古扎拉蒂第五版数据Table 12_10
古扎拉蒂《计量经济学基础》复习笔记和课后习题详解（多元回归分析：推断问题）【圣才出品】
古扎拉蒂《计量经济学基础》复习笔记和课后习题详解（多元回归分析：推断问题）【圣才出品】第8章多元回归分析：推断问题8.1 复习笔记考点一：再议正态性假定★当回归模型的参数用于估计和推断两个方面时，还需要假定u i服从正态性假定，即：u i～N（0，σ2）。
在三变量模型中，偏回归系数的OLS估计量与ML估计量一致，是最优线性无偏估计量（BLUE）。
参数估计量也是正态分布的，且（n－3）（σ∧2/σ2）～χ2（n－3）。
参数的t值均服从自由度为n－3的t分布。
t分布可用于构造置信区间并进行假设检验。
χ2分布可用于检验关于真实σ2的假设。
考点二：多元回归中的假设检验的多种形式★1．检验个别偏回归系数的假设。
2．检验估计的多元回归模型的总体显著性，即判别全部偏斜率系数是否同时为零。
3．检验两个或多个系数是否相等。
4．检验偏回归系数是否满足某种约束条件。
5．检验所估计的回归模型在时间上或在不同横截面单元上的稳定性。
6．检验回归模型的函数形式是否正确。
考点三：检验关于个别偏回归系数的假设★★t检验的程序是基于随机误差项u i服从正态分布的假定。
检验方法：给定一个特定的显著性水平α，当t值超过临界值tα/2（df），则拒绝原假设。
或使用p值判断，当p足够小，则拒绝原假设。
参数β∧2的（1－α）置信区间为：（β∧2－tα/2se（β∧2），β∧2＋tα/2se（β∧2））。
由于不能直接观测u i，所以利用代理变量u∧i，即残差。
残差的正态性可进行雅克-贝拉（JB）检验（大样本检验）。
考点四：检验样本回归的总体显著性★★★★★1．总体显著性检验（1）定义总体显著性检验的原假设为：H0：β2＝β3＝0。
也就是检验Y是否与X2和X3存在线性关系。
（2）总体显著性检验与个别显著性检验检验个别显著性时，隐含地假定每一个显著性检验都是根据一个不同的（即独立的）样本进行的。
如果用同一样本数据去进行联合检验，就违反了检验方法所依据的基本假定。
数据库系统第五版课后习题答案
第1章绪论1 ．试述数据、数据库、数据库系统、数据库管理系统的概念。
答：( l ）数据（ Data ) ：描述事物的符号记录称为数据。
数据的种类有数字、文字、图形、图像、声音、正文等。
数据与其语义是不可分的。
解析在现代计算机系统中数据的概念是广义的。
早期的计算机系统主要用于科学计算，处理的数据是整数、实数、浮点数等传统数学中的数据。
现代计算机能存储和处理的对象十分广泛，表示这些对象的数据也越来越复杂。
数据与其语义是不可分的。
500 这个数字可以表示一件物品的价格是 500 元，也可以表示一个学术会议参加的人数有 500 人，还可以表示一袋奶粉重 500 克。
( 2 ）数据库（ DataBase ，简称 DB ) ：数据库是长期储存在计算机内的、有组织的、可共享的数据集合。
数据库中的数据按一定的数据模型组织、描述和储存，具有较小的冗余度、较高的数据独立性和易扩展性，并可为各种用户共享。
( 3 ）数据库系统（ DataBas 。
Sytem ，简称 DBS ) ：数据库系统是指在计算机系统中引入数据库后的系统构成，一般由数据库、数据库管理系统（及其开发工具）、应用系统、数据库管理员构成。
解析数据库系统和数据库是两个概念。
数据库系统是一个人一机系统，数据库是数据库系统的一个组成部分。
但是在日常工作中人们常常把数据库系统简称为数据库。
希望读者能够从人们讲话或文章的上下文中区分“数据库系统”和“数据库”，不要引起混淆。
( 4 ）数据库管理系统（ DataBase Management sytem ，简称 DBMs ) ：数据库管理系统是位于用户与操作系统之间的一层数据管理软件，用于科学地组织和存储数据、高效地获取和维护数据。
DBMS 的主要功能包括数据定义功能、数据操纵功能、数据库的运行管理功能、数据库的建立和维护功能。
解析 DBMS 是一个大型的复杂的软件系统，是计算机中的基础软件。
目前，专门研制 DBMS 的厂商及其研制的 DBMS 产品很多。
数值分析课程第五版课后习题答案
=
1 = 1.7863 × 10 − 2 。 55.982
8、当 N 充分大时，怎样求 ∫ [解]因为 ∫
N +1 N
1 dx ？ 1+ x2
1 dx = arctan( N + 1) − arctan N ，当 N 充分大时为两个相近数相 1+ x2
减，设 α = arctan( N + 1) ， β = arctan N ，则 N + 1 = tan α ， N = tan β ，从而 tan(α − β ) = 因此 ∫
5、计算球体积要使相对误差限为 1%，问度量半径 R 允许的相对误差是多少？ 4 ε * ( π (R* )3 ) 4 3 [解]由 1% = ε r* ( π ( R * ) 3 ) = 可知， 4 3 * 3 π (R ) 3 ′ 4 4 4 ε * ( π ( R * ) 3 ) = 1% × π ( R * ) 3 = π ( R * ) 3 ε * ( R * ) = 4π ( R * ) 2 × ε * ( R * ) ， 3 3 3
ε * ( y n ) = 10ε * ( y n −1 ) = 10 n ε * ( y 0 ) ，
1 1 从而 ε * ( y10 ) = 1010 ε * ( y 0 ) = 1010 × × 10 − 2 = × 10 8 ，因此计算过程不稳定。 2 2 12、计算 f = ( 2 − 1) 6 ，取 2 ≈ 1.4 ，利用下列公式计算，哪一个得到的结果最 好？ 1 ( 2 + 1)
* r
x= x
*
ε ( x * ) = n( x * ) n −1 2% x * = 2n% ⋅ x * ，
(完整版)数值分析第五版答案(全)(最新整理)
第一章 绪论1．设,的相对误差为，求的误差。
0x >x δln x 解：近似值的相对误差为*x *****r e x x e x x δ-===而的误差为ln x ()1ln *ln *ln **e x x x e x =-≈进而有(ln *)x εδ≈2．设的相对误差为2%，求的相对误差。
x n x 解：设，则函数的条件数为()n f x x ='()||()p xf x C f x =又, 1'()n f x nx -= 1||n p x nx C n n-⋅∴==又((*))(*)r p r x n C x εε≈⋅ 且为2(*)r e x ((*))0.02n r x nε∴≈3．下列各数都是经过四舍五入得到的近似数，即误差限不超过最后一位的半个单位，试指出它们是几位有效数字：,, , ,*1 1.1021x =*20.031x =*3385.6x =*456.430x =*57 1.0.x =⨯解：是五位有效数字；*1 1.1021x =是二位有效数字；*20.031x =是四位有效数字；*3385.6x =是五位有效数字；*456.430x =是二位有效数字。
*57 1.0.x =⨯4．利用公式(2.3)求下列各近似值的误差限：(1) ,(2) ,(3) .***124x x x ++***123x x x **24/x x 其中均为第3题所给的数。
****1234,,,x x x x 解：*41*32*13*34*151()1021()1021()1021()1021()102x x x x x εεεεε-----=⨯=⨯=⨯=⨯=⨯***124***1244333(1)()()()()1111010102221.0510x x x x x x εεεε----++=++=⨯+⨯+⨯=⨯***123*********123231132143(2)()()()()1111.10210.031100.031385.610 1.1021385.6102220.215x x x x x x x x x x x x εεεε---=++=⨯⨯⨯+⨯⨯⨯+⨯⨯⨯≈**24****24422*4335(3)(/)()()110.0311056.430102256.43056.43010x x x x x x x εεε---+≈⨯⨯+⨯⨯=⨯=5计算球体积要使相对误差限为1，问度量半径R 时允许的相对误差限是多少？解：球体体积为343V R π=则何种函数的条件数为23'4343p R V R R C V R ππ===A A (*)(*)3(*)r p r r V C R R εεε∴≈=A 又%1(*)1r V ε=故度量半径R 时允许的相对误差限为εr (V ∗)=13∗1%=13006．设，按递推公式 （n=1,2,…）028Y =1n n Y Y -=-计算到（5位有效数字），试问计算将有多大误差？100Y 27.982≈100Y解： 1n n Y Y -=10099Y Y ∴=9998Y Y =9897Y Y =-……10Y Y =-依次代入后，有1000100Y Y =-即，1000Y Y =-, 27.982≈100027.982Y Y ∴=-*310001()()(27.982)102Y Y εεε-∴=+=⨯的误差限为。
Geoneutrinos in Borexino
