I need help in this problem. Really i'm in bad situation. I have these data and i should find a correlation between food likes. i'm not familiar with statistics. would you show me any example for this problem. i have no idea for that.
closed as unclear what you're asking by gung♦, kjetil b halvorsen, Sycorax, Juho Kokkala, Scortchi♦ Aug 11 '15 at 13:00
Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.
How about just try correlations between any of two variables using Pearson or Spearman correlation coefficient.
The followings are SAS code and I use the top 10 observations in your table,
data a; input active gender age pizza salad chocolate coffe; datalines; 1 1 54 1 0 0 1 1 1 38 1 0 1 0 1 2 34 0 1 1 0 1 1 23 0 0 0 0 0 2 46 1 1 1 0 0 2 46 1 0 1 0 0 2 54 0 1 0 1 1 1 58 0 1 1 0 1 1 25 1 1 1 0 0 1 33 0 0 0 1 ; run; proc corr data=a spearman Pearson; var active gender age pizza salad chocolate coffe; run;
It seems Coffee and Chocolate are negatively correlated (r=-0.8017, p=0.0053), i.e people who prefer coffee will not like Chocolate, and vise visa. It seems reasonable, since Coffee is bitter and Chocolate is sweet. I did not see correlations between any other two variables.
The analysis is simple but I hope it can help you.
The "food like" variables look like binary values, so for each pair (e.g. pizza and salad), you could use Pearson's correlation. For a general discussion about correlations between binary vectors, see this question.
It would probably make sense to also divide the data by the other variables. E.g. is there a different correlation between pizza and pasta preference for men and for women?
You can do one of two things:
1) Multinomial logistic regression.
2) Boxplots on segmented data.
We're looking for long answers that provide some explanation and context. Don't just give a one-line answer; explain why your answer is right, ideally with citations. Answers that don't include explanations may be removed.