Today it was the introductory session of Business Analytics in which we were exposed to the basic concepts of the package SPSS. There are different other tools in the market like SAS, Minitab but we are using SPSS as it is user friendly and it is widely accepted.

The first learning was about understanding the concept of variables:

Classification of variable:-

1.      Category variable- must have finite number of values example- District, State, Months etc

2.      Continuous- infinite values example- marks, age, etc. This is further classified into

a.      Continuous- infinite values including fractions eg-

b.      Discrete- infinite values with whole numbers eg- age

In the SPSS home page we saw variables and it explains the relationship of each and every variable in the data view of the data editor with that of the variable view of the same data editor. Each variable attributes are explained using its NAME ,TYPE, WIDTH, DECIMALS, LABEL, VALUE, MISSING.

Sometimes the respondents doesn’t answer/fill a particular category because of various reasons, this leads to missing numbers. This can happen for reasons like privacy, respondent didn’t understand the Qs or Qs not applicable for him. These missing numbers is necessary because it helps us in correcting our mistake if any in framing the Qs which might have lead to no response from the respondent.

The next concept was about understanding Measure which can be:

1.                 Nominal: We have the freedom to assign any number to a variable. Eg. If suppose we consider Male and female then we can assign 1 to Male and  2 to Female or vice versa.

2.                    Ordinal: shows order like

No School –       1     4

High School-      2     3

Graduation-        3     2

Post Graduate-  4     1

The first order is correct but not the second

3.                   Scale:  Where we can spot the exact difference in the range of ordinal scale. Ex-

If we consider 2 registration number of cars

WB02k   0125

WB02k   0534

Looking at the last 4 digits we can figure out that the first number had an early registration than the other one.

Classification of techniques:

1.                 1^st level analysis: frequencies, cross-tabs, OLAP cubes

                               2^nd level analysis: multi-variate techniques

2.                 Univariate – use/ show only one variable at a time. Pie chart (various values of the same variable)                

              A pie chart can be bivariate if one bring thickness of the pie into the picture.

                              Bivariate – correlation, t-test

                              Multivariate – bubble diagram

PS:  We have to use all variables as numeric variable as far as possible.

Understanding all the concepts we started our first assignment for proving a hypothesis for a given set of data.

Descriptive Statistics in SPSS

·           Frequencies:        It is used primarily for nominal and ordinal data. Tells the number of times the variable has occurred.

         

           Cross Tabulation: It is a process by which two or more data variables are tabulated, and displays the relationship in a tabular form. Generates information about  bi-variate relationships. It is not suitable for continuous variables that assume multiple values. In such a case, these continuous variables are re-categorised into category variables.

By

Suman Boro 

14169