Use Case: Trending a Dimension over time

by Phil A.

This use case examines how to set up your analysis in Advanced Exploration if you want to trend a Dimension variable over a certain period of time.  

Some common examples that this use case can be used for include:

  • Purpose of Visit by week
  • Visit Frequency by month
  • Task Completion by quarter
  • Demographic data variables by year / quarter / month / week / day

 

For this use case, we'll address the following request: 

 

I would like to view a monthly trend of my respondents’ Purpose of Visit. 

 

Step 1: Select your Columns (X-Axis) and Rows (Y-Axis)

Note that the Resp_TimeEnd variable specifies when respondents submitted their responses, and can be used for analyses that require trending.

To analyze Purpose of Visit by Month, you would place Purpose of Visit (Dimension) as a Row, and Resp TimeEnd (Dimension) as a Column:

 

Step 2: Convert the Resp TimeEnd variable from “Year” to “Month”

By default, adding the Resp TimeEnd variable as a Column provides the data by Year.  For this example, right-click the variable, and select the “Month” option for which the year is also provided:

 

Step 3: Determine the format in which the data will be shown

The “Color”, “Shape” and “Text” options provided in the Marks card allows you to specify how to show this data in the table or chart.  For this example, the data will be shown in “Text” format.

Since respondents’ Purpose of Visit is being evaluated, click and drag the Purpose of Visit variable from the Dimensions menu to the “Text” option in the Marks card:

 

Step 4: Determine how the data in the output will be calculated

Now that we have specified the questions that are included in our analysis, and the format in which this analysis will be displayed, you must specify how the data will be calculated (e.g. as a percentage or an average). 

For this step, the items below can be performed by right-clicking the Purpose of Visit variable in the “Marks” card:

 

Convert this variable from a Dimension to a Measure (Measure > Count).  This will update the data to provide the sample size counts for each item in the table:

 

 

Then, specify the type of calculation that should be performed in the table. Since we are interested in the proportion of respondents who had certain Purposes of Visit, we want to view the data as a percentage (Quick Table Calculation > Percent of Total).

 

 

Finally, since we are working with percentages, we must specify if the Columns or the Rows in the table should add up to 100%. In this example, each of the Columns should add up to 100% (Compute Using > Table Down).

 

Step 5: Choose the chart type for your analysis

Using the “Show Me” option in the toolbar, select the format in which to display the data:

 

Additional Use Cases

Aggregate Analysis

Cross-Tabbing 2 Dimensions

Cross-Tabbing 1 Dimension And 1 Measure

Analyzing Data For Multi-Select Questions

Analyzing Respondent-Level Open-Ended Responses

Analyzing Close-Ended Data In Map Format

 

Trended Analysis

Trending A Measure Over Time

Trending A Crosstab Of 2 Dimensions Over Time

Trending A Crosstab Of 1 Measure And 1 Dimension Over Time

Was this article helpful?
0 out of 0 found this helpful
Have more questions? Submit a request

Comments

Powered by Zendesk