a r X i v :h e p -e x /0604019v 1 10 A p r 2006Geoneutrinos in BorexinoMarco G.Giammarchi and Lino Miramonti 1Dipartimento di Fisica dell’Universit`a di Milano and Infn.Via Celoria 16,20133Milano,Italy Abstract.This paper describes the Borexino detector and the high-radiopurity studies and tests that are integral part of the Borexino technology and development.The application of Borexino to the detection and studies of geoneutrinos is discussed..1.The Gran Sasso National Laboratory The Gran Sasso National Laboratory (Laboratori Nazionali del Gran Sasso -LNGS),home of the Borexino experiment,is the world’s largest underground laboratory.It is located in the center of Italy in the highway tunnel between Teramo and L’Aquila under the ”Monte Aquila”(Gran Sasso mountain).The laboratory is financed and operated by the Italian National Institute for Nuclear Physics (Infn).Its total underground volume is about 180,000m 3with an area greater than 13500m 2.It is composed of three main experimental halls (20m high,18m wide and 100m long).The overburden rock is on the average about 1,400m,equivalent to 3,700meters of water.The muon flux is reduced by about 6orders of magnitude to a value of approximately 1.1muons per square meter per hour,whereas the neutron flux is of the order of 3×10−6neutrons per square centimeter per second with energies greater than 2.5MeV.The rock of the Gran Sasso mountain has a density of 2.71±0.05g ·cm −3,and consists mainly of CaCO 3and MgCO 3[1].The primordial radionuclide content of the rock of Hall C is 0.66±0.14ppm for 238U,0.066±0.025ppm for the 232Th and 160ppm for K [2].Theradioactive content of the concrete employed as experimental hall liner is 1.05±0.12ppm for 238U and 0.656±0.028ppm for the 232Th [3].The LNGS hosts about 15experiments of astroparticle physiscs such as neutrino research,double beta decay physics,dark matter studies and nuclear astrophysics.Interdisciplinary studies (biology,geology)are also conducted in the LNGS underground location.The Borexino detector is located in one of the big underground experimental halls,hall C.2.The Borexino detectorBorexino is a real time experiment whose main goal is to study the low energy (sub-MeV)solar neutrinos,and in particular the 862keV 7Be solar neutrino line,through the neutrino-electron elastic scattering reaction.The maximum energy of the recoiling electron is 664keV and the experimental design threshold is set at 250keV [4].1talk given by M.G.GiammarchiBorexino is an unsegmented scintillation detector featuring300tonnes of well shielded liquid ultra-pure scintillator viewed by2200photomultipliers(PMT).The detector core is a transparent spherical vessel(Nylon Sphere,100µm thick),8.5m of diameter,filled with300tonnes of liquid scintillator and surrounded by1,000tonnes of high-purity buffer liquid.The scintillator mixture is PC(Pseudocumene)and PPO(1.5g/l)as afluor,while the buffer liquid will be PC alone (with the addition of DMP as light quencher).The photomultipliers are supported by a Stainless Steel Sphere,which also separates the inner part of the detector from the external shielding, provided by2400tonnes of pure water(water buffer),seefigure??.An additional containment vessel(Nylonfilm Radon barrier)is interposed between the Nylon Sphere and the photomultipliers,with the goal of reducing Radon diffusion towards