《应用商务统计学讲义第一章 中英文对照ppt课件.ppt》由会员分享，可在线阅读，更多相关《应用商务统计学讲义第一章 中英文对照ppt课件.ppt（30页珍藏版）》请在三一办公上搜索。
1、Ch0:First Things First and Ch1:Defining and collecting data Learning Objectives,What is Statistics?什么是统计学Basic concepts in Statistics 统计学中的基本概念Data,variable,population,sample,parameter,statistic,etc数据、变量、人口样本统计量、参数，等等Data/variable types 数据/变量类型How to collect data如何收集数据The different ways to collect a
2、 sample收集样本的不同方法The types of survey errors调查误差的类型,1,What is Statistics?,Statistics refers to methods that help transform data into useful information for decision makers.统计指的是帮助决策者将数据转化为有用信息的方法。Statistics is a way of thinking that can lead to better decisions.统计是一种可以带来更好决策的思维方式。,2,Why Statistics?,In
3、 todays digital world ever increasing amounts of data are gathered,stored,reported on,and available for further study.Business information systems在当今的数字世界中，越来越多的数据被收集、存储、报告，并可供进一步研究。-商业信息系统You hear the word data everywhere.你到处都听到“数据”这个词。Data are facts about the world and are constantly reported by a
4、n ever increasing number of sources.数据是关于世界的事实，并且不断地被越来越多的来源所报道。,3,To Properly Apply Statistics You Should Follow A Framework To Minimize Possible Errors为了正确地应用统计数据，您应该遵循一个框架，以尽量减少可能出现的错误。,In this course we will use DCOVADefine the data you want to study in order to solve a problem or meet an object
5、iveCollect the data from appropriate sourcesOrganize the data collected by developing tablesVisualize the data by developing chartsAnalyze the data collected to reach conclusions and present results在这个过程中我们将使用DCOVA-定义你想研究的数据，以解决问题或达到一个目标。-从适当的来源收集数据-组织开发表收集的数据-通过开发图表来可视化数据-分析收集到的数据，得出结论并给出结果,4,Using
6、 The DCOVA Framework Helps You To Apply Statistics To:使用DCOVA框架帮助你申请统计：,Summarize&visualize business data总结和可视化业务数据Reach conclusions from those data从这些数据中得出结论Make reliable forecasts about business activities对业务活动作出可靠的预测Improve business processes改进业务流程,5,Business Analytics:The Changing Face Of Statis
7、tics商业分析：统计数据的变化,Use information systems methods to collect and process data sets of all sizes,including very large data sets that would otherwise be hard to examine efficiently.使用信息系统方法收集和处理各种大小的数据集，包括非常大的数据集，否则很难有效地检查这些数据集。Use statistical methods to analyze and explore data to uncover unforeseen r
8、elationships.使用统计方法分析和探索数据，以发现不可预见的关系。Use management science methods to develop optimization models that impact an organizations strategy,planning,and operations.使用管理科学方法开发影响组织战略、规划和运作的优化模型。The growth of“Big Data”spurs the use of business analytics“大数据”的增长刺激了商业分析的应用“Big data”or very large data sets
9、are arising because of the automatic collection of high volumes of data at very fast rates.“大数据”或非常大的数据集的出现，是因为以非常快的速率自动收集大量数据。,6,Data Vocabulary数据的词汇,Data:measurements that are collected,recorded,and summarized for presentation,analysis,and interpretation 数据：收集、记录和总结用于陈述、分析和解释的测量Variable:characteri
10、stic of the elements whose values may differ from element to element and is of interest to the data collector变量：元素的特征，其值可能不同于元素到元素，并且对数据收集器感兴趣。Element:an entity or object on which data are collected.Also called case,subject,individual,item-元素：收集数据的实体或对象。也称案件、主体、个人、项目Observation:measurement of a vari
11、able on a single element-观察：单个元素上变量的测量,7,Data Vocabulary,8,Data Vocabulary,Types of Variables变量类型Qualitative:labels or names for a characteristic(position,gender,name)-定性：特征的标签或名称（位置，性别，名字）Quantitative:measurement of amount or quantity-定量：量或量的测量Discrete(counting)(#of family numbers):limited values i
12、n a range离散（计数）（#家属）：在一个有限的范围值Continuous variable(measuring)(age,income):any value in a range连续变量（测量）（年龄，收入）：某一范围内的任何值,9,Data Vocabulary,Words?,Integers?,10,定性的（名义的，明确的,变量类型,定量（数值）,分离的，不相关联的,连续的,整数？,语言?,No order ordered/rankede.g.Eye color Rating of a professor,Absolute zeroDifference is meaningful
13、Ratio is also meaningfulSalary,Levels/Scales of measurement,No true zero Difference is meaningfulRatio is not meaningfulTemperature,Four Levels of Measurement,11,测量的四个层次,信息量,水平/测量尺度,1。标称等级2。顺序层次,3.区间水平4.率水平,Four Levels of Measurement,Qualitative data:Nominal and Ordinal levels Nominal scale/level:Va
