Shulou(Shulou.com)06/01 Report--

This article shows you the application of SPSS statistics software in beer data statistics, the content is concise and easy to understand, it can definitely brighten your eyes. I hope you can get something through the detailed introduction of this article.

Application of SPSS Statistical Software in Beer data Statistics

The following example introduces the application of SPSS in beer enterprise quality data collection, statistical description, control chart drawing, orthogonal experiment result analysis and so on.

Quality management personnel in beer enterprises often need to collect and analyze data when they are engaged in beer quality management, and some data analysis work is troublesome, especially when time is tight, tasks are urgent, the amount of data is large, and the accuracy of calculation results is high. Sometimes I feel powerless. For example, the application of commonly used statistical techniques, such as control chart and process capability analysis, analysis of variance, regression analysis, data analysis of experimental design, is often prohibitive because of the complexity of calculation. The application of statistical technology is a weak link in beer quality management. some people think that the reason for this phenomenon is that the calculation workload of statistical technology or data analysis is large. The application of SPSS statistical software helps us to solve this problem. Although SPSS is not only a statistical software designed for quality management, it can help almost all data analysis and statistical analysis of quality management. It can not only greatly improve work efficiency, but also improve the accuracy of calculation results, and achieve the purpose of improving the efficiency and effectiveness of beer quality analysis.

I. brief introduction of SPSS statistical software

SPSS (Statistical Package for the Social Science, social science statistics software package) is one of the world famous statistical software analysis software. In 1968, three students from Stanford University in the United States developed the earliest SPSS statistical software system. So far, SPSS software has a growth history of more than 30 years and has about 250000 product users worldwide. They are distributed in communications, medical, banking, securities, insurance, manufacturing, commerce, market research, scientific research and education and other fields and industries. They are the most widely used statistical software in the world.

SPSS uses Windows window to expand a variety of management and analysis of data methods, using dialog boxes to show a variety of functional options, as long as master certain Windows operation skills, and understand the principle of statistical analysis, you can use the software for the enterprise quality management work service, will no longer feel annoyed for the tedious data analysis, and will experience the magic and successful fun of data analysis. If you are interested, you can also try the application of this software in other areas of enterprise management, which is likely to benefit.

The basic functions of SPSS include data management, statistical analysis, chart analysis, output management and so on. The process includes descriptive statistics, mean comparison, general linear analysis, correlation analysis, logarithmic linear model, clustering analysis, data simplification, survival analysis, time series analysis, multiple responses and other categories, each category is divided into several statistical processes. For example, regression analysis is divided into several statistical processes, such as linear regression analysis, curve analysis, Logistic regression and so on, and each process allows users to choose different methods and parameters. There is also a special drawing system in SPSS, which can draw all kinds of graphics according to the data. For quality management work, all kinds of data analysis and statistical technical problems in quality management work can be solved by using SPSS statistical software. At present, most of the users in our country use version 9.0 / 13.0.

2. Collection and simple management of beer quality data

Beer quality information data set is the data set established by SPSS for all kinds of beer quality information and data. SPSS uses beer quality information data set for statistical analysis. The collection of beer quality information data here refers to the establishment of a quality data set in the SPSS software based on the quality data obtained in the process of beer production and inspection (as shown in figure 1 below); for the information obtained which is not data, it is necessary to carry out data processing and transform it into data that can be statistically analyzed, and then establish the data set. The simple management of the established data set includes the search of data and cells, the classification and sorting of observations, the classification and summary of data files, the selection of data, and so on. How to build the quality information data set and the simple management of the data set, the operation procedure is the same as the establishment of the general data SPSS data set, you can consult the special SPSS software teaching materials.

III. Statistical description of quality data

In order to make a good statistical analysis of beer quality data, we must first make a descriptive statistical analysis of these data. The description of quality information by SPSS statistical software is mainly concentrated in the Descriptive Statistics menu, which mainly includes the establishment of quality data frequency table, general statistical description of quality data, exploratory analysis and cross statistics, and so on.

The general statistical description of quality data mainly refers to the general description statistics of continuous random variables. This function is provided by the "Frequencies …" of "Descriptive Statistics" in the "Analyze" menu of SPSS. Item to complete. For example, to count the quality of finished beer in bubble retention and turbidity within one month (SPSS analysis data use the data in figure 1 above, which only shows part of the data), you need to make a general statistical description of these data and get the required indicators (average, maximum, minimum, range, mean standard deviation, etc.), and do the following:

[step 1] Click the Frequencies command in the Descriptive Statistics item of the Analyze menu, as shown in figure 2.

[step 2] the Frequencies dialog box pops up, as shown in figure 3. Now want to seek the average value of bubble holding, turbidity, maximum and minimum, range, mean standard deviation, so select "bubble holding" and "turbidity" in the list of variables on the left side of the dialog box, click the button to add it to the Variable (s) box.

[step 3] Click the Statistics button below and the dialog box shown in figure 4 pops up. Select the items to be counted, select the average Mean in the Central Tendency box, select the maximum Maximum, minimum Minimum, range Range, mean standard deviation S.E.mean in the Dispersion box, click the Continue button to return to the Frequencies dialog box, click the OK button, and the SPSS starts calculation.