the internal part of the detector.The outer water shield is instrumented with200outward-pointing PMT’s serving as a veto for penetrating muons,the only significant remaining cosmic ray background at the Gran Sasso depth.The innermost2200photomultipliers are divided into a set of1800PMT’s equipped with light cones(so that they see light only from the Nylon Sphere region)and a set of400PMT’s without light cones,sensitive to light originated in the whole Stainless Steel Sphere volume. This design greatly increases the capability of the system to identify muons crossing the PC buffer(and not the scintillator).The Borexino design is based on the concept of a graded shield of progressively lower intrinsic radioactivity as one approaches the sensitive volume of the detector;this culminates in the use of 200tonnes of the low background scintillator to shield the100tonnes innermost Fiducial Volume. In these conditions,the ultimate background will be dominated by the intrinsic contamination of the scintillator,while all backgrounds from the construction materials and external shieldings will be negligible.Borexino also features several external plants and purification systems conceived to purify the experimentalfluids(water,nitrogen and scintillator)used by the experiment.The main problem of a real time experiment with such a low energy threshold is the natural radioactivity which is present in any environment and in any material.For these reasons an intense R&D program has been carried out in the last ten years to develop methods for selecting low radioactivity materials and/or purify them.An effort in thisfield has to be complemented by a comparably thorough research concerning detection and measurement of very low radioactivity levels.In this context four purification methods have been developed: distillation,water extraction,stripping with ultrapure N2,solid gel column(Si gel,Al gel) adsorption.Significative results have been achieved by the Collaboration as for example:10−16−10−17(g of contaminants/g of material)for232Th and238U family and a fewµBq of Rn-222in gases and liquids.In addition the organic solvent selected by the collaboration showed a14C concentration clearly below10−17in its ratio to12C;this impurity is particularly important because it cannot be removed by chemical purification processes.For the measurements of these ultralow radioactivity levels,dedicated methods were developed.In addition to small-scale techniques(Ge underground detectors in Rn-free environments,Inductively Coupled Plasma Mass Spectometer,high sensitivity Neutron Activation,Atomic Absorption Spectroscopy etc...[5])a prototype of the Borexino detector, the Counting Test Facility(CTF),has been constructed on purpose and operated in the Hall C of LNGS.The radiopurities and sensitivities reached are summarized below and correspond to the lowest radioactivity levels obtained by the Borexino Collaboration,in preparation of the experiment:•Bulk material radiopurities of10−10g/g for238U and232Th,∼10−5for nat K,few tenths of mBq/kg for60Co,have been measured with Ge detectors in construction materials such asstainless steel,photomultipliers,metal and plastic gaskets,products for PMT sealing,etc...•Radon emanations of10µBq/m2from plastic materials,0.1mBq/m3for Rn-222and1 mBq/m3for Ra-226in water,below1mBq/m3for the N2used for scintillator stripping.•Radiopurity levels of a few times10−15g/g238U,232Th and40K have been reached with ICMPS in measuring the Borexino and CTF shielding water.•Sensitivities of few ppt for238U and232Th concentrations have been obtained in the Nylon Sphere material measurements.