The general name of the digital data reflecting the national economy and social phenomena obtained in the process of statistical work activities and other related data
Statistical data is a general term for the digital data obtained in the process of statistical work to reflect the national economy and social phenomena, as well as other related data.Statistics are the results of measuring phenomena.For example, the measurement of the total amount of economic activities can getgross domestic product(GDP) data;The measurement of the level of stock price change can be obtainedstock market indexData;The measurement of population gender can obtain such data as men or women.The following describes the classification of statistical data from different perspectives.As a product of statistical workday, the quality of statistical data is "in line with the standard" from the perspective of statistical work process, which should accurately reflect the objective reality.[1]
Statistical data refers to aGeographical regionData on the characteristics, scale, structure, level and other indicators of natural economic elements.It is the basic data for qualitative, positioning and quantitative statistical analysis.For example, we usually call it statistical yearbook.
data classification
Announce
edit
1. Statistical data can be expressed in statistical tables andStatistical mapTwo.
It can be divided into:
① Partition statistics.That is, the area of the figure or the number of the same figure is used to represent the sum of all similar phenomena in the division unit;For example, one-year data from the 2008 American Community SurveysampleOverall document
② Hierarchical statistics.That isStatistical chartThe form is classified according to administrative divisions or economic divisions, and the phenomenon is represented by halo lines and halo points with different shades of color or densityRelative indicatorsDifferences;
③ Positioning statistics.withStatistical chartThe form represents the special phenomenon and change rule at a certain point.
2. Statistical data are divided intoMacroeconomic indicatorsStatistics and industry economic indicators statistics.
Common macroeconomic indicators include GDP, CPI, PPI,[2]PMIAnd cash in circulation.
Industrial economic indicators such as the prosperity analysis of coal industry and oil industry.
data type
Announce
edit
The statistical data is based onMetrological scaleDifferent types of statistical data will be obtained by using different measurement scales for the measurement results of things.From the results of the above four measurement scales, statistical data can be divided into the following four types:
oneCategorical data——It is characterized by category, but does not distinguish the order. It is formed by the measurement of classification scale.
threeDistance data——It is expressed as a numerical value and can be added or subtractedinterval scaleFormed by measurement.
fourConstant ratio data——It is numerical value, which can be added, subtracted, multiplied and divided. It is formed by constant scale metrology.
The first two types of data describe the quality characteristics of things, which cannot be represented by data. Their results are both categories, also known asQualitative dataorQuality data（Oualitative data）；The latter two types of data show the quantitative characteristics of the phenomenon, which can be expressed numerically, so they are also calledQuantitative dataorQuantity data（Quantitative data）。Since the distance scale and the ratio scale belong to the same measurement level, the latter two types of data can be regarded as the same type of data, collectively referred to as quantitative data orNumerical data。
It is very important to distinguish between the level of measurement and the type of data, because different statistical methods will be used to process and analyze different types of data.For example, yesCategorical data, usually calculate the frequency or frequency of each group, and calculate the sum of its modesHeterodox ratio, proceed[3]Contingency tableAnalysis andX2 inspectionEtc;yesOrdering data, which can be calculatedmedianandInterquartile difference, CalculateGrade correlation coefficientIsoparametric analysis;To distance orConstant ratio dataMore statistical methods can also be used for processing, such as calculating variousstatistic, proceedparameter estimation And inspection, etc.Most of the data we deal with are quantitative data.
It should be noted here that it is applicable to low levelmeasured data Ofstatistical methodIt is also applicable to higher level measurement data, because the latter has the mathematical characteristics of the former.For example, in the description of dataConcentrated trendFor classified data, the mode is usually calculated, for sequenced data, the median is usually calculated, but for distance and ratio data, the mode and median can also be calculated.On the contrary, statistical methods suitable for high-level measurement data cannot be used for low-level measurement data, because low-level data does not have the mathematical characteristics of high-level measurement data.For example, for fixed distance and fixed ratio data, the average can be calculated, but forCategorical dataAnd sequenced data cannot be averaged.Understanding this is very useful for selecting statistical analysis methods.[4]
Data collection
Announce
edit
Statistical data mainly comes from two sources: one is from direct surveys and scientific experiments, which is the direct source of statistical data, called first-hand or direct statistical data;It is data from other people's surveys or experiments, which is an indirect source of statistical data, called secondary or indirect statistical data.
Organizational form of statistical data collection
1、general survey: The census is a one-time comprehensive survey specially organized for a specific purpose to collect comprehensive information about important national conditions, national strength and resources, and provide a basis for the government to formulate plans, guidelines and policies.
2. Sampling survey: sampling survey is the most widely used survey method in practice. It is a kind of non comprehensive survey method that randomly selects a part of unit seat samples from the population of survey objects for survey, and infers the overall quantitative characteristics according to the sample survey results.
3. Statistical report: statistical report is a survey method based on comprehensive investigation, which is arranged from top to bottom by the competent government department according to statistical laws and regulations in the form of statistical tables and administrative means, and then summarized and reported by enterprises and institutions from bottom to top to provide basic statistical data level by level
4、Key investigationKey investigation is a kind of non comprehensive investigation specially organized, which is to select individual or some key units to conduct investigation in the overall to understand the basic situation of the overall.
5、Typical survey: Typical survey is also a kind of special organizationIncomplete investigationAccording to the purpose and requirements of the investigation and research, on the basis of a comprehensive analysis of the overall situation, it consciously selects representative typical units for in-depth and detailed investigation, so as to understand the essential characteristics, causality and development and change laws of things.
Collection methods of statistical data
In the actual survey, the specific methods of collecting data mainly include interview surveyMail survey、Telephone survey, symposium, individual in-depth interview, online survey.
1. Interview investigation: interview investigation is also called sending personnel to investigate. It is an investigation method that the investigator and the investigated get the required information through face-to-face conversation.
2. Mail survey: mail survey is to sendquestionnaireIt is a survey method that is sent to the respondent, filled in by the respondent, and then sent back or sent to the designated collection point.
3. Telephone survey: telephone survey is a survey method in which investigators use telephone to communicate with interviewees in order to obtain information.The advantages of telephone survey are fast timeliness and low cost;Insufficient is that the number of investigation questions cannot be too large.
4. Colloquium: Colloquium is also calledGroup interview method, it is a method to gather a group of respondents on the survey site and let them express their opinions on the subject of the survey, so as to obtain survey data.This method is suitable for collecting the tendencies and opinions of a few people who are closely related to the research topic.
5. Individual in-depth interview: an individual in-depth interview is a special interview with only one respondent at a timeQualitative research。It is often used in motivation research to explore the interviewees' non superficial in-depth opinions.This method is most suitable for studying more confidential issues, such as personal privacy;More sensitive issues, etc.
6. Online survey: There are three methods of online survey: E-mail, interactive CATI system and Internet CGI program.
