This page contains a number of sets of data for hierachical ( and more complex structures)

http://www.bristol.ac.uk/cmm/learning/mmsoftware/

It also show for a very large range of software how they have been analysed by random effects analysis.

See below link

http://en.wikipedia.org/wiki/Database_model#Hierarchical_model

dear Rao,

you can use adult dataset from uci machine learning http://archive.ics.uci.edu/ml/. There are also others datasets such as census or IPUMS datasets where they are as demography dataset.

I use AOI (Attribute Oriented Induction) Data Mining technique to learn this dataset.

as I used in my papers which you can see at my profile where I used some attributes from adult dataset such as workclass, education, marital-status, occupation and native-country.

You can see my how I used adult dataset in my papers such as

1. Attribute Oriented Induction of High-level Emerging Patterns

2. Star Schema Design for Concept Hierarchy in Attribute Oriented Induction

3. Attribute Oriented Induction with simple select SQL statement

4. Attribute oriented induction with star schema

Good luck

Thank you

This page contains a number of sets of data for hierachical ( and more complex structures)

http://www.bristol.ac.uk/cmm/learning/mmsoftware/

It also show for a very large range of software how they have been analysed by random effects analysis.

Let me know what kind of help do you need ?

I would like to know about dataset in .arff format which can be used for mining multilevel association rule.

If you're using .arff, maybe you're using weka.

There are alot of dataset on waikato university repository for learning datamining at the begining. They have from biology dataset until population dataset in format of .arff.

From my opinion its alot easier to understand and simple dataset sample and tutorial. As my senior Mr. Spits say, the easiest way is to learn step by step from association rule,classification and clustering on data mining. Than goes deeper to its development on data analytic or data science

You please cheek in the following link

http://archive.ics.uci.edu/ml/