解放軍文職招聘考試Statistics-解放軍文職人員招聘-軍隊文職考試-紅師教育
發(fā)布時間：2017-12-20 21:59:36StatisticsThere were two widely divergent influences on the early development ofstatistical methods. Statistics had a mother who was dedicated to keepingorderly records of governmental units (state and statistics come from thesame Latin root status) and a gentlemanly gambling father who relied onmathematics to increase his skill at playing the odds in games of chance.The influence of the mother on the offspring, statistics, is representedby counting, measuring, describing, tabulating, ordering, and thetaking of censuses -- all of which led to modern descriptivestatistics. From the influence of the father came modern inferentialstatistics, which is based squarely on theories of probability.Descriptive statistics involves tabulating, depicting and describingcollections of data. These data may be quantitative such as measures ofheight, intelligence or grade level -- variables that are characterized byan underlying continuum -- or the data may represent qualitative variables,such as sex, college major or personality type. Large masses of data mustgenerally undergo a process of summarization or reduction before they arecomprehensible. Descriptive statistics is a tool for describing orsummarizing or reducing to comprehensible form the properties of anotherwise unwieldy mass of data.Inferential statistics is a formalized body of methods for solving anotherclass of problems that present great difficulties for the unaidedhuman mind. This general class of problems characteristicallyinvolve attempts to make predictions using a sample ofobservations. For example, a school superintendent wishes to determine theproportion of children in a large school system who come to school withoutbreakfast, have been vaccinated for flu, or whatever. Having a littleknowledge of statistics, the superintendent would know that it isunnecessary and inefficient to question each child: the proportion for theentire district could be estimated fairlyaccurately from a sample of as few as 100 children. Thus, the purpose ofinferential statistics is to predict or estimate characteristics of apopulation from a knowledge of the characteristics of only a sample of thepopulation.統(tǒng)計學統(tǒng)計方法的早期發(fā)展受到兩種截然不同的影響。 統(tǒng)計學有一個 母親 ，她致力于井井有條地記錄政府機構的文件(國家和統(tǒng)計學這兩個詞源于同一個拉丁語詞根，status)，還有一個有紳士般的賭博 父親 ，他依靠數(shù)學來提高賭技，以便在幾率的游戲中取勝。 母親 對其子女統(tǒng)計學的影響表現(xiàn)在計數(shù)、測量、描述、制表、歸類和人口普查。 所有這些導致了 現(xiàn)代描述統(tǒng)計學的誕生。由于 父親 的影響則產生了完全基于概率論原理的現(xiàn)代推理統(tǒng)計 學。 描述統(tǒng)計學涉及對所收集數(shù)據的制表、制圖和描述。 這些數(shù)據可以是數(shù)量性的數(shù)據，如高度、智商、或者是層級性的數(shù)據--具有連續(xù)性的變量--或數(shù)據也可以代表性質變量，如 性別、大學專業(yè)或性格類型等等。數(shù)量龐大的數(shù)據通常必須經過概括或刪減的程序才能為 人所理解。 描述統(tǒng)計學就是這樣一個工具，它對極其龐雜的數(shù)據進行描述、概括或刪減，使其變成能為人理解的東西。 推理統(tǒng)計學是一套已定形了的方法體系，它解決的是光憑人 腦極難解決的另一類問題。這類問題的顯著特點是試圖通過取樣調查來作出預測。 例如， 有一位教育督察想知道在一個龐大的學校系統(tǒng)中，不吃早飯就上學的學生、已經做過防感冒免疫的學生，或其它任何類型的學生占多大比例。 若具備一些統(tǒng)計學的知識，這位督察應 明白，詢問每個孩子是沒有必要而且沒有效率的，只要用 100個孩子為樣本，他就可以相當 精確地得出這些孩子占整個學區(qū)的比例了。 因此，推理統(tǒng)計學的目的就是通過了解一個群體中一些樣本的特性，從而對整個群體的特性進行推測和估算。
