Where might I find a finite population dataset, with one dependent and two independent variables, with population size approximately 15 < N < 100, and all continuous (no count) variables? (A sample from an infinite population, with approximately 15 < n < 100, perhaps preferably a random sample, might possibly do. However it is important that two predictor variables are deemed adequate for the illustration I have in mind.)
I have a method for comparing regression model performances graphically, for cases with all continuous data, for which I want to write a clear explanation, including a simple graphical illustration. I am retired and would just be relying on Excel, and possibly a small population data set to illustrate this. I tried searching the internet and was at first encouraged by the number of multiple regression datasets available, but quickly found that locating such a dataset for clear illustrative purposes, and with my limited programming resources, was elusive.
Any suggestions would be appreciated. - Thank you.
I.
If you don't need real data, it's pretty easy to make data in excel that will fit what you need. For example, one column is X1, which is normally distributed, with some mean and standard deviation. (Maybe =NORMINV(RAND(),0,1) ?). X2 likewise. And then the third column is defined as a linear function of the first two columns, plus a random component (e.g. (5 + 10*A1 + 20*B1 + RAND()+0.5)*5).
II.
If you are looking for real data, the datasets in R might be useful. The ones that come with the base installation are at the following link. But also most packages come with more datasets, so there are many to choose from.
http://stat.ethz.ch/R-manual/R-devel/library/datasets/html/00Index.html
If you don't want to install R, you can use the following website. Just type in the dataset name in the lower box, and press enter. If the dataset is small enough to print, it will print it out right there. From there I had good luck copying, pasting into a .txt document, and then importing that .txt document into excel as fixed-width data. As an example, attached is the mtcars dataset.
http://www.r-fiddle.org/#/
James, I am curious why a sample of the size you want of such datasets that you found available online is not working?
Dear
It is better to make descriptive analysis of your data before any test. R Software will give you more possible for data using. But I need to underline that the size of the sample must be defined before the data collection.
Salvatore - You noted above that "If you don't want to install R, you can use the following website. Just type in the dataset name in the lower box, and press enter." However, I did not see a list of available dataset names from which to choose. -
Mehmet - I just want a dataset as described which would then suffice to show the simplest example of the method I would describe. That way I can refer people to a short paper rather than a rough, short description each time this comes up. The latest came up in the last part of my response to the following: https://www.researchgate.net/post/Why_in_a_simple_regression_an_independent_variable_shows_good_power_of_explanation_but_when_running_a_multiple_regression_it_does_not
Thank you all.
I meant you can resample from those datasets any size you wish.
Thank you, Salvatore.
FYI, all, I found this as well (with files listed after some 'related' data and references) from Florida State University (jburkardt), found somehow during Web surfing, but I don't recall what sent me there:
http://people.sc.fsu.edu/~jburkardt/datasets/regression/regression.html
- Badges
- Science topic