Exploring Nonlinearities in Path Models

In causal analysis, path models are an appropriate tool for studying relationships between social phenomena. However, they assume linear linkages between variables, and hence they are not always suitable for describing the complexity and richness of relationships in social phenomena. The aim of this work is to propose an exploratory graphical method to evaluate if the phenomena under analysis are actually characterized by non-linear linkages. In particular, the method is well suited to discovering interactions between the observed variables in path models. The proposed approach, which does not depend on any hypothesis on the error distribution, is based on a series of plots that can be easily interpreted and drawn using standard statistical software. As an additional feature, the plots – which we call joint effect plots – support qualitative interpretation of the non-linear linkages after the path model has been specified. Finally, the proposed method is applied within a case study. Non-linearities are explored in a casual model aiming to find the determinants of remittances of a group of Tunisian migrants in Italy.

[1]  K. Jöreskog.  A general method for analysis of covariance structures , 1970 .

[2]  Rex B. Kline,et al.  Principles and Practice of Structural Equation Modeling , 1998 .

[3]  A. Goldberger,et al.  Causal Models in the Social Sciences. , 1972 .

[4]  E. Arjas.  Causal Analysis and Statistics: A Social Sciences Perspective , 2001 .

[5]  Roy E. Welsch,et al.  Regression Diagnostics with Dynamic Graphics: [With Discussions and Response] , 1989 .

[6]  A. Israëls.  Path analysis for mixed qualitative and quantitative variables , 1987 .

[7]  E. Funkhouser,et al.  Remittances from international migration: a comparison of El Salvador and Nicaragua. , 1995 .

[8]  Futoshi Yamauchi.  Are experience and schooling complementary? Evidence from migrants' assimilation in the Bangkok labor market , 2004 .

[9]  William S. Cleveland,et al.  Visualizing Data , 1993 .

[10]  D. Rubinfeld,et al.  Econometric models and economic forecasts , 2002 .

[11]  J. Jaccard,et al.  Interaction effects in multiple regression , 1992 .

[12]  W. Y. Tan,et al.  On comparing several straight lines under heteroscedasticity and robustness with respect to departure from normality , 1982 .

[13]  G. Ritschard,et al.  Path analysis with partial association measures , 1996 .

[14]  N. Wermuth,et al.  On the identification of path analysis models with one hidden variable , 2005 .

[15]  Christopher Winship,et al.  Structural Equations and Path Analysis for Discrete Data , 1983, American Journal of Sociology.

[16]  C. Lance.  Residual Centering, Exploratory and Confirmatory Moderator Analysis, and Decomposition of Effects in Path Models Containing Interactions , 1988 .

[17]  Futoshi Yamauchi.  Are experience and schooling complementary , 2003 .

[18]  L. E. Jones,et al.  Analysis of multiplicative combination rules when the causal variables are measured with error. , 1983 .

[19]  K. Land.  Principles of Path Analysis , 1969 .

[20]  James Jaccard,et al.  Measurement error in the analysis of interaction effects between continuous predictors using multiple regression: Multiple indicator and structural equation approaches. , 1995 .

[21]  Ken Nishina.  Application of Statistical Causal Analysis to Process Analysis , 2001 .

[22]  Richard P.C. Brown.  Estimating remittance functions for Pacific Island Migrants , 1997 .

[23]  M. Mcclendon,et al.  Multiple Regression and Causal Analysis , 1994 .

[24]  S. West,et al.  Multiple Regression: Testing and Interpreting Interactions. , 1994 .

[25]  J. Brian Gray,et al.  Applied Regression Including Computing and Graphics , 1999, Technometrics.

[26]  R. Hauser,et al.  The Decomposition of Effects in Path Analysis , 1975 .

[27]  D. A. Kenny,et al.  Correlation and Causation , 1937, Wilmott.

[28]  Randy Hodson,et al.  Organizational Trustworthiness: Findings from the Population of Organizational Ethnographies , 2004, Organ. Sci..

[29]  R. Dennis Cook,et al.  Regression Diagnostics With Dynamic Graphics , 1989 .

[30]  H. Lenz,et al.  Frontiers in Statistical Quality Control 2. , 1984 .

[31]  J. Heckman.  Sample selection bias as a specification error , 1979 .

[32]  P. Holland.  CAUSAL INFERENCE, PATH ANALYSIS AND RECURSIVE STRUCTURAL EQUATIONS MODELS , 1988 .

[33]  E. Szabady.  Changes in Hungarian Society during 1945–1970 , 1969 .