I have a dependent variable - how much land does a household cultivate out of total in their possession. The answers are categorized in 3 different groups (1 - 70% - 100%, 2 - 40 - 70%, 3 - less than 40%).

I have asked a bunch of questions about the households I assume have sth to do with the percentage of cultivated land. Some answers (variables) are ranks, some are categorical, some are Likert-based etc. In total there are 90 variables. I want to see which variables are significant for the differentiation of those three categories of land cultivation. I want to say - most of the land will be cultivated by households which are on average young, less educated, with less income, with more tractors and have more members. Where less land is cultivated, the households are old, they want to live in the city and have chicken.

I can't do it one by one - eg. number of people per household on cultivated land, age of respondents on cultivated land etc., because eg. 9 people in a household is not enough of an information - there is an assumed difference if those 9 people are young or old. So maybe there is a difference of 9 young and 9 old. But what if the education is also important? Both 9 young and 9 old are statistically not significant, but 9 young educated and 9 old non educated are statistically different on cultivated land. Etc. I hope I am clear with my question. What method could I use in this? Thank you in advance.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.