Cross tabulation also known as cross-tab or contingency table is a statistical tool that is used for categorical data. Categorical data involves values that are mutually exclusive to each other. Data is always collected in numbers, but numbers have no value unless they mean something. 4,7,9 are simply numerical unless until specified. For example, 4 apples, 7 bananas, and 9 kiwis.

Cross tabulation is usually used to examine the relationship within the data that is not evident. It is quite useful in market research studies and in surveys. A cross table report shows the connection between two or more question asked in the survey.

While deploying a survey if the survey creator decides to send the survey to two different groups of people, cross tabulation helps to compare side by side, the responses of the two groups.

Cross-tab is a popular choice for statistical data analysis. Since it is a reporting/ analyzing tool it can used with any level of data: ordinal or nominal, because it treats all data as nominal data (nominal data is not measured it is categorised).

Let’s say you can analyze the relation between two categorical variable like age and purchase of electronic gadgets.

There are two questions asked here:

- What is your age?
- What is the electronic gadget that you are likely to buy in the next 6 months?

Age | Laptop | Phone | Tablet | Digital Camera |
---|---|---|---|---|

20-25 | 38% | 29% | 31% | 12% |

25-30 | 19% | 15% | 24% | 17% |

30-35 | 23% | 19% | 11% | 27% |

35-40 | 19% | 12% | 9% | 30% |

above 40 | 12% | 17% | 5% | 31% |

In this example you can see the distinctive connection between the age and the purchase of the electronic gadget. It is not surprising but certainly interesting to see the correlation between the two variables through the data collected.

In survey research crosstab allows to deep dive and analyze the prospective data, making it simpler to spot trends and opportunities without getting overwhelmed with all the data gathered from the responses.

- Login to your QuestionPro account and click Survey.
- Under Survey you will find the option for “Reports”. Click on Cross- Tabulation under Advanced.
- Select you row question and the column question from the dropdown respectively
- A cross-tab table will be generated along with Pearson’s Chi-square analysis
- Once you have generated the report, you can also download the report.

Chi square or Pearson's chi- square test, is any statistical hypothesis, which is used to determine whether there is a significant difference between expected frequencies and the observed frequencies in one or more category.

Another significant term that we will introduce here is “Null hypothesis”. The null hypothesis, basically assumes, any kind of difference or importance one can see in a set of data is by chance. The opposite of the null hypothesis is called the “alternative hypothesis”.

Applying chi square to surveys is usually done with these question types:

- Demographics
- Likert scale questions
- Cities
- Product name
- Dates and number (when clubbed together)

For example, we need to find out if there is any association between the buyer behavior of purchasing electronic devices and the region where it is sold then the data will be entered like the one in the table below:

As mentioned earlier the Chi square test helps you determine if two discrete variables are associated. If there's an association, the distribution of one variable will differ depending on the value of the second variable. But if the two variables are independent, the distribution of the first variable will be similar for all values of the second variable.

Using cross tabulation and chi square we derive the following inference:

Applying the Chi square calculation to the above values:

Pearson's chi square= 0.803, P- Value= 0.05

So what does this mean?

We need to pay attention to the p- value. Compare the p-value to your alpha-level which is commonly 0.05

- If p-value is less than or equal to alpha-value then the two variables are associated.
- If p-value is greater than alpha value, you conclude the variables are independent.

In this example Pearson chi-square statistics is 0.803 (with a p-value 0.05). So with an alpha-value of 0.05, we therefore, conclude that there is no correlation and is insignificant.

- One major advantage of using cross tabulation in a survey is, its simple to compute and extremely easy to understand. Even if the researcher does not have an in-depth knowledge of the concept, it is extremely easy to interpret the results.
- It eliminates confusions as raw data can sometimes be difficult to understand and interpret. Even if there are small data sets there is a possibility that you might get confused if the data is not arranged in an orderly manner. Cross tabulation offers a simple way of correlating the variables that help minimize a confusion related to data representation.
- One can derive numerous insights from cross tabulation. As mentioned in the examples of cross tabulation in the section above, it is not easy to interpret raw data. Cross-tab clearly maps out the correlation between variables, insights that otherwise may have been overlooked are clearly understood. It is extremely easy to understand the insights from even a complicated form of statistics.
- It provides the qualified or relative data on two or more variable across multiple features with ease.
- The most important advantage of using cross tabulation for survey analysis is the ease of using any type of data, whether it is nominal, ordinal, interval and ratio.