•The radiopurity of the scintillator itself was measured to be at the level of few10−16g/g for238U,232Th and∼10−18for14C/12C in the Counting Test Facility.•Bulk radiopurity levels of10−13−10−14g/g for Au,Ba,Ce,Co,Cr,Cs,Ga,Hg,In,Mo, Rb;less than few10−15g/g for Cd,Sb,Ta,W;10−16−10−17g/g for La,Lu,Re,Sc,Th;less than1x10−17g/g for U,have been reached by means of Neutron Activation followed byβ-γdelayed coincidence analysis applied to the scintillator.•Kr and Ar contamination in nitrogen at0.005ppm(for Ar)and0.06ppt(for Kr)were obtained and measured with noble gas mass spectrometry.These results represent a milestone in the development of the Borexino detector and technique.Several of these concepts were incorporated in the construction of the high purity systems for the treatment of the most critical liquid,the scintillator of the experiment.3.The Counting Test FacilityThe CTF description and its performance have been published elsewhere[6,7,8].In this section we simply review the main features of this detector.The CTF consists of an external cylindrical water tank(⊘11×10m;≃1,000t of water) serving as passive shielding for4.8m3of liquid scintillator contained in an inner spherical vessel (Inner Vessel)of2.1m in diameter and observed by100PMT’s.An additional nylon barrier against Radon convection and a muon veto system were installed in1999.Figure??shows a picture of the CTF detector.The radio-purity level of the water is≃10−14g/g(U,Th),≃10−10g/g(nat K)and<5µBq/l for222Rn[6,8,9].The organic liquid scintillator has the same composition as in Borexino.The yield of emitted photons is≃104per MeV of energy deposited and thefluorescence peak emission is located at365nm.The principal scintillator decay time is≃3.5ns in a small volume,while for large volume(because of absorbtion and re-emission)this value is4.5–5.0ns.The attenuation length is larger than5m above380nm[10].The purification of the scintillator is performed by recirculation from the Inner Vessel through a Radon stripping tower,a water extraction unit,a Si-Gel column extraction unit,and a vacuum distillation unit.The232Th and238U contaminations in the CTF liquid scintillator were found to be less than(2–5)·10−16g/g.The Inner Vessel for the liquid scintillator containment is made of nylon with a thickness of500µm,with excellent optical clarity at350-500nm.The collection of scintillation light is ensured by100PMT’s mounted to a7m diameter support structure inside the CTF tank.The photomultiplier tubes are8inches(Thorn EMI9351,the same as for Borexino)made of low radioactivity Schott8246glass and characterized by high quantum efficiency(26%at420 nm),limited transit time spread(σ=1ns),good pulse height resolution for single photoelectron pulses(Peak/Valley=2.5),low dark noise rate(0.5kHz),low after pulse probability(2.5%), and a gain of107.The PMT’s are equipped with light concentrators57cm long and with50cm diameter aperture.The PMT system provides an overall20%optical coverage for events taking place inside the Inner Vessel.The number of photoelectrons per MeV measured experimentally is (300±30)/MeV on average.The total background rate in the250-800keV energy range is about0.3counts/yr·keV·kg and appears to be dominated by external background from Radon in the shielding water(≈30 mBq/m3in the region surrounding the Inner Vessel).The internal background was measured to be less than0.01counts/yr·keV·kg.4.The Counting Test Facility related publicationsData collected with the Counting Test Facility have contributed significantly to the best limits on quantities such as neutrino magnetic moment,electron lifetime,nucleon decays in invisible channels,violation of