4. Drawing quality control chart

The graphic tool of SPSS is very powerful and has strong statistical analysis function. In quality data management, some graphic methods and tools are often used, such as Pareto chart, histogram, scatter chart, control chart, sequence diagram and so on. SPSS can effectively apply these graphic methods and tools to deal with quality data information, and these functions are concentrated in the Graph menu.

Control chart can help people to distinguish whether the quality problems related to the process are caused by system or accidental factors. therefore, control chart is widely used in quality management. The following is an example of how the SPSS software draws quality control charts.

Ex.: a beer product needs to add a compound enzyme per batch, at least 10ppm, but not more than 50ppm. In order to control the production process, we are prepared to use the control chart to monitor the production process. The steps are as follows:

Step 1: create a data file. It has been determined that this example applies the average-range control chart, with every 5 observations as a group (the data diagram is omitted here).

Step 2: click the "control" item in the Graph menu and pop up the "Control Charts" dialog box. Among them, "Xmuri Barther R _ (th) s" represents the control chart of mean, range and standard deviation; "Individuals Moving" represents the control chart of single value and moving range; "pforce NP" represents the rate of failure and unqualified NC drawing; and "c _ line u" represents the NC drawing of the number of defects and unit defects. Here, select "XMui Bargamer R & P s". And choose the data organization mode as "Cases are units" to represent the observation classification mode.

The third step: click the "Define" button, the pop-up "XmurBarje R Process Measurement cases Are Units" dialog box, where "Process Measurement" box is used to select process variables, that is, variables to be analyzed; "Subgroups Defined by" is used to select grouping variables; "X-Bar and range" means to draw an average-range control chart; "X-Bar and standard deviation" means to draw a mean-standard deviation control chart. Here, select the variable "weight" into "Process Measurement"; select the variable "group number" into "Subgroups Defined by"; select "X-Bar and range", that is, the average-range control chart.

Step 4: click the "Options" button to open the "XSumi Barjournal Rjournal options" dialog box, where "Number of Sigmas" indicates how many times the distance between the upper and lower control lines is the standard deviation, and fill in "3" here; "Minimum subgroup size" is the minimum sample size of each group, fill in "5" here; "Display subgroups defined by missing values" indicates the group that displays the missing value, do not select here, click "Continue". " The "Specification Limits" box in the dialog box is used to set the upper and lower guides to compare data, where you can fill in "45" and "25", respectively.

Finally, click "OK" and you can draw the required control chart.

Through this control chart, we can see the mean, range upper and lower control lines and average values, as well as the group numbers other than the 25 and 45 reference lines, and through the analysis, we can know that there is nothing abnormal in the two control charts, indicating that the production process is normal and controlled.

five。 Design experiment and regression Analysis of quality Management

Orthogonal experimental design has important applications in the process of improving product quality, developing and optimizing new processes, etc. This paper introduces the data analysis process of orthogonal experimental design by SPSS statistical software with an example.

L9 (34) orthogonal table was selected to study the effects of fermentation temperature, wort concentration and the amount of yeast inoculation on the PH of finished beer. The high-concentration wort was mixed with washing dregs water to sell juice with different concentrations, and different amounts of large-scale yeast mud were fermented at different temperatures. The selected factors and levels are shown in the following table:

Fermentation temperature (℃)

Original concentration (°P)

Number of inoculations (ten thousand / ml)

Level 1

1 (8)

1 (9.8)

1 (900)

Level 2

2 (12)

2 (11.6)

2 (1800)

Level 3

3 (18)

3 (13.4)

3 (2700)

The first step is to create a dataset file for spss. (since the author's version does not have this functional module, it will not be described here.)

The second step, the analysis process is as follows:

① Click the Analyze menu and select Linear in the Regreesion item. Item. Select the variable "data PH" into the "Dependent" box, and select the fermentation temperature, original concentration and inoculation amount of other variables into the "Independent" box.

② clicks "OK" to analyze the results.

Results discussion: regarding the PH of beer as dependent variable, fermentation temperature, yeast addition and wort concentration as independent variables, the regression analysis was carried out. According to figure 12, the regression equation was easily obtained as follows:

YQing 4.063-0.0214X1+0.03426X2+1.852X3 × 10-6

Formula: X1 fermentation temperature (℃)

X2 wort original concentration (0P)

Addition of X3-yeast (ten thousand / ml)

Y-PH of beer

As can be seen from figure 13, the significance level of the equation is α = 0.046, that is, the credibility level of the equation is 95.4% > 95%, and the regression equation is significant. Therefore, when the raw material, saccharification process, yeast strain and other factors were unchanged, when the fermentation temperature increased by 1 ℃, the PH of beer decreased by about 0.021; similarly, when the original concentration of wort increased by 10p, the PH of beer increased by about 0.034; when the amount of yeast inoculation increased by 1 million / ml, the PH of beer increased by about 0.18. These data can basically reflect the effects of fermentation temperature, wort concentration and yeast inoculation amount on beer PH.

Through the preliminary discussion on the application of SPSS in beer data statistics, it is not difficult to find that although SPSS is a general social science statistics software, it is very suitable for the processing and analysis of quality data. Beer quality workers can gradually explore the new use of SPSS in quality management, greatly improve the efficiency and effect of quality management, help managers to make optimal decisions, and maximize the quality of products and services.

The above is the application of SPSS statistics software in beer data statistics. Have you learned the knowledge or skills? If you want to learn more skills or enrich your knowledge reserve, you are welcome to follow the industry information channel.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.