Still in the testing phases. Contact B. Dudek if this app does not work for you.
This app will permit the user to upload a .csv file that contains data to be displayed. It needs to have at least two columns that represent the IV and DV, respectively. It is very important to follow the instructions here.
The application will only accept a “comma separated text file (.csv). It will work best if the number of rows (cases, or sample size) is less than 100.
The csv file must have only a small number of variables. The user can specify which variable to be used as the IV (X) and which is to be used as the DV (Y).
The first row in the csv file should contain the variable names (a "header”) . If you upload a .csv file without a header (and indicate that by unchecking the entry box on the sidebar), the variables to choose from will be listed as V1, V2, V3, etc, depending on their position in the .csv file. It is best to use .csv files that include variable names as a header row.
The best approach would begin by creating a file in a spreadsheet such as this:
Then save it as a .csv file.
Open the csv file in a text editor and it should look like this:
Author: Bruce Dudek at the University at Albany.
The simulation approach in this application simulates samples drawn from a bivariate normal distribution, where the means, sd's, rho, and n are specified by the user. The randomly drawn sample results are displayed in the scatterplot along with the sample pearson product-moment correlation.
If the user wants to see the same kind of scatterplot with their own data, the data upload approach permits this with upload of a .csv file.
For both appraoches, the scatterplots emphasize examination of the “rug plots” of both the raw Y values and the Yhat values. The user can explore how the dispersion of the Yhat values depends on the size of the pearson product-moment correlation.
The correlation simulation uses the rmvnorm function in the mvtnorm package in R.
Ver 1.6, Jan 23, 2017