14、lues represent category or group membership of elements.Only show difference).No order implied.定性数据：名词和序数级-名义量表/级别：值表示元素的类别或组成员关系。仅表现出差异）。无订单暗示。Ordinal scale/level:values convey less than,equal to,and greater than relationships among elements,i.e.the relative ranks of the elements with respect to th
15、eir values for the variable in question(one better than another?)(ratings of customer service:good,average,poor)-序数量/等级：值传递小于，等于，大于元素之间的关系，即相对于变量的值的元素的相对秩（一个比另一个更好？）（客户服务等级：好的，一般的，差的）,12,Four Levels of Measurement,Quantitative data:Interval and Ratio ScalesInterval scale/level:the difference between
16、 measurements is a meaningful quantity but does not involve a true zero pointFahrenheit temperature:difference between 68-70 is the same as 70-72.0 degree does not mean no temperature.定量数据：区间和比率标度-间隔刻度/水平：测量之间的差异是有意义的数量，但不包括真正的零点。华氏温度之间的差别是：68 70-72相同。0度并不意味着没有温度。Ratio scale:values can take on a nat
17、ural or absolute zero and ratio is meaningfulSalary:0 means no income.40000 is twice as much as 20000.80000 is twice as much as 40000.比例标尺：值可以是自然的或绝对的零，比率是有意义的。工资：0表示没有收入。40000是20000的两倍。80000是40000的两倍。,13,Data collection methods数据收集方法,Data distributed by an organization or an individual由组织或个人分发的数据A
18、designed experiment设计的实验A survey/An observational study调查/观察性研究Data collected by ongoing business activities正在进行的业务活动收集的数据,14,Sources of Data数据来源,Primary Sources:The data collector is the one using the data for analysis主要来源：数据采集器是一个用数据分析Data from a political survey从政治的调查数据Data collected from an expe
19、riment试验数据采集Observed data观测数据Secondary Sources:The person performing data analysis is not the data collector次要来源：进行数据分析的人不是数据采集器Analyzing census data分析人口普查数据Examining data from print journals or data published on the internet.检查数据从印刷刊物或在互联网上公布的数据,15,More Definitions更多的定义,Population:entire set of obj
20、ects of interest人口：一整套感兴趣的对象Sample:a part of the population of interest样本：感兴趣人群中的一部分Parameter(population characteristics)vs.Sample Statistic(sample characteristics)参数（人口特征）与样本统计（样本特征）In practice,we usually collect a sample to study the characteristics of a population在实践中，我们通常收集样本来研究人口的特征。,16,Process
21、 of Statistical Inference/inferential Stats统计推断/推断统计过程,A study shows 研究表明.,17,人口包括所有的利益因素。,一个项目的样本被接受和检查。,统计被用作人口特征的估计,示例数据提供描述性统计。,Sampling,ExpenseSpeedDestructive nature of data collectionInaccessibility of some elementsRandom/Probability Sampling Methods Other approaches,Why sample?How to sample?
22、,18,抽样,为什么抽样？,怎么抽样,费用速度-数据收集的破坏性交通不便的一些元素,-随机/概率抽样方法其他方法,How to sample:Probability Sample,In a probability sample,items in the sample are chosen on the basis of known probabilities.,Probability Samples,Simple Random,Systematic,Stratified,Cluster,19,如何抽样：概率抽样,在概率抽样中，根据已知概率选择样本中的项。,概率抽样,简单的随机,有系统的，有规则
23、的,集群,分层,Simple Random Sample,Number each unit from 1 to N每个单元从1到nUse a random number generator to select n distinct numbers between 1 and N,inclusivelyAvailable toolsEasier to perform for small populationsCumbersome for large populations,Random number generatorTable of random numbersExcel functions:
24、Randbetween(min,max)Add-in:SamplingWith replacement or without rep.,20,简单随机样本,使用随机数发生器选择n个不同的数字之间的1和N，含,可用的工具,随机数发生器随机数表Excel函数：randbetween（min，max）加入：抽样更换或不带代表,对小群体来说更容易执行,庞大人口的累赘,Systematic Sampling,Population elements are an ordered sequenceFirst sample element is selected randomly from the first
25、 k population elementsThen,sample elements are selected at a constant interval,k,from the ordered sequence frame,21,系统抽样,人口要素是一个有序序列,第一个样本元素是从第一k个人口元素中随机选取的。,然后，样品的元素是在一个恒定的间隔，K的选择，从有序的序列帧,试样量，样本大小,群体大小,选择间隔的大小,Systematic Sampling,N=20 n=5k=N/n=4,First,find a random starting point Then items from ev
