Cross Tab method , correlation method & T-test- Freny Mehta Group-1

CROSS TAB METHOD

Cross tabulation (or crosstabs for short) is a statistical process that summarize categorical data to create a contingency table.They are heavily used in survey research, business intelligence, engineering and scientific research. They provide a basic picture of the interrelation between two variables and can help find interactions between them.

Some entries may be weighted, unweighted tables are commonly known as pivot tables.

Cross tab is done to find relationship between two variables.(Bivarient)

Null hypothesis- There is no relationship between the two variables.

If calculated chi square- Table chi square value(critical square)

We reject the null hypothesis & vice versa

P value is less than 0.05, We reject null hypothesis.

CORRELATION METHOD- Two continuous variables done to find the strength of association between two variables.

For eg- The price of ice cream will determine demand.

If one variable increase and second variable decrease there is negative relationship, and when both variable increase there is positive relationship.

Significant relationship- If both variables are increasing at the same rate.

There is no hypothesis in correlation method

Values are between +1 and -1 indicate a strong relationship.

T-TEST

It is a bivariant test consisting of 3 methods

1. single sample)

2. paired

3. independent (equal variance & unequal variance)

Purpose of doing T-test- To compare means of two continous variables. T-test is not done for category variables.

If means are equal- Null hypothesis is accepted,

 If t-test value is > t critical (table value) we reject the null hypothesis.