Approach towards statistics(Session 1)

Everybody must have seen the advertisement of Parle-g where curosity is the biggest teacher.This also applies in statistics ,where curosity is of uttermost importance "why is it so" "what's the reason", these are some dynamic aspects of statistics, so for studying we need to be dynamic at some point of time.

 The first thing we came to know about was data minning i.e we have to dig and dig deeper and realize whether  this is the real problem or this is just a symptom.
we would like  to elaborate this data minning by giving examples
1. Suppose in a company called "xyz", a particular employee called X was not able to concentrate on his work. we try to find the reason behind this and it was due to his poor health, well this is root problem, No this is just a symptom, then we started digging more we got the problem as the company policy and working hours were the main reason for his poor health.

 Now we came to know about the classification of techniques as stated below:
1: Univariate analysis:- Analysis of single variable
   for ex: How many of the student in the freshman class are female?
2: Bivariate analysis:- Involving two variables
 for ex: Is there a relationship between the number of females in computer programming and their scores in mathematics
3: Multivariate:-Involving more than 2 variables

Above techniques can also be classified as
1:Cross tab
2:Olap analysis

while further moving on we came to know about how to proceed while examing a statistical problem
the steps are as follows:
1:Analysis/processing
2:Observation
3:Interpretation
4:Strategy

what comes to the basics of statistics are cases and variables
1. cases: It is as entity which is in particular and can be used as an identifier
 for ex: a person name is always is in particular
2.Variable: It is an attribute which the cases possess
for ex: a person will be having age, gender etc this can be considered as variable


cases and variable together form record.

variable can be further classified as 1) category- very few values
                                                      2)continous -lots of values


Data classification
1) Nominal - These number don't have any meaning for ex: numbers written on back of jersey of football players
2)Ordinal - The quantity where we can have comparisons, but we can't have the exact differance .
                 for ex: X is more heavier than Y
3)Scale - Quantity where the order is needed to be maintained  and magnitude of exact differance is known
              for ex: Nagpur is 10 celcius more hotter than pune
4)Ratio - Highest level of  measurement have order, magnitude of differance known, have abosulute zero,       ratio of two number is meaningful

this was all about theoretical part after this we came to know about SSPS version 15

“True education is concerned not only with Theory goals but also with Practical’s.” by keeping this thought in mind we are taught how to work with SPSS.15.

In Data View:

As we mentioned above, all statics began with data which can be Primary Data (Collected by ourselves) or Secondary Data (Derive from Primary or Avail by third party). We should have at least two columns: one for dependent variable, and one for group (independent variable).

In the Variable View:

Make sure that the appropriate scale is selected for each variable. The dependent variable should be a scale variable, and the group variable should be ordinal or nominal.

 this was all about session 1 and 2.

1)Navdeep Singh
2)Navneet Singh
3)Shyam Pandhule
4)Praloy Kumar Saha
5)Pankaj Ruplani