the Pauli exclusion principle,production of heavy-neutrinos in the sun.Concerning the study of the stability of the electron,the CTF data have been analyzed to search for the256keV line of the gamma emitted in the decay channel e→γν.Since we have found no signal,we established a limit on the electron lifetime ofτ≥4·1026(90%C.L.);this is still the best world limit for the electron decay in this channel[11].CTF data analysis has allowed the study of the neutrino magnetic moment,obtaining the limit ofµν≤0.5·10−10µB,still a very competitive result[12].We have also investigated the possibility of heavy neutrinos(M≥m e)emitted in the 8B reaction in the sun.Heavy neutrinos would decay to light neutrinos via the reaction νH→νL+e++e−.The analysis of the CTF energy spectrum has allowed to significantly enlarge the excluded region of the parameter space with respect to previous experiments[13].The stability of nucleons bounded in nuclei has been studied in the Counting Test Facility searching for decays of single nucleon or pair of nucleons into invisible channels.The limits are comparable to or improve the previously set world limits[14].Furthermore a search was made for non-Paulian transitions of nucleons from nuclear1P shell to afilled1S1/2shell obtaining the best limit on the Pauli exclusion principle[15].Other studies have concerned the search for anti-neutrinos coming from the sun[16]and the cosmogenic11C underground production[17].5.Geoneutrinos detectionOne of the possible application of a high mass well shielded scintillator detector such as Borexino is the search for geoneutrinos,a new and very interesting subject which we will discuss in the remaining of this paper.The conceptual foundations of Earth science rest on a variety of observables as well as interior characteristics.One of the most important interior parameter is the internally produced heat which is currently measured to be in the∼60mW/m2range(or30TW when integrated on the planet surface).Part of this energyflow is due to the presence of radioactive elements in the Earth interior, mainly naturally occurring Uranium and Thorium chain elements and potassium.Models of the Earth disperse about50%of the total U,Th in the crust while leaving the remaining half to the mantle.Roughly speaking,the35km thick continental crust contains a few ppm of U,Th while the much thinner(∼6km)oceanic crust has a typical concentration of∼0.1ppm.Our goal is to measure this radiogenic heat by detecting neutrinos emitted during the decays of the radioactive chains.For a given structure of naturally occurring radioactive families,a measurement of antineutrinoflux can be related to the U,Th family content of the Earth.In the case of the238U family(the235U leftover can be neglected)one can globally represent the full decay chain as:238U→206P b+8α+6e−+6νe+42.8MeV(2) where again a definite number of antineutrinos is emitted and a well defined energy is released.Finally,antineutrinos are also emitted in the K terminations:40K→40Ca+e−+νenergy spectra produced by these three sources are plotted infig.??.Our goal will be to detect antineutrinos emitted by these sources in order to measure the rates of occurrence of the above reactions.5.1.Principle of geoneutrino detectionWhile low energy neutrino detection offers formidable experimental challenges due to backgrounds as explained above,antineutrinos were discovered in a reaction that naturally affords a nice way to cope with the unwanted background events.The proposed detection reaction:νe+p→n+e+detection reaction has a threshold of of1.8MeV which is determined by the mass difference between neutron plus positron