```Overview
Path analysis is an extension of the regression model, used to test the fit of the correlation matrix against two or more causal models which are being compared by the researcher. The model is usually depicted in a circle-and-arrow figure in which single-headed arrows indicate causation. A regression is calculated for each endogenous variable in the model as a dependent on others which the model indicates are causes. The standardized regression weights predicted by the model are the path coefficients. The covariance matrix implied by the model is compared with the observed covariance matrix for the variables and a goodness-of-fit statistic is calculated. The best-fitting of two or more models is selected by the researcher as the best model for advancement of theory.
Formerly path analysis was accomplished as a series of multiple linear regressions, one for each endogenous variable. This method yielded standardized regression coefficients (beta weights) and a R-square goodness of fit for each endogenous variable, but did not yield an overall goodness of fit for the model. Now path analysis is implemented  by structural equation modeling (SEM) programs, which calculate all the paths simultaneously and yield an overall goodness of fit measure for the model.  While SEM typically centers on latent variables, it is possible to model simple observed variables. When only observed variables are in the model, the researcher is conducting a path analysis.
In most software implementations, path analysis requires the usual assumptions of linear regression. It is particularly sensitive to model specification because failure to include relevant causal variables or inclusion of extraneous variables often substantially affects the path coefficients, which are used to assess the relative importance of various direct and indirect causal paths to the ultimate  dependent variable. While it is possible to conduct path analysis on a single model, it is better if interpretations are based on comparing alternative models since goodness of fit is a relative concept which cannot prove that a single model is "correct".

Overview	6
Key Concepts and Terms	7
Path model	7
Causal paths	7
Exogenous and endogenous variables	8
Path coefficient/path weight	8
Path coefficients	10
Path multiplication rule	10
Disturbance terms	11
Estimation	11
Effect decomposition	12
Example 1	13
Example 2	14
Path analysis through structural equation modeling	15
OLS path modeling vs. SEM path modeling	15
The SEM path model	15
Selecting outputs: The Analysis Properties dialog	16
Path estimates	17
Goodness of Fit measures	19
Correlations	21
Direct and indirect effects	21
Modification indexes	23
Assumptions	25
Linearity	25
Interval level data	25
Uncorrelated error	25
Disturbance terms are uncorrelated with endogenous variables	25
Low multicollinearity	26
No underidentification or underdetermination of the model	26
Recursivity	26
Proper specification	26
Appropriate correlation input	27
The same sample	27
Does path analysis confirm causation in a model?	28
Can path analysis be used for exploratory rather than confirmatory purposes?	28
How do I know if my model is "underidentified" and what difference does it make? How does this relate to "recursivity?	29
How does the significance of a path coefficient compare with the significance of the corresponding regression coefficient?	29
How do you assess the significance of the total (direct and indirect) effect of exogenous variable x on endogenous variable y?	29
Why might the direct effect be zero?	29
How are path coefficients related to the correlation matrix for purposes of testing a model?	29
How, exactly, can I compute path coefficients in SPSS?	31
How do I compute the value of the path from an error term to an endogenous variable?	32
How can multiple group path analysis determine if the path model differs across groups in my sample?	32
Could I substitute logistic regression when doing effect decomposition?	32
Can path analysis handle hierarchical/multilevel data?	32
Are regression and SEM the only approaches to path analysis?	33
Bibliography	33

```