This blog series demonstrates the usefulness of JMP's categorical platform. Part 1 shows that a single answer, multiple answers, etc. can be aggregated together, Part 2 shows how to compare response rates and scores by attribute (gender, age, etc.). In Part 3, the final part, we will show that there are various ways to hold data for multiple answers, and that any way to hold data can be treated as "categorical".
Lots of buttons related to multiple responses
As mentioned above, the role of response for each variable is specified in "Categorical", but there are various buttons in the "Multiple" tab as shown below. Actually this is Mechanism for handling multiple answers flexibly That's it.
Various input formats for multiple response data
For example, suppose there is a question Q1 with multiple answers, and the format is to answer all of the answer options 1, 2, 3, 4, and 5 that apply.
In the format where one person's answer is entered in one line, the following input methods ①, ②, and ➂ can be considered as data input methods.
① (Q1) is entered in one cell using a delimiter (comma ", " in this example).
② (Q1 1 to Q1 5) spans five columns, and the answer options are entered in order from the left column.
➂ (Q1-1 to Q1-5) spans five columns and is entered with 1/0 indicator variables. For example, the first row answers 1, 2, and 3, so we enter a value of 1 for Q1-1, Q1-2, and Q1-3, and a value of 0 for Q1-4 and Q1-5. .
Which format (1), (2), or (3) above is used depends on the ease of input for those who enter data manually, the system for collecting questionnaires, and other factors. Categorical in JMP allows any data format to be treated directly as multiple responses without any manipulation of the data.
The figure below shows the input formats corresponding to the "Multiple" buttons by numbers.
Of course, the same result is output regardless of method ①, ②, or ➂.
Even so, it is better to combine multiple answers in one column.
However, When analyzing multiple responses in JMP, it is more flexible to enter them in one column using delimiters as in ①. Although ② and ➂, which are entered over multiple columns, can be directly analyzed in "categorical", they cannot be handled as they are in "univariate distribution".
But don't worry. In JMP, even if the format is input across multiple columns, such as ② and ➂, it can be easily converted to the delimiter format of ①.
Here, we will introduce how to convert the indicator variable format (3) to (1) using the multiple response columns of the SQC training questionnaire introduced in this series.
How to combine multiple response columns into one column
- Select all columns of indicator variables (Q1_ Necessary for work to Q1_6 Others), Columns > Utilities > Merge Columns Choose.
- In the Merge Columns window, specify the column name (the column name when the combined column is created after this), delimiter, and [Selected columns are indicator variables], [Multiple responses] and click [OK].
Then a new column "Q1" is created as below. The values in this column are comma-separated multiple values, and you can see that the scale is set to Multiple responses.
The latest version "JMP 17" can handle multiple responses in Graph Builder
By using the above method to group them in one column, you can analyze multiple responses with [Univariate distribution]. With the latest version of JMP 17, Graph Builder now supports multiple response columns.
If you drop the newly created multiple response column "Q1" into the X zone, you can draw a bar chart with counts by identifying the responses with a delimiter as follows.
Graph Builder is convenient because you can flexibly set the settings such as sorting in descending order of frequency and changing the color and transparency of the graph.
The “categorical” platform described in this blog series. How was it. Although it is a little-known and unused platform, I hope that this blog will provide more opportunities for its utilization.