and the initial state proton.Therefore this reaction has the drawback of not being sensitive to the detection of K antineutrinos(see fig.??).The detector will reconstruct the antineutrino energy based on the observed positron kinetic energy.The visible energy of the event has to take into account also the1.02MeV energy due to annihilation:E(vis)=K(e+)+1.02MeV(6) which is plotted infig.??for the case of the U and Th chain.In turns,the energy of the antineutrino is shifted with respect to K(e+)by the Q-value of the reaction:E(νenergy isE(vis)=E(νoscillations in the Sun,muon induced neutron production andintroduced in the detecting volume either by natural bulk(226Ra)contamination or(perhaps most importantly)through222Rn diffusion.210Pb has anα-emitting daughter(210Po)which has a138days half-life and can give rise to the reaction13C(α,n)16O(9) This originates a chain of events closely mimicking the[12]H.O.Back et al.,Physics Letters B563(2003)37.[13]H.O.Back et al.,JETP Letters78(2003)261.[14]H.O.Back et al.,Physics Letters B563(2003)23.[15]H.O.Back et al.,European Physical Journal C37(2004)421.[16]M.Balata et al.,hep-ex/0602027.[17]M.Balata et al.,hep-ex/0601035.[18]R.S.Raghavan et al.,Phys.Rev.Lett.80(1998)635.[19] F.Calaprice et al.,Geophys.Res.Lett.25(1998)1083.[20]T.Araki et al.,Nature436(2005)499.[21] F.Mantovani et al.,Phys.Rev.D69(2004)013001.。
数据库系统概念(第五版)Abraham Silberschatz著,CH10
Database System Concepts - 5th Edition, Aug 22, 2005.
10.2
©Silberschatz, Korth and Sudarshan
Introduction
XML: Extensible Markup Language Defined by the WWW Consortium (W3C) Derived from SGML (Standard Generalized Markup Language), but simpler to use than SGML Documents have tags giving extra information about sections of the document E.g. <title> XML </title> <slide> Introduction …</slide> Extensible, unlike HTML Users can add new tags, and separately specify how the tag should be handled for display
Chapter 10: XML
Database System Concepts
©Silberschatz, Korth and Sudarshan See for conditions on re-use
XML
Structure of XML Data XML Document Schema Querying and Transformation Application Program Interfaces to XML Storage of XML Data XML Applications
Dorado 5 快速入门
Dorado 5 快速入门富浏览器展现中间件快速创建Rich Internet Application的表现层解决方案1.前言 (4)2.简介 (5)3.STUDIO (6)3.1.使用说明 (6)3.2.工程管理 (17)3.2.1.工程管理 (17)3.2.2.系统菜单 (17)4.一个简单的DORADO应用界面 (17)4.1.视图模型简介 (17)4.2.创建DORADO应用 (20)4.2.1.新建工程 (20)4.2.2.数据连接配置 (22)4.2.3.制作dorado JSP (23)5.常用组件应用技巧 (32)5.1.自由表单(A UTO F ORM) (32)5.2.数据表格(D A TA T ABLE) (36)5.3.菜单(M ENU) (53)5.4.树(T REE) (53)5.5.下拉框(D ROP D OWN) (53)5.6.命令(C OMMAND) (53)6.视图模型 (53)6.1.视图模型的状态 (53)6.2.视图模型实现类 (55)6.3.视图模型的上下文(D ORADO C ONTEXT) (56)6.4.视图模型中的JDBC开发 (58)6.4.1.事务管理 (59)6.4.2.异常处理 (60)7.业务逻辑框架整合范例 (61)7.1.S QL D ATASET (61)7.1.1.预定义Sql编程 (62)7.1.2.实现预定义Sql编程的动态性: (63)7.1.3.运行时Sql编程 (64)7.2.存储过程 (65)7.3.J A V A 实体对象 (66)7.3.1.记录集的监听器内部实现 (66)7.3.2.系统的业务对象实现 (67)7.3.3.通过引入第三方框架管理与组织自己业务对象的基础之上实现(如加入Spring,Hibernate) (69)8.数据坞 (71)8.1.数据模块中的D A TASET (71)9.典型界面开发 (83)10.权限管理和PROFILE (83)10.1.P ROFILE使用说明 (83)10.2.P ROFILE文件的定义 (87)10.3.视图模型(V IEW M ODEL)PROFILE的指定 (87)11.文件或BLOB字段的处理 (88)12.发布 (88)12.1.基本原理 (88)12.2.发布方法 (90)12.2.1.dorado studio打包: (90)12.2.2.其他工具打包: (91)13.升级 (91)14.附录 (93)14.1.参考程序光盘说明 (93)14.2.数据库配置说明 (93)1.前言dorado是由BSTEK公司推出的面向J2EE 的新一代Web应用的开发框架，支持AJAX 机制。
数值分析第五版答案(全)
第一章 绪论1．设0x >,x 的相对误差为δ，求ln x 的误差。
解：近似值*x 的相对误差为*****r e x xe x x δ-=== 而ln x 的误差为()1ln *ln *ln **e x x x e x =-≈进而有(ln *)x εδ≈2．设x 的相对误差为2%，求n x 的相对误差。