26、ery 4 invoices,Invoice 0618Invoice 0620Invoice 0721Invoice 0802Invoice 0808Invoice 0906Invoice 1002Invoice 1012Invoice 1014 Invoice 1113,22,系统抽样,发票,首先，找到一个随机出发点,每4张发票的项目,Stratified Random Sample,What if our population can be clearly divided into subgroups based on some characteristics and we want ou
27、r sample to include all subgroups?Population is divided into nonoverlapping subpopulations called strataA random sample is selected from each stratumPotential for reducing sampling errorProportionate-the percentage of the sample taken from each stratum is proportionate to the percentage that each st
28、ratum is within the population,23,分层随机样本,如果我们的人口可以根据一些特征明确地划分为亚组，我们希望我们的样本包括所有子组，该怎么办？,种群分成互不重叠的亚群，称为地层,从每个阶层挑选一个随机样本。,减少抽样误差的可能性,比例-从每个阶层抽取的样本比例与每个阶层在人口中所占的百分比成比例,Stratified Random Sample,Suppose we want to study the advertising expenditures for the 352 largest companies in the United States.假设我们想研
29、究美国352家最大公司的广告支出。To make sure that a sample of 50 companies is a fair representation of the 352 companies,the companies are grouped on percent return on equity and a sample proportional to the relative size of the group is randomly selected.,24,分层随机样本,为了确保50家公司的样本是这352家公司的公平代表，公司按股本回报率分组，而与该集团相对规模成比
30、例的样本是随机的。,Cluster Sampling(two-stage sampling),Population is divided into non-overlapping clusters or areas人口分为不重叠的群体或地区。Each cluster is a miniature,or microcosm,of the populationA subset of the clusters is selected randomly for the populationSimple random sampling from each cluster selected.,25,（两阶
31、段抽样）,分群组抽象法,每一个集群都是人口的缩影或缩影。,集群的一个子集是随机选择的。,选择每个群集的简单随机抽样。,Nonprobability Sample,In a nonprobability sample,items included are chosen without regard to their probability of occurrence.In convenience sampling,items are selected based only on the fact that they are easy,inexpensive,or convenient to sa
32、mple.In a judgment sample,you get the opinions of pre-selected experts in the subject matter.Snowball sampling.,26,非概率抽样,在非概率抽样，项目包括有选择不考虑其发生的概率。,-在便利抽样中，仅根据容易、便宜或便于取样的事实选择项目。,在一个判断样本中，你可以得到预先选定的专家在主题问题上的意见。,滚雪球抽样,Types of Survey Errors,Coverage error or selection bias覆盖误差或选择偏移Exists if some groups
33、are not included in the pool and have no chance of being selectedNonresponse error or bias无回答误差或偏差People who do not respond may be different from those who do respondSampling errorVariation from sample to sample will always existMeasurement errorDue to weaknesses in question design,respondent error,
34、and interviewers effects on the respondent,27,测量误差类型,如果某些组不包含在池中，并且没有被选中的机会，则存在,没有回应的人可能不同于那些做出反应的人,抽样误差,从样品到样品的变化总是存在的,测量误差,由于问题设计的弱点，回答错误，以及面试官对被告的影响。,Descriptive statistics vs Inferential Statistics,Descriptive statistics描述统计（学）Tabular,graphical,and numerical methods used to summarize one or more
35、 characteristics of a set of data.用于概括一组数据的一个或多个特征的表格、图形和数值方法。Transform data into useful information将数据转换为有用的信息Inferential Statistics推论统计A decision,estimate,prediction,or generalization about a population,based on a sample.基于样本的关于人口的决定、估计、预测或概括。,28,描述性统计与推断统计学,Chapters 0 and 1 review第0章和第1章回顾,Basic
36、concepts:Statistics,data,variable,object,observation,population,sample,parameter,and statistic基本概念：统计学、数据、变量、对象、观察、人口、样本、参数和统计Descriptive and inferential statistics描述性统计和推断统计Two types of variables:qualitative and quantitative(discrete and continuous)两种类型的变量：定性和定量（离散和连续）Four levels/scales of measurem
37、ent:nominal,ordinal,interval,ratio测量的四个等级/等级：名词、序数、音程、比率How to collect data如何收集数据The different ways to collect a sample收集样本的不同方法The types of survey errors调查误差的类型,29,Tools 工具,Use Excel for assignments and exams用excel做作业和考试Resources资源Excel guides after each chapter.每个章节都有excel指南。Appendix B,C and D pro
38、vide guidelines for using Excel as well including how to download the data sets for the examples in the textbook.附录B、C和D提供了使用excel的指导原则，包括如何下载教材中示例的数据集。Download data,Excel examples and other online resources下载数据、Excel示例和其他在线资源 choose this bookExcel 2007,2010,2013,2016 and office 365 Other tools:Excel add-in PHStat2,SPSS,SAS,Minitab,Matlab etcExcel添加phstat2，SPSS，SAS，Minitab、MATLAB等,30,
