Expected Frequency Formulas:
For independence test: \[ E = \frac{\text{(row total)} \times \text{(column total)}}{\text{grand total}} \]
For goodness of fit: \[ E = n \times p \]
From: | To: |
Expected frequency (E) is the theoretical frequency that would be expected in a cell of a contingency table if the null hypothesis were true. It's used in chi-square tests to compare with observed frequencies.
The calculator provides two formulas for different statistical tests:
For test of independence: \[ E = \frac{\text{(row total)} \times \text{(column total)}}{\text{grand total}} \]
For goodness of fit test: \[ E = n \times p \]
Where:
Details: Expected frequencies are crucial for chi-square tests, which assess whether observed frequencies differ significantly from expected frequencies under the null hypothesis.
Tips: Select the appropriate test type (independence or goodness of fit) and enter the required values. All values must be positive numbers.
Q1: When should I use each formula?
A: Use the independence formula for contingency tables (chi-square test of independence). Use the goodness of fit formula when testing if sample data matches a theoretical distribution.
Q2: What if my expected frequency is less than 5?
A: For chi-square tests, expected frequencies should generally be ≥5. For smaller values, consider Fisher's exact test or combine categories.
Q3: Can expected frequency be a decimal?
A: Yes, expected frequencies are often decimal values, though observed counts must be whole numbers.
Q4: How does this relate to chi-square statistic?
A: The chi-square statistic is calculated by summing (observed-expected)²/expected for all cells.
Q5: What's the difference between expected and observed frequency?
A: Observed is what you actually measured, expected is what you would get if the null hypothesis were true.