SPSS stands for
Statistical package for social science. SPSS is among the most widely used
programs for statistical analysis in social science. It is used by market
researchers, health researchers, survey companies, government, education
researchers, marketing organizations and others.
The features of
the software include: statistical
analysis, data management and data documentation
Statistics
included in the SPSS software:
·
Descriptive statistics: Cross tabulation, Frequencies, Descriptives, Explore, Descriptive
Ratio Statistics
·
Bivariate statistics: Means, t-test, ANOVA, Correlation (bivariate, partial, distances),
Nonparametric tests
·
Prediction for numerical
outcomes: Linear regression
·
Prediction for identifying
groups: Factor analysis, cluster analysis
(two-step, K-means, hierarchical), Discriminant
The above
statistical tools provide various options for enquiring the relationship
between the variables. We started our Business Analytics learning with Usage of
some of these tools.
To perform any
analysis using SPSS the data needs either to be feed, or to be exported to a
SPSS editor. The SPSS editor has two sheets namely data view, and Variable
view. The data view sheet contains all the data captured against corresponding
variables (Each column in a data view sheet represents a distinct variable),
while the variable view sheet summarizes the characteristics of the various
variables present in the data sheet.
The column
labels of the variable view sheet are fixed, and the labels are:
·
Name: Represents name of the variable. E.g. - Age, Gender, etc.
·
Type: Contains the information about the type of variables. The various
types include Numeric, Comma, Dot, Scientific Notation, Date, Dollar, Custom
Currency and String (Alphanumeric).
·
Width: Represents the permissible size of the corresponding column. The
default width is the width of the first data entered in any column of the data
view sheet.
·
Decimals: Represents the decimal places up till which data is expected.
·
Label: Contains the detailed description of the variable.
·
Values: Variables are of two types, namely category, and continuous. The
continuous variables are further classified as continuous, and descriptive. In case of category variable we assign a
numeric value to each of the category. This column contains information about
all such assignments.
·
Missing: This column contains the information about the number of missing
response against a particular variable.
·
Column: Represents the visible width of any data. For ex. Consider the
width of name variable is 5, and the name entered against that variable is
ABCDE, if the column has the value 3 then the data visible to us would be ABC.
·
Alignment: Shows the various alignment options for the data.
·
Measure: Shows the type of data i.e. scale, ordinal or nominal.
Nominal
data are the data which doesn’t have any information. E.g. - name, location,
etc. The order of these data doesn’t convey any information, ordinal data
contains the information about the order of the data .ie, how a, b, c, d, e
should be ranked based on magnitude or some characteristics, but it doesn’t
reveal the magnitude of difference between two data points, and Scale data are
the data which contain the order and magnitude information i.e. If a, b are two
data points on a scale then we have the information that whether a>b or
b>a, and by how much.
To start any
research project we need to develop hypothesis to be verified. Hypothesis is of
two types, namely:
a) Null Hypothesis: The null hypothesis advocates
nonexistence of the relationship between the variables
b) Alternate Hypothesis: Accepts the existence relationship
between the variables.
The second step
is verification of the established hypothesis based on the available data. We
verified some of the hypothesis developed in the class using SPSS tools.
The various
tools used in the last class were:
·
Descriptive statistics: Frequency, Crosstab( Chi-square, Percentage representation of data)
·
Transformation: Reduces continuous variable to category variable.
Authors:
Nishant Lal
Manish Kumar
Lath
No comments:
Post a Comment