Data Analysis Concept of data analysis

Data analysis refers to the use of appropriate statistical methods to analyze a large amount of first-hand and second-hand information collected in order to Strive to maximize the development of data functions and bring into play the role of data. It is the process of conducting detailed research and summary of data in order to extract useful information and form conclusions.

Data is also called observation value, which is an experiment The results of measurements, observations, surveys, etc. are often given in the form of quantities.

Data analysis is closely related to data mining, but data mining tends to focus on larger data sets and less on Inference, often using data originally collected for a different purpose. The purpose and significance of data analysis

The purpose of data analysis is to extract information hidden in a large amount of seemingly disorganized data. Concentrate, extract and refine to find out the inherent laws of the object under study.

In practice, data analysis can help people make judgments so that appropriate actions can be taken. Data analysis is the purposeful collection of data by organizations. , the process of analyzing data and turning it into information. This process is the support process of the quality management system. The data analysis process needs to be appropriately applied throughout the entire life cycle of the product, including from market research to after-sales service and final disposal. To improve effectiveness. For example, J. Kepler found out the laws of planetary motion by analyzing the observation data of planetary angular positions. Another example is that the leader of a company needs to conduct market research and analyze the data obtained to determine market trends and formulate policies. Appropriate production and sales plans. Therefore, data analysis has a very wide range of applications. Functions of data analysis

Data analysis mainly includes the following functions:

1. Simple mathematical operations ( Simple Math)

2. Statistics

3. Fast Fourier Transform (FFT)

4. Smoothing and Filtering

5. Baseline and Peak Analysis (Baseline and Peak Analysis)

Types of data analysis

In the field of statistics, some people divide data analysis into description

Exploratory data analysis: refers to a method of analyzing data in order to form a worthy hypothesis test. It is a supplement to traditional statistical hypothesis testing methods. This method was developed by the famous American statistician John T. Named after John Tukey.

Qualitative data analysis: also known as "qualitative data analysis", "qualitative research" or "qualitative research data analysis", refers to the analysis of words, photos, observations, etc. Analysis of non-numeric data (or data) such as this.

Data analysis steps

Data analysis has a very wide range of applications. Typical data analysis may include the following three Steps:

1. Exploratory data analysis. When the data is first obtained, it may be messy and no patterns can be seen. Calculate certain characteristics by drawing, making tables, and fitting various forms of equations. Use quantitative and other means to explore possible forms of regularity, that is, in what direction and in what way to find and reveal the regularity hidden in the data.

2. Model selection analysis, in exploratory analysis One or several possible models are proposed on the basis of the model, and then a certain model is selected through further analysis.

3. Inferential analysis, usually using mathematical statistics methods to determine the reliability and reliability of the model or estimate Make inferences based on the degree of accuracy.

Data analysis process implementation

The main activities of the data analysis process consist of identifying information needs, collecting data, analyzing data, evaluating and improving the effectiveness of data analysis.

1. Identifying information needs

Identifying information needs is the first condition to ensure the effectiveness of the data analysis process. It can provide clear goals for collecting and analyzing data. Identifying information needs is the key to management Managers’ responsibilities should be based on the needs of decision-making and process control.

Information needs. As far as process control is concerned, managers should identify the needs and use the information to support the review of process inputs, process outputs, rationality of resource allocation, optimization plans for process activities, and discovery of abnormal process variations. 2. Collect data< /p>

Purposeful collection of data is the basis for ensuring the effectiveness of the data analysis process. The organization needs to plan the content, channels, and methods of collecting data. When planning, the following should be considered:

① Will identify Transform the needs into specific requirements. For example, when evaluating a supplier, the data that need to be collected may include its process capabilities, measurement system uncertainty and other related data;

② Make it clear who is responsible for where and when, Through which channels and methods to collect data;

③ The record form should be easy to use;

④ Take effective measures to prevent data loss and false data from interfering with the system.

3. Analyzing data

Analyzing data is to process, organize and analyze the collected data into information. The commonly used methods are:

Seven old tools , that is, Pareto diagram, cause-and-effect diagram, hierarchical method, questionnaire, walk chart, histogram, control chart;

The new seven tools are correlation diagram, system diagram, matrix diagram, KJ method, and plan Review technology, PDPC method, matrix data chart;

IV. Improvement of data analysis process

Data analysis is the foundation of the quality management system. The managers of the organization should, when appropriate, pass Analyze the following issues and evaluate their effectiveness:

① Whether the information provided for decision-making is sufficient and credible, and whether there are problems in decision-making errors due to insufficient information, inaccurate information, and lag;

② Whether the role of information in continuously improving quality management systems, processes, and products is consistent with expectations, and whether data analysis is effectively used in the product realization process;

③ Whether the purpose of collecting data is clear, Whether the collected data is true and sufficient, and whether the information channels are smooth;

④ Whether the data analysis method is reasonable and whether the risks are controlled within an acceptable range;

⑤ The resources required for data analysis Is it protected?