This tutorial will help you implement a Principal Component Analysis (PCA) on a subset of particular observations.
Dataset for running a Principal Component Analysis
An Excel sheet containing both the data and the results for use in this tutorial can be downloaded by clicking here.
The data are from the US Census Bureau and describe the changes in the population of 51 states between 2000 and 2001. The initial dataset has been transformed to rates per 1000 inhabitants, with the data for 2001 serving as the focus for the analysis. We are interested in studying large states (with a population greater than the average population). A size variable has been added (large/small).
Goal of this Principal Component Analysis
Our goal is to analyze the correlations between the variables and to find out if the changes in population in some states are very different from the ones in other states. We focus on the large states by using the filter option of XLSTAT.
The only difference between this tutorial and the tutorial available here is that we decide to study only the large states.
Setting up a Principal Component Analysis
Once XLSTAT-Pro is activated, select the XLSTAT / Analyzing data / Principal components analysis command, or click on the corresponding button of the Analyzing Data toolbar (see below).
The Principal Component Analysis dialog box will appear.
Select the data on the Excel sheet. The Data format chosen is Observations/variables because of the format of the input data.
The PCA type that will be used during the computations is the Pearson's correlation matrix, which corresponds to the classical correlation coefficient.
In the Data options tab, select the filter option and select the size column of the dataset.
In the Charts tab, we wish to have all large states displayed and thus do not activate the filter option.
Click on OK. A new dialog box asking you which group you want to keep is displayed. Select the large group and click Ok.
The computations begin once you have clicked on OK. You are asked to confirm the number of rows and columns.
Then you should confirm the axes for which you want to display plots. In this example, the percentage of variability represented by the first two factors is not very high (72.09%); to avoid a misinterpretation of the results, we have decided to complement the results with a second chart on axes 1 and 3.
Interpreting the results of a Principal Component Analysis applied on filtered data
The results for the largest states are displayed. The first table gives some descriptive statistics.
Then, eigenvalues are displayed.
We are interested in the maps for variables and observations. Regarding variables we have the following map:
We can see that on the first axis older states are opposed to younger states. The second axis opposes states with high domestic migration rates to states with lower domestic migration rates.
Regarding observations we have the following map.
This simple tool allows you to filter observations directly from your PCA dialog box and avoid complex data manipulation.