# How do I run a TURF analysis with XLSTAT-MX?

An Excel spreadsheet containing the data and the results of this example can be downloaded by clicking here . The data comes from ratings by 185 customers on 27 dishes. Scores are given on a scale of 1 to 5 in response to the question "Would you buy the product?" (1: no, not at all to 5: Yes, quite sure). The goal here is to obtain a product line consisting of 5 dishes that will be sold in some stores. It should be constructed such that the market share of this line is as strong as possible.

We use the TURF method (Total Unduplicated Reach and Frequency), which provides a product line that has the highest penetration. All combinations of 5 products among all productsis testd in order maximize the chance that at least one of these products is consumed (for details, see the help of XLSTAT).

After opening XLSTAT, select the XLSTAT/XLSTAT-MX/TURF command, or click on the corresponding button of the "XLSTAT-MX" button (see below).

Once the button is clicked, the dialog box appears. You can then select the data on the Excel sheet. You must select all products as “data”. The "Variable labels" is left enabled because the first line of the column of data includes the product name. The size of the subset is 5. The scale being 1 to 5, we select as a scale 1-5.

In the “options” tab, the number of combinations to be displayed is 10. Thus, the 10 best lines of 5 products will be displayed. Then, you define the goal. In our case, we consider that a consumer will buy the product if he gives a score of 4 or 5. The method used is the enumeration that will necessarily give the optimal result.

Once you have clicked the "OK" button, the calculations start, and the results are displayed.

## Interpreting the results of a TURF analysis

The first table includes the frequencies at which the objective is achieved for each product separately.

The following table gives the 10 best combinations obtained, each time with the reach and the frequency obtained. The reach is the number of consumers who intend to buy at least one product of the line (it will be worth up to 185), the frequency is the number of times a product line has received a score of 4 or 5 (maximum of 5 * 185 = 925).

The following table gives the same information as the previous with percentages instead of raw values.

This brief analysis has allowed us to bring out a product line that will have a very good market share. This line consists of products (14, 15, 16, 23, 26) and gets a reach of 129, or nearly 70% of the consumers.

Kovach Computing Services (KCS) was founded in 1993 by Dr. Warren Kovach. The company specializes in the development and marketing of inexpensive and easy-to-use statistical software for scientists, as well as in data analysis consulting.

Like us on  Facebook

### Get in Touch

• Email:
sales@kovcomp.com