PARTIAL CORRELATION (2014 EDITION)
An illustrated tutorial and introduction to partial correlation using SPSS, SAS, or Stata. Suitable for introductory graduate-level study. Partial correlation is the correlation of two variables while controlling for a third or more other variables. The technique is commonly used in "causal" modeling of small models (3 - 5 variables).
The 2014 edition updates the 2012 edition in four ways.:
The full content is now available from Statistical Associates Publishers. Click here.
Below is the unformatted table of contents.
PARTIAL CORRELATION Table of Contents Overview 5 Key Concepts and Terms 6 Control variables 6 Order of correlation 6 Effects 6 No effect 6 Explanation 7 Spurious correlation 7 Partial explanation 7 Suppression 8 Control variables with partial correlation and regression 11 Example data 11 Types of controls 12 Partial correlation method in SPSS 12 Partial correlation method in SAS 14 Partial correlation method in Stata 16 Residual method 18 Rate method 20 Regression method 24 Semi-partial (part) correlation 27 How it works 29 Why partial r is always larger than semi-partial r 30 Assumptions 30 Simple models 30 Recursivity 30 Linearity 31 Additivity 31 Data level 31 Model specification 31 Low multicollinearity 31 Frequently Asked Questions 31 SPSS gives me a choice of one-tailed and two-tailed tests. Which do I want? 31 If partial correlation assumptions are met and measures are reliable and valid, does upholding a model through partial correlation analysis mean that the model is true? 32 Is there any rule which can express the relation of the partial correlation to the original bivariate correlation (ex., is it always lower)? 32 What do SAS partial correlation scatterplots look like? 32 How is partial correlation computed? 33 Why does SPSS tell me I have 0 cases and it cannot compute partial correlation? 34 Can I use partial correlation for analysis of larger models? 34 Is there a form of partial association for nominal and ordinal variables, analogous to partial r for interval variables? 34 From statistical output for regression, how may we derive the significance of a partial correlation coefficient like rYX1.X2X3?? 36 Bibliography 37 Pagecount: 40