: 1 个论坛币
是不是真的啊，表示怀疑
运用起来，远比matlab简单，向大家强力推荐
等号后面的ret_CHS_m 要改成什么东西，怎么改
好东西 刚好论文用到 弄下来看看怎样
请楼主告知如果没有用时间段 用的是unstructure的 只有observation的数量 在那个地方怎么改才能运行
{:soso_e132:}可以用吗？
特别想看看
楼主好宁 解决我的大问题了 实在是感谢
论坛好贴推荐
&nbsp&nbsp|
&nbsp&nbsp|
&nbsp&nbsp|
&nbsp&nbsp|
&nbsp&nbsp|
&nbsp&nbsp|
为做大做强论坛，本站接受风险投资商咨询，请联系（010-）
邮箱：service@pinggu.org
合作咨询电话：(010)
广告合作电话：（刘老师）
投诉电话：(010)
不良信息处理电话：(010)
京ICP证090565号
京公网安备号
论坛法律顾问：王进律师