2019.10.17 Wang Junyi _SPSS

Spss input data the following precautions

 

1. The character data

 

In spss, the case-sensitive character data only, uppercase and lowercase m m is not the same.

 

The number (1) is provided in the variable characters can be input View "width", and character. When "column" value, only the width of the character "column" set "width" of the variable is greater than the value set in view, but other characters remain. Generally greater than the width of the column value

 

(2) character data may be provided a paper label. As the column, two values ​​"sex" variable to m, f, their performance values ​​were female male

 

(3) If the label is English only, you can click the Spelling spell check to check the label refers to filled out in English

 

2. missing values

 

If there is missing data, there are SPSS for character data and numerical data different approach, numerical data for the missing values ​​by default. ""; For a string line data system default value is empty, an empty string if meaningful , you need to define the missing values ​​in the variables view

 

Data source name (title name)

 

Description (description)

 

TCP / ID (address) server: localhost port (port): 3306

 

user (user name): root

 

password (password): root

 

Open Database Connectivity is central to understanding between heterogeneous databases, data sharing produced, has become a major part of WOSA (window open system) and is based on a standard database access interface window environment, Od pc provide access to heterogeneous databases unified interface. Allows the application to take the standard sol data have different data access management data odbc application directly manipulate db dispense with the changed DB changed by oDbc Db can access files on various types of computer. Access and Excel tables and even ascll data files such non-data objects.

 

Database variable naming only in English (first letter capitalized) (if not English, Pinyin or Hanyu Pinyin initials)

 

2.3. Edit and output of data

 

File - Open - data

 

Find simplitd Chinese file into the samples under variable method in SPSS installation position

 

  Will be inserted in front of a variable in the data of the upper left corner of the target column view an insert a variable

 

Delete variables:

 

Right-click the column in the data view - Cleanup

 

Right-click again on the target data view - Clear

 

Insert Case:

 

Right-click to view on the column - insertion Case

 

Delete Case:

 

  Right-click the row in Data View - clear

 

  Withdraw the case

 

  Redo button

 

Save Output

 

   Save as a file

 

Save the file name Type: You can choose a variety of

 

Variables: you can choose to save content

 

3.1 Data sorting.

 

When the statistical analysis, the initial variables may not meet the requirements of statistical analysis, the user needs to be in line with the target data collation classification

 

Sort Cases

 

  A data sorting case

 

  Sort by

 

  Sort

 

Variable ordering

 

   Data - variable ordering

 

   Variable View column

 

   Order

 

3.2 Data transpose

 

Row the row data into columns Column - transpose

 

Variable becomes, observations. Name variable becomes the variable name, you can be a part of the variable go, but data is lost and can not undo

 

Database variable naming only English capitalized (with Pinyin and English is not the first Chinese phonetic alphabet.)

 

For more than two different cases, merge data file into Add Variable

 

1. Add Cases: Select Data - Merge Files - Add Cases

 

2. Add variables: Select Data - Merge Files - Add Variable

 

First, merge the two data files

 

Key variables (marked with matching variable and when two different files of the data set may sort order may specify the position of the time variable key, key variables need to be a key variable in accordance with the data set sorted order, if not in ascending order.)

 

For large sources of data may need to be limited to a smaller number of cases of a representative sample, can significantly reduce the time required to run its program, the interface limits retrieved cases.

 

Reading two or more database tables, ways must specify a correlation between the database associated in most cases can be selected in the default, this type of association, to ensure complete matching conditions associated records will be imported SPSS, if external left side, the left side of the double arrow and timely data table records in the data table on the right side will not match the SPSS elected data set,

 

spss merge the two files transversely, leading to combined error

 

Appendix: ODBC data source for the database file

Guess you like

Origin www.cnblogs.com/wangjunyi/p/11694389.html