IBM SPSS Statistics (ISS)

SPSS (Statistical Product and Service Solution) is a computer application used to process and analyze statistical data. The purpose of this introduction is so that we can use the basic operations of SPSS especially for the Windows operating system, besides that we can also know how to enter data and edit it.

Judging from its function, flexibility and final results, it turns out that SPSS is very helpful in solving social and non-social problems related to statistical science.

IBM SPS

"All-in-one" is an expression that refers to IBM SPSS Statistics Premium Edition, an edition designed for business purposes, but there is nothing wrong with using it for educational purposes as well.

IBM SPSS Statistics Premium Edition helps in data analysis, planning, forecasting, research, surveys, program evaluation and marketing database, with a very wide array coverage and its ability to process or display integrated statistical data. This software is special, because it is able to increase productivity significantly and help achieve superior results for both specific projects and business purposes.

General advantages:

Easy to operate (user friendly), such as pressing the operating mode on the full-down menu with dialog box interface

Excellent in displaying analysis result graphs and ease in editing graphs.

Provides syntax windows as a means of writing program instructions to solve problems such as case weighting as desired. Program instructions with a full-down menu are less efficient when compared to interactive mode and batch mode.

Provides more complete facilities so that no other text editor is needed.

Provides SPSS syntax so that it can define special terms in commands, subcommands and keywords in SPSS.

Technical advantages:

Linear model (Linear Model): provides sophisticated regression and statistical procedures. Designed to fit the inherent characteristics of data that describe complex relationships.

Nonlinear models (Nonlinear Models): help implement more sophisticated ways of data processing.

Simulation capabilities: automatically able to model many possible outcomes when input is uncertain, improving risk analysis and decision making.

Customized tables: make it easier for users to understand their own data and summarize information in different styles according to the user.

Data preparation: shows the preparation stage of an analytical process.

Data validity and missing values: increases the likelihood of receiving statistically significant results.

Categorical and numeric data (Data categories and numeric): can be used to predict outcomes and express graphical relationships.

Decision trees: make it easier to identify groups, find relationships between groups and predict future events.

Forecasting (Prediction feature): allows you to analyze historical data and predict trends faster.

Structural equation modeling (Structural equation modeling tools): allows you to build structural equation models with more accuracy than standard multivariate statistical models.

Bootstrapping: makes it easier to test the stability and accuracy of the model, so the results are reliable.

Advanced sampling assessment and testing (Advanced sampling assessment and testing): provides statistically valid conclusions by incorporating sample design into survey analysis.

Direct marketing and product decision-making tools (Tools pembuatan Kebijakan produk dan Pemasaran): help you identify the right customers and campaign models.

High-end charts and graphs (Charts dan graphs papan atas): easy way to create, share and interact with attractive visualizations and support for a wide range of smart-device platforms.

Introduction to SPSS

SPSS is the most popular statistical software, its facilities are very complete compared to other software, and it is quite easy to use.

The first step that must be done is to first install the SPSS software that will be used. In this learning using SPSS 12 Software. Currently SPSS software has experienced various additional facilities, the latest version is SPSS 17. The way to learn it is not much different from other versions of SPSS.

After the installation is done, the next step is to enter the SPSS program, the appearance is similar to Microsoft Corporation's Excel.

The first thing to do is, look for the SPSS shortcut on the desktop screen, or enter via the start button, then select All Programs, then select SPSS for Windows 12.0, as shown in the image below.

Then the image will appear as below. Then just click cancel on the existing dialog box to enter new data.

Then the dialog box will disappear, so we can continue entering data.

Note in the lower left corner, there are 2 sheets (like Excel), namely Data View and Variable View. To enter data, first determine the variables which are then inputted into the Variable View, such as Name, Weight, Height, Blood Pressure, Date of Birth, and so on.

| Name      | : filled with the variable name, for example Name                                                                                     | 
|----------|----------------------------------------------------------------------------------------------------------------------| 
| Type      | : filled with the data type, for example numeric (for numeric data) or string for text data .                                      | 
| Width     | : filled with the maximum number of characters to be inputted in the Data View .                                                      | 
| Decimal   | : filled with the maximum number of characters to be inputted in the Data View .                                                      | 
| Label     | : filled with a description for the variable (can be left blank) . | | Value | : to provide coding, for example Male =                                                                   1 
, Female     = 2. | | Missing | : for                                                           data 
treatment of   Missing Value (ignore according to default) .                                                  | 
| Align     | : for display alignment settings in the Data View, such as left, center, right .                                       | 
| Measure   | : by default Nominal will be selected if the variable is of string type, and Scale will be selected if the data is of Numeric type .  |

After determining the variables, now all that remains is to fill in the data in the Data View sheet. To make it easier, we will display an example of the data that will be input. After determining the variables, now all that remains is to fill in the data in the Data View sheet. To make it easier, we will display an example of the data that will be input.

This is the course grade data for 10 students:

Entomology (X) : 90, 67, 78, 85, 75, 60, 87, 87, 90, 60
Biostatistics (Y): 87, 75, 67, 80, 70, 56, 76, 54, 87, 65

Now we start inputting data according to the example above.

1]. Click start ‐> All programs ‐> SPSS for windows

2]. The menu that will appear is a sheet (Excel), namely Data View (where to enter data), Variable View (where to define variables)

3]. Click Variable View.

"Name" column = X (variable names must not be marked with spaces)

column "Type" = Numeric

Column "Width" = 8 (number of characters)

Column "Decimal" = 0 (number of digits after the decimal point)

Column "Label" = ENTOMOLOGY (variable label)

Column "Value" = None (filled in if the data is qualitative: for example L = 1, P = 2)

Column "Missing" = None (difference between variables)

Column "Columns" = 8 (column width is adjustable)

Column "Align" = Right (align writing)

Column "Measure" = Scala (data type)

4]. Continue by defining the variable "Y".

5]. Click Data View, input all Entomology variable data in column X, input all Biostatistics variable data in column Y.

6]. Finished (The data input process is complete), do not close the SPSS menu,

Then we continue with descriptive analysis

Descriptive Analysis

It is an analysis that aims to describe the state of the data. Descriptive analysis in the form of measures of central symptoms in the form of mean, median, and mode. Measures of distribution in the form of quartiles, deciles and percentiles. Measures of distribution in the form of data range, deviations (standard deviation and variance). Measures of skewness in the form of population models, skewness coefficients (kurtosis), and convexity coefficients (skewness).

The steps:

1. Click Analyze ‐> click Descriptive Statistics ‐> click Frequencies.

2]. Click Entomology (X) ‐> click the (>) sign (to enter the X variable into the variables(s) column).

3]. Click Biostatistics (Y) ‐> click the (>) sign (to enter the Y variable into the variables(s) column or highlight all X and Y variables then click the (>) sign.

4]. Check the box (V) for display Frequency Tables.

5]. Click Statistics, check (v) Quartile, Percentile (fill in 25, click Add, repeat for 50, and 75) Std. deviation, Variance, Range, Minimum, Maximum, SE mean, Mean, Median, Mode, Sum, Skewness, Kurtosis.