0
$\begingroup$

I am looking for "must read"/classical references on data aggregation/disaggregation in statistics, particularly, what they are exactly, why they are done and how statistical measures (media, mean, correlation coefficient, etc.) and indices (Human Development Index, poverty, Gini, etc.) behave under aggregation/disaggregation of data. Is this topic worked out in basic school or undergraduate courses. It seems it is not.

$\endgroup$
1
  • 1
    $\begingroup$ The question seems weakly related to math. ed., except in the way that all mathematics that is taught or learned is related to education. -- Cross-posted: stats.stackexchange.com/questions/613536/… (currently closed there). $\endgroup$
    – user1815
    Apr 20, 2023 at 15:26

1 Answer 1

4
$\begingroup$

A classic reference is The Future of Data Analysis by John Tukey. This appeared in the Annals of Mathematical Statistics in 1962 and is widely available, for example on JSTOR. I love the beginning sentences: For a long time I have thought I was a statistician, interested in inference from particular to general. But as I have watched mathematical statistics evolve, I have cause to wonder and doubt. Of particular interest for this forum is section 9 of the paper titled "teaching of data analysis." Tukey also authored the book Exploratory Data Analysis in 1977.

Tukey is referred to as "the progenitor of data science," was an intellectual giant of the twentieth century, and was one of the most influential statisticians of the twentieth century. He discovered the ubiquitous Fast Fourier Transform, coined the word "bit," developed the statistical programming language S which begat R, introduced visualizations such as box and whisker plots, $\ldots$

$\endgroup$
4
  • $\begingroup$ It's unclear from the answer whether the book deals with aggregration/disaggregation. $\endgroup$
    – user1815
    Apr 20, 2023 at 15:29
  • $\begingroup$ @Raciquel, Data aggregation refers to numeric or non-numeric information that is (1) collected from multiple sources and/or across multiple measures, variables, or individuals and (2) compiled into data summaries or summary reports, typically for reporting purposes. audiences or statistical analysis. This means examining trends, making comparisons, or revealing information and insights that would not be observable when the data elements are viewed in isolation. $\endgroup$ Apr 23, 2023 at 1:28
  • $\begingroup$ @Raciquel, Data aggregation can be divided into two categories: types of aggregation by period and types of aggregation with mathematical functions. Period aggregation types include temporal aggregation and spatial aggregation. Temporal aggregation is the collection of data about a single resource over a given period. Spatial aggregation is a time period for which all data points for a group of features are collected. $\endgroup$ Apr 23, 2023 at 1:29
  • $\begingroup$ @HumbertoJoséBortolossi Neither of your comments refers to Tukey's book. The relevance of the book to the specific focus of your question was the point on which I sought clarification. $\endgroup$
    – user1815
    Apr 23, 2023 at 1:57

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.