*53*

**Pearson residuals** are used in a Chi-Square Test of Independence to analyze the difference between observed cell counts and expected cell counts in a contingency table.

The formula to calculate a **Pearson residual** is:

r_{ij} = (O_{ij} â€“ E_{ij}) / âˆšE_{ij}

where:

**r**: The Pearson residual for the cell in the i_{ij}^{th}column and j^{th}row**O**: The observed value for the cell in the i_{ij}^{th}column and j^{th}row**E**: The expected value for the cell in the i_{ij}^{th}column and j^{th}row

A similar metric is the **Standardized (adjusted) Pearson residual**, which is calculated as:

r_{ij} = (O_{ij} â€“ E_{ij}) / âˆšE_{ij}(1-n_{i+})(1-n_{+j})

where:

**r**: The Pearson residual for the cell in the i_{ij}^{th}column and j^{th}row**O**: The observed value for the cell in the i_{ij}^{th}column and j^{th}row**E**: The expected value for the cell in the i_{ij}^{th}column and j^{th}row**p**: The row total divided by the grand total_{i+}**p**: The column total divided by the grand total_{+j}

Standardized Pearson residuals are normally distributed with a mean of 0 and standard deviation of 1. Any standardized Pearson residual with an absolute value above certain thresholds (e.g. 2 or 3) indicates a lack of fit.

The following example shows how to calculate Pearson residuals in practice.

**Example: Calculating Pearson Residuals**

Suppose researchers want to use a Chi-Square Test of Independence to determine whether or not gender is associated with political party preference.

They decide to take a simple random sample of 500 voters and survey them on their political party preference.

The following contingency table shows the results of the survey:

Â | Republican | Democrat | Independent | Total |

Male | 120 | 90 | 40 | 250 |

Female | 110 | 95 | 45 | 250 |

Total | 230 | 185 | 85 | 500 |

Before we calculate the Pearson residuals, we must first calculate the expected counts for each cell in the contingency table. We can use the following formula to do so:

Expected value = (row sum * column sum) / table sum.

For example, the expected value for Male Republicans is: (230*250) / 500 =Â **115**.

We can repeat this formula to obtain the expected value for each cell in the table:

Â | Republican | Democrat | Independent | Total |

Male | 115 | 92.5 | 42.5 | 250 |

Female | 115 | 92.5 | 42.5 | 250 |

Total | 230 | 185 | 85 | 500 |

Next, we can calculate the **Pearson residual** for each cell in the table.

For example, the Pearson residual for the cell that contains Male Republicans would be calculated as:

- r
_{ij}= (O_{ij}â€“ E_{ij}) / âˆšE_{ij} - r
_{ij}= (120 â€“ 115) / âˆš115 - r
_{ij}= 0.466

We can repeat this formula to obtain the Pearson residual for each cell in the table:

Â | Republican | Democrat | Independent |

Male | 0.446 | -0.259 | -0.383 |

Female | -0.446 | 0.259 | 0.383 |

Next, we can calculate the **Standardized Pearson residual** for each cell in the table.

For example, the Standardized Pearson residual for the cell that contains Male Republicans would be calculated as:

- r
_{ij}= (O_{ij}â€“ E_{ij}) / âˆšE_{ij}(1-p_{i+})(1-p_{+j}) - r
_{ij}= (120 â€“ 115) / âˆš115(1-250/500)(1-230/500) - r
_{ij}= 0.897

We can repeat this formula to obtain the Standardized Pearson residual for each cell in the table:

Â | Republican | Democrat | Independent |

Male | 0.897 | -0.463 | -0.595 |

Female | -0.897 | 0.463 | 0.595 |

We can see that none of the Pearson Standardized Residuals have an absolute value greater than 3, which indicates that none of the cells contribute to a significant lack of fit.

If we use this online calculator to perform a Chi-Square Test of Independence, weâ€™ll find that the p-value of the test is **0.649198**.

Since this p-value is not less than .05, we do not have sufficient evidence to say that there is an association between gender and political party preference.

**Additional Resources**

The following tutorials explain how to perform a Chi-Square Test of Independence using different statistical software:

An Introduction to the Chi-Square Test of Independence

How to Perform a Chi-Square Test of Independence in Excel

How to Perform a Chi-Square Test of Independence in R

Chi-Square Test of Independence Calculator