Below are some clarificatory notes related to the dataset.

Populist Outcome Related

Clarifications on Electoral Data

A few additional clarifications, as background information, are necessary to understand some of the measures related to the electoral data.

• 1. Bal Thackeray had never contested an election. But it seemed unjustifiable to ignore him, as he was clearly a populist leader of some measure in Maharashtra. Thus, I took the first electoral victory of the Shiv Sena in the assembly elections of 1995 as the populist instance, because Bal Thackeray reigned supreme for many years prior to and after this victory. And I took the electoral statistics of the incumbent chief minister and loyalist, Manohar Joshi, as the proxy for Bal Thackeray, assuming that the party chief that has got the assembly majority for the first time in its history would have its most trusted loyalist as the chief minister.

• 2. Jayalalitha's elections in 2001, 2011, and 2016 also need clarifications. In 2001, Jayalalitha was disqualified from competing in the election in May 2001 but was acquitted in December 2001 and thereafter won the byelections from Andipatti in 2002. In 2011, even though Jayalalitha won from the Srirangam constituency (which was the constituency included in the dataset), she was convicted by the Karnataka High Court soon thereafter and acquitted subsequently. She then contested from the RK Nagar constituency and resumed her chief ministership and contested from RK Nagar again in 2016.

In this chapter, I will present the results of the qualitative comparative analysis (QCA) and then interpret them to describe the configurations that constitute populism in India. I will then provide the results of the tests for necessary and sufficient conditions and discuss the parameters of fit in terms of consistency and coverage. Finally, I will cover the various solution terms that indicate the pathways to populism.

The Sets of Data

Table 5.1 presents the data, that is, the sets of data, comprising 37 cases along five conditions and a populist outcome. Describing the worksheet as comprising sets of data instead of a dataset seems more accurate because each of the columns in the sheet is a set and its members are points of data (as fuzzy scores or as percentage scores) along the rows as constituent parts of the unit of analysis. The unit of analysis is an instance of a party candidate contesting elections at the state or at the national level. The cases have been purposively selected by reviewing the scholarship that explicitly indicates that the cases can be identified as instances of populism. And the conditions described earlier—electoral invocation to their people (P), antagonistic boundary setting (B), populist political leadership (L), populist attitude (A), and anxiety about the future (F)—are some of the commonly accepted attributes in the comparative scholarship on populism. In set theoretic terms, we will explore if P, B, L, A, and F are the conditions that constitute the membership of the populist outcome Y.

When we see data on a spreadsheet, concepts and methods associated with standard quantitative techniques inevitably come to mind. Usually and by default, we try to make sense of the data by deriving the summary statistics to understand what has gone up or down, we explore associations between factors by identifying correlations, and administer technical tests to see if the results confirm, reinterpret, or nullify our research questions and hypotheses.

But is it possible to look at a dataset “qualitatively”? And what would that imply? Is it possible to look at columns and rows and identify relations and configurations between them that are more than associational? At first glance, the possibility of this approach seems incongruous because we usually associate qualitative methods with text and quantitative methods with numbers.

This chapter introduces the reader to a qualitative approach by providing an overview of the set theoretic methodology and the QCA method. An introduction to the methodology and the method is important not just because it is mostly an unfamiliar method to many social scientists, particularly those who work in the Indian context, but also because, as a methodology, its philosophical and conceptual roots are somewhat distinct from standard social science approaches. And, equally important, because QCA relies on numbers and software codes for analysis, it misconstrues expectations since the use of numbers can inadvertently lead to interpretations based on quantitative reasoning.

Over the past 75 years, there have been at least 800 state government terms ruled by around 375 political leaders as chief ministers and counting. Populist leaders are a small but pivotal subset among these leaders. Scholarship on such leaders has necessarily been long on descriptive accounts because of their exceptional rise to and stay in political office. Such accounts are the basis upon which this comparative account is built.

The unit of analysis in this study is not a populist personality over a period of time, but a personality in a particular year that corresponds with either an assembly