Recent research in information economics has focused on signals as mechanisms to solve problems that arise under asymmetric information. A firm or individual credibly communicates the level of some unobservable element in a transaction by providing an observable signal. When applied to conveying product quality information, this issue is of particular interest to the discipline of marketing. In this article, the authors focus on the ways a firm may signal the unobservable quality of its products through several marketing-mix variables. The authors develop a typology that classifies signals and discuss the available empirical evidence on the signaling properties of several marketing variables. They consider managerial implications of signaling and outline an agenda for future empirical research.

No Pain, No Gain: A Critical Review of the Literature on Signaling Unobservable Product Quality:

This paper disaggregates the income of individuals or households into different factor components, such as earnings, investment income, and transfer payments, and considers how to assess the contributions of these sources to total income inequality. In the approach adopted, a number of basic principles of decomposition are proposed and their implications for the assignment of component contributions are examined.

/pdf/income-decomposition-by-factor-components-44qwnd1rry.pdf

Income decomposition by factor components

Motivation: In life sciences, interpretability of machine learning models is as important as their prediction accuracy. Linear models are probably the most frequently used methods for assessing feature relevance, despite their relative inflexibility. However, in the past years effective estimators of feature relevance have been derived for highly complex or non-parametric models such as support vector machines and RandomForest (RF) models. Recently, it has been observed that RF models are biased in such a way that categorical variables with a large number of categories are preferred.

Results: In this work, we introduce a heuristic for normalizing feature importance measures that can correct the feature importance bias. The method is based on repeated permutations of the outcome vector for estimating the distribution of measured importance for each variable in a non-informative setting. The P-value of the observed importance provides a corrected measure of feature importance. We apply our method to simulated data and demonstrate that (i) non-informative predictors do not receive significant P-values, (ii) informative variables can successfully be recovered among non-informative variables and (iii) P-values computed with permutation importance (PIMP) are very helpful for deciding the significance of variables, and therefore improve model interpretability. Furthermore, PIMP was used to correct RF-based importance measures for two real-world case studies. We propose an improved RF model that uses the significant variables with respect to the PIMP measure and show that its prediction accuracy is superior to that of other existing models.

Availability: R code for the method presented in this article is available at http://www.mpi-inf.mpg.de/~altmann/download/PIMP.R

Contact:altmann@mpi-inf.mpg.de, laura.tolosi@mpi-inf.mpg.de

Supplementary information:Supplementary data are available at Bioinformatics online.

/pdf/permutation-importance-527g6pap2t.pdf

Permutation importance

Decomposition techniques are used in many fields of economics to help disentangle and quantify the impact of various causal factors. Their use is particularly widespread in studies of poverty and inequality. In poverty analysis, most practitioners now employ decomposable poverty measures—especially the Foster et al. [10] family of indices—which enable the overall level of poverty to be allocated among subgroups of the population, such as those defined by geographical region, household composition, labour market characteristics or education level. Recent examples include Grootaert [11], Szekely [26], Thorbecke and Jung [28]. Other dynamic decomposition procedures are used to examine how economic growth contributes to a reduction in poverty over time, and to assess the extent to which the impact of growth is reinforced, or attenuated, by changes in income inequality: see for example, Ravallion and Huppi [20], Datt and Ravallion [6] and Tsui [29]. In the context of income inequality, decomposition techniques enable researchers to distinguish the “between-group” effect due to differences in average incomes across subgroups (males and females, say), from the “within-group” effect due to inequality within the population subgroups. Decomposition techniques have also been developed in order to measure the importance of components of income such as earnings or transfer payments.

/pdf/decomposition-procedures-for-distributional-analysis-a-1ikcjdo7xr.pdf

Decomposition procedures for distributional analysis: a unified framework based on the Shapley value

The analysis of inequality is placed in the context of recent developments in economics and statistics.

/pdf/measurement-of-inequality-42h81e6xrc.pdf

Measurement of inequality

This paper furthers the discussion of income inequality decomposition by focusing attention on the problems which arise in this context when available data are restricted to the distribution of factor incomes between groups of families defined by their total income level. First, it sets out the Rao (1969) decomposition of the Gini coefficient for total income in terms of factor shares and factor concentration ratios. Further decomposition of concentration ratios into rank correlation ratios and factor Ginis is recommended when individual data are available. Second, interpretation of concentration ratios as Gini coefficients is shown to be misleading. An analogue in economic theory is required. The results obtained required exploration of the alternative concepts and measurements which are possible when individual family data are available. In turn, these had to be related to the more limited set of concepts which can be calibrated when available data are taken from a secondary source. Caution is advised in interpreting results based on secondary sources of income inequality by factor components.

https://www.jstor.org/stable/info/1885088

Chau-nan Chen

Papers

The Distribution of Income by Factor Components