topic Re: Comparisons of several groups within categories in Discussions

Comparisons of several groups within categories

Gunnar — Sun, 05 Apr 2020 17:39:51 GMT

I have data from 260 individuals. In 1 row the persons are ceategorized into male or female.

Within each gender, there is another coloums categorizing individuals into children, adolescents, adults, elderly.

And then there are coloums With measured parameters, e.g food intake, intake of energy etc.

How do I compare the measured parameters between age categories from each gender?

Re: Comparisons of several groups within categories

txnelson — Sun, 05 Apr 2020 19:54:13 GMT

your description of your data, I believe the below is representative of what the structure is like?

If this is so, I think what you need to do, is to start off with the Distribution Platform, learning about the distributions of the data. Are there any unusual issues? I would then list out the questions about the data that you want answered. Once you get to that point you may see what you need to do to answer the questions. At least, you will be able to as the Community, a more specific question.

Re: Comparisons of several groups within categories

KarenC — Sun, 05 Apr 2020 22:25:08 GMT

Well, "it depends" on so many questions. But to get you started:

1. Use graph builder to build charts (nest the descriptors: Graph Builder Documentation on Nested Axes)

2. You can select both descriptor columns, right click, select new formula, character, concatenate with a space to build a new column that contains a column with the two level description (Documentation on new formula column from right click)

3. Use Fit Y by X with a by variable (Documentation on One Way analysis )

4. Use Fit Model (Documentation on fitting linear models )

5. Potentially use the consumer research categorical platform - depends on what types of responses you have.

Re: Comparisons of several groups within categories

Gunnar — Mon, 06 Apr 2020 07:23:17 GMT

Hi thanks for the answer.

I know the data are not normally Distributed and non-Parametric tests have to de bone

I have compared the data for gender.

And I have also plotted and compared data for different age Groups (categories).

But then I would like to divide the data into age categories AND gender at the same time and have not figured out how to do this in JMP without splitting the data into one file for male and one for females

Gunnar

Re: Comparisons of several groups within categories

Gunnar — Mon, 06 Apr 2020 07:25:42 GMT

Re: Comparisons of several groups within categories

Gunnar — Mon, 06 Apr 2020 09:39:10 GMT

Re: Comparisons of several groups within categories

Gunnar — Mon, 06 Apr 2020 07:40:58 GMT

Yes this is quite similar to what the data look like. And I know the data is not normally distributed. I have compared the data between gender and between age Groups, but I would like to find out how to compare for example male and female adolescent, male and female elderly etc. DO I need to make subgroups and new files or is it an easier way to do this?

Re: Comparisons of several groups within categories

txnelson — Mon, 06 Apr 2020 11:13:26 GMT

You should be able to do the separate analyses you are mentioning "male and female adolescent, male and female elderly etc", by specifying those columns as "By" columns in the analysis and graphical platforms you are running. The example below adds "Age" and "Sex" to a simple Fit Y by X for "Height" vs. "Weight"

and it produces the output for each combination of sex and age

Re: Comparisons of several groups within categories

Gunnar — Mon, 06 Apr 2020 14:19:10 GMT

After using the fit X by Y function , the kcal intake as response, the age category as X factor and sex in the BY function, I have now got 2 graphs like the one below, one for the male and one for female.

What I wanted to do was to have all the Groups in the same figure and be able to compare them also by Wilcoxio tests