解：设()nf x x =，则函数的条件数为'()||()p xf x C f x = 又1'()n f x nx-=, 1||n p x nx C n n-⋅∴== 又((*))(*)r p r x n C x εε≈⋅且(*)r e x 为2]((*))0.02n r x n ε∴≈3．下列各数都是经过四舍五入得到的近似数，即误差限不超过最后一位的半个单位，试指出它们是几位有效数字：*1 1.1021x =,*20.031x =, *3385.6x =, *456.430x =,*57 1.0.x =⨯解：*1 1.1021x =是五位有效数字； *20.031x =是二位有效数字； *3385.6x =是四位有效数字； *456.430x =是五位有效数字； *57 1.0.x =⨯是二位有效数字。
4．利用公式求下列各近似值的误差限：(1) ***124x x x ++,(2) ***123x x x ,(3) **24/x x .其中****1234,,,x x x x 均为第3题所给的数。
解： {*41*32*13*34*151()1021()1021()1021()1021()102x x x x x εεεεε-----=⨯=⨯=⨯=⨯=⨯***124***1244333(1)()()()()1111010102221.0510x x x x x x εεεε----++=++=⨯+⨯+⨯=⨯ ***123*********123231132143(2)()()()()1111.10210.031100.031385.610 1.1021385.6102220.215x x x x x x x x x x x x εεεε---=++=⨯⨯⨯+⨯⨯⨯+⨯⨯⨯≈**24****24422*4335(3)(/)()()110.0311056.430102256.43056.43010x x x x x x xεεε---+≈⨯⨯+⨯⨯=⨯=5计算球体积要使相对误差限为1，问度量半径R 时允许的相对误差限是多少 解：球体体积为343V R π=则何种函数的条件数为23'4343p R V R R C V R ππ===(*)(*)3(*)r p r r V C R R εεε∴≈=又(*)1r V ε=%1：故度量半径R 时允许的相对误差限为εε(ε∗)=13∗1%=13006．设028Y =，按递推公式1n n Y Y -=（n=1,2,…）计算到100Y 27.982≈（5位有效数字），试问计算100Y 将有多大误差解：1n n Y Y -=10099Y Y ∴=9998Y Y =9897Y Y =……10Y Y =依次代入后，有1000100Y Y =- %即1000Y Y =27.982≈, 100027.982Y Y ∴=-*310001()()(27.982)102Y Y εεε-∴=+=⨯100Y ∴的误差限为31102-⨯。
古扎拉蒂计量经济学
P2(1) Pi (1)
(
( 2) P P2( 2) 1
2）边缘分布 设（X,Y）具有 P ( X = xi , Y = yi ) = pij ，则
P ( X = xi ) = ∑ P ( X = xi , Y = yi ) = ∑ pij = pi ⋅ = pi( )（联合分布表中第 i 行各概率相加）
ϕ ( x, y ) 为在 Y＝y 条件下关于 X 的条件概率密度。 ϕY ( y ) ϕ ( x, y ) 为在 X＝x 条件下关于 Y 的条件概率密度。 ϕX ( x)
若 ϕ X ( x ) > 0 ，称 ϕ ( y | x ) = 条件分布函数为：
4
FX |Y
( x | y) = ∫
x
−∞
ϕ ( x, y ) dx ϕY ( y ) ϕ ( x, y ) dy ϕX ( x)
−∞ −∞ −∞
x
+∞
x
称为（X,Y）关于 X 的边缘分布函数。
ϕ X ( x ) = ∫ ϕ ( x, y ) dy 称为（X,Y）关于 X 的边缘概率密度。
−∞
+∞
FY ( y ) = P (Y ≤ y ) = P ( −∞ < X < +∞, Y ≤ y ) = lim F ( x, y )
x →+∞
pij pi(1)
=
P ( X = xi , Y = y j ) P ( X = xi )
称为在 X = xi 条件下关于 Y 的条件分布。 4）二元离散型随机变量的分布函数
3
F ( x, y ) = ∑ ∑ pij
xi ≤ x y j ≤ y
2、二维连续型随机变量 1）联合概率密度 如果存在非负函数 ϕ ( x, y ) ，使得（X,Y ）的分布函数 F ( x, y ) 对于任意实数 x ，y ，都有
(完整版)数值分析第五版答案(全)
第一章 绪论1．设0x >,x 的相对误差为δ，求ln x 的误差。
解：近似值*x 的相对误差为*****r e x xe x x δ-=== 而ln x 的误差为()1ln *ln *ln **e x x x e x =-≈进而有(ln *)x εδ≈2．设x 的相对误差为2%，求n x 的相对误差。
解：设()nf x x =，则函数的条件数为'()||()p xf x C f x = 又1'()n f x nx-=, 1||n p x nx C n n-⋅∴== 又((*))(*)r p r x n C x εε≈⋅且(*)r e x 为2((*))0.02n r x n ε∴≈3．下列各数都是经过四舍五入得到的近似数，即误差限不超过最后一位的半个单位，试指出它们是几位有效数字：*1 1.1021x =,*20.031x =, *3385.6x =, *456.430x =,*57 1.0.x =⨯解：*1 1.1021x =是五位有效数字； *20.031x =是二位有效数字； *3385.6x =是四位有效数字； *456.430x =是五位有效数字； *57 1.0.x =⨯是二位有效数字。
4．利用公式(2.3)求下列各近似值的误差限：(1) ***124x x x ++,(2) ***123x x x ,(3) **24/x x .其中****1234,,,x x x x 均为第3题所给的数。
解：*41*32*13*34*151()1021()1021()1021()1021()102x x x x x εεεεε-----=⨯=⨯=⨯=⨯=⨯***124***1244333(1)()()()()1111010102221.0510x x x x x x εεεε----++=++=⨯+⨯+⨯=⨯ ***123*********123231132143(2)()()()()1111.10210.031100.031385.610 1.1021385.6102220.215x x x x x x x x x x x x εεεε---=++=⨯⨯⨯+⨯⨯⨯+⨯⨯⨯≈**24****24422*4335(3)(/)()()110.0311056.430102256.43056.43010x x x x x x xεεε---+≈⨯⨯+⨯⨯=⨯=5计算球体积要使相对误差限为1，问度量半径R 时允许的相对误差限是多少？ 解：球体体积为343V R π=则何种函数的条件数为23'4343p R V R R C V R ππ===(*)(*)3(*)r p r r V C R R εεε∴≈=又(*)1r V ε=%1故度量半径R 时允许的相对误差限为εr (V ∗)=13∗1%=13006．设028Y =，按递推公式1n n Y Y -= （n=1,2,…）计算到100Y 27.982≈（5位有效数字），试问计算100Y 将有多大误差？解：1n n Y Y -=-10099Y Y ∴=9998Y Y =9897Y Y =……10Y Y =依次代入后，有1000100Y Y =-即1000Y Y =27.982≈, 100027.982Y Y ∴=-*310001()()(27.982)102Y Y εεε-∴=+=⨯100Y ∴的误差限为31102-⨯。
古扎拉蒂《计量经济学基础》第9章
虚拟变量数量的设置规则
1．若定性因素具有m（m≥2）个相互排斥
属性(或几个水平)，当回归模型有截距项时， 只能引入m-1个虚拟变量；
2．当回归模型无截距项时，则可引入m个 虚拟变量；否则，就会陷入“虚拟变量陷阱”。 （为什么？）
若对两个相互排斥的属性 “性别属性”， 仍然引入m=2个虚拟变量，则有
E Yi | Di = 0 = 0
Yi （ 0 1） i 女 性
Yi 0 i
男性
（2）一个定性解释变量（两种属性）和一
个定量解释变量的情形
模型形式 Yi = f(Di，Xi )+μi 0 1Di
例如：Yi =0 1Di +Xi +μi
其中：Y－支出；X－收入;
Di
1 0
女性 支出
例：比较改革开放前、后我国居民（平 均）“储蓄－收入”总量关系是否发生了变 化？模型的设定形式为：
Yt 1 2 Dt 1X t 2 (Dt X t ) ut
其中 : Yt为储蓄总额，X t为收入总额。
D
1
0
改革开放后 改革开放前
回归方程：
改革开放后 EYt | Xt , D 1 （1 2）（1 2）Xt 改革开放前 EYt | Xt , D 0 1 1Xt
夏季、农村居民
E Yi | X i ,D1 = 1, D2 = 0 =（ 0 + 1）+ X i
冬季、城市居民
E Yi | X i , D1 0, D2 1 (0 2 )＋ X i
冬季、农村居民
E Yi | X i , D1 0, D2 0 0 X i
Y
D1 1,D2 1
基准：四季度
（4）两个定性解释变量（均为两种属性） 和一个定量解释变量的情形
PHOENICS中文教程
目录 ..................................................................................................................................................... 1 1 简介.............................................................................................................................................. 5 1.1 1.2 1.3 FLAIR 是什么 ? .................................................................................................................. 5 FLAIR 可以做些什么？ ...................................................................................................... 8 FLAIR 组成部分以及 PHOENICS 的关系 ........................................................................ 9 FLAIR 模块 .................................................................................................................. 9 FLAIR 与 PHOENICS 的关系..................................................................................... 9 用户接口功能 (In-Form) ............................................................................................. 9 自动收敛控制 ............................................................................................................. 10 PARSOL 技术............................................................................................................ 10 嵌套网格 .................................................................................................................... 11 LVEL 湍流模型 ......................................................................................................... 12 IMMERSOL 辐射模型 .............................................................................................. 12
智慧树答案计量经济学(山东联盟)知到课后答案章节测试2022年
第一章1.计量经济学是一门学科。
答案:经济学2.计量经济学的创始人是：答案:弗里希3.计量经济学主要由、和三门学科的内容有机结合而成。
答案:经济学;数学;统计学4.国际计量经济学会成立标志着计量经济学作为一门独立学科地位的正式确立。
答案:对5.计量经济学具有综合性、交叉性和边缘性的特点。
答案:对6.计量经济模型一般由、、、等四个要素构成。
答案:经济变量、参数、随机误差项和方程的形式7.对计量经济模型进行检验的三个常用准则是：答案:经济意义准则、统计检验准则和计量检验准则8.判断模型参数估计量的符号、大小、相互之间关系的合理性属于经济意义准则。
答案:对9.在同一时间不同统计单位的相同统计指标组成的数据列是横截面数据。
答案:对10.建立计量经济模型的一般步骤是：答案:模型设定，参数估计，模型检验，模型应用第二章1.进行回归分析时，当x取各种值时，y的条件均值的轨迹接近一条直线，该直线称为y对x的回归直线。
答案:对2.将总体被解释变量y的条件均值表现为解释变量x的函数，这个函数称为总体回归函数。
答案:对3.计量经济模型中引进随机扰动项的主要原因有：答案:经济现象的内在随机性;作为未知影响因素的代表;作为无法取得数据的已知因素的代表;可能存在模型的设定误差和变量的观测误差;作为众多细小影响因素的综合代表4.答案:可解释分量;系统分量5.回归分析中，最小二乘法的准则是指：答案:;6.当回归模型满足假定SLR.1～SLR.3时, OLSE具有无偏性，如果还满足SLR.4，则OLSE具有有效性。
答案:对7.利用一元回归模型对被解释变量平均值E(yf|xf )进行区间预测的上界是：答案:;8.一元线性回归模型对回归系数显著性进行t检验，构造的t统计量为：答案:;第三章1.k元线性回归模型参数βj的置信度为1-α的置信区间为，n为样本个数。
答案:;2.多元回归模型的矩阵形式是：答案:;3.要使模型能够得出参数估计量，所要求的最小样本容量为n≥k+1，其中k为解释变量个数。
《数据库系统概论》王珊-萨师喧版(第五版)课后习题答案
第二章关系数据库1 ．试述关系模型的三个组成部分。
答：关系模型由关系数据结构、关系操作集合和关系完整性约束三部分组成。
2 ．试述关系数据语言的特点和分类。
答：关系数据语言可以分为三类：关系代数语言。
关系演算语言：元组关系演算语言和域关系演算语言。
SQL：具有关系代数和关系演算双重特点的语言。
这些关系数据语言的共同特点是，语言具有完备的表达能力，是非过程化的集合操作语言，功能强，能够嵌入高级语言中使用。
3 （略）4 ．5 . 述关系模型的完整性规则。
在参照完整性中，为什么外部码属性的值也可以为空？什么情况下才可以为空？答：实体完整性规则是指若属性A是基本关系R的主属性，则属性A不能取空值。
若属性(或属性组)F是基本关系R的外码，它与基本关系S的主码Ks相对应(基本关系R和S不一定是不同的关系)，则对于R中每个元组在F上的值必须为：或者取空值(F的每个属性值均为空值)；或者等于S中某个元组的主码值。
即属性F本身不是主属性，则可以取空值，否则不能取空值。
6．设有一个SPJ数据库，包括S，P，J，SPJ四个关系模式：1）求供应工程J1零件的供应商号码SNO：πSno(σJno=‘J1’（SPJ）)2）求供应工程J1零件P1的供应商号码SNO：πSno(σJno=‘J1’∧Pno=‘P1‘(SPJ))3）求供应工程J1零件为红色的供应商号码SNO：πSno(πSno,,Pno（σJno=‘J1‘(SPJ))∞πPno（σCOLOR=’红‘（P）))4）求没有使用天津供应商生产的红色零件的工程号JNO：πJno(SPJ)-πJNO（σcity=‘天津’∧Color=‘红‘（S∞SPJ∞P）5）求至少用了供应商S1所供应的全部零件的工程号JNO：πJno，Pno(SPJ)÷πPno（σSno=‘S1‘（SPJ））7. 试述等值连接与自然连接的区别和联系。
答：连接运算符是“=”的连接运算称为等值连接。