What is Chi-Square distribution?
The chi-Square distribution is a test used to test a hypothesis and is denoted by X2. In probability theory and statistics, the Chi-Square distribution is also known as the Central Chi-Square distribution.
The formula of Chi-Square distribution:
Generally, we use the following formula to calculate the Chi-Square distribution:
Chi-Square distribution = X2 = ∑ (Oi – Ei)2 / Ei
In the above formula:
Oi = Original values provided in data
Ei = Expected value calculated by the following formula
E = RT × CT / GT
Here
RT = Row Total
CT = Column Total
GT = Grand Total
Steps to calculate Chi-Square Distribution manually:
These are the following steps of Chi-Square distribution:
- Make a null hypothesis and also write an alternate hypothesis
- Calculate rows, columns, and Grand total
- Calculate the “expected value” E with the help of rows, columns, and grand total
- Draw a table and put the original and expected value in separate columns
- Calculate (O – E) in the next column
- Calculate (O – E)2 in the next column
- Calculate (O – E)2 / E in the next column
- The sum of the last column is our calculated value
- Find out the degree of freedom by the (r – 1) * (c – 1) formula
- Use the degree of freedom and level of significance to find out the table value
- Compare the calculated value and table value and write a conclusion
Example section:
In this section, we solve an example with the help of basic rules of Chi-square distribution.
Example 1:
Calculate Chi-Square distribution by taking null hypothesis Ho: µ1 = µ2 and H1: µ1 ≠ µ2 with the level of significance 5%.
| Category 1 | Category 2 |
Group 1 | 64 | 56 |
Group 2 | 42 | 28 |
Solution:
Step 1: Extract the data.
Ho: µ1 = µ2
H1: µ1 ≠ µ2
Step 2: Find RT, CT, and GT
| Category 1 | Category 2 | Total |
Group 1 | 64 | 56 | 120 |
Group 2 | 42 | 28 | 70 |
Total | 106 | 84 | 190 |
Step 3: Calculate Expected values
| Category 1 | Category 2 |
Group 1 | 66.947 | 53.053 |
Group 2 | 39.053 | 30.947 |
Step 4: Draw a Table and calculate the Chi-Square distribution value
O | E | O – E | (O – E)2 | (O – E)2 / E |
64 | 66.947 | - 2.947 | 8.6848 | 0.1297 |
56 | 53.053 | 2.947 | 8.6848 | 0.1637 |
42 | 39.053 | 2.947 | 8.6848 | 0.2223 |
28 | 30.947 | - 2.947 | 8.6848 | 0.2806 |
| | | Total | 0.7963 |
Step 5: Calculate the Degree of freedom
Df = (r – 1) * (c – 1)
Df = (2 – 1) * (2 – 1)
Df = 1 * 1
Df = 1
Step 6: Find out the table value
Table value = 0.3720
Step 7: Conclusion
Because the calculated value is greater than the table and lies in the critical region so we reject the null hypothesis and accept the alternate hypothesis.