One-Way ANCOVA For 3 Independent Samples

Analysis of Covariance for 3 Independent Samples
For Importing Data from a Spreadsheet

The logic and computational details of the one-way
independent-samples ANCOVA are described
in Chapter 17 of Concepts and Applications.

This page will perform an analysis of covariance for three independent samples, A, B, and C, where

A, B, and C represent three quantitative or categorical levels of the independent variable;
DV = the dependent variable of interest; and
CV = the concomitant variable whose effects one wishes to bring under statistical control.

Procedure: When importing data from a spreadsheet, the paired values of CV and DV for each sample must be in the form of two adjacent columns, as shown in the following figure, with the CV for each sample on the left and the DV on the right. Within the spreadsheet application, select and copy the two columns of data for Sample A.

Then return to this page, click the cursor into the data-entry field for Sample A, below, and perform the 'Paste' operation. Do the same for the other two samples in your analysis, then click the 'Calculate' button.

For each sample, make sure that the final entry is not followed by an extra line. (An extra line after the final entry in a sample will be interpreted as an extra data entry whose value is zero.) After all values for a sample have been entered, click the cursor immediately to the right of the final entry in the list, then press the down-arrow key. If an extra line is present, the cursor will move downward. Extra lines can be removed by pressing the down arrow key until the cursor no longer moves, and then pressing the 'Backspace' key (on a Mac platform, 'delete') until the cursor stands immediately to the right of the final entry.

Data Entry:
CV = concomitant variable [left column in each sample]
DV = dependent variable [right column in each sample]

Levels of Independent Variable
Sample A	Sample B	Sample C

Dependent Variable
Sample			Total
A	B	C	Total
n

Observed Means

Adjusted Means

Aggregate Correlation within Samples: CV vs DV
r =	r² =

ANCOVA Summary

Source	SS	df	MS	F	P
adjusted means
adjusted error
adjusted total

Test for homogeneity of regressions:

Source	SS	df	MS	F	P
between regressions
remainder
adjusted error

Home	Click this link only if you did not arrive here via the VassarStats main page.
©Richard Lowry 1998- All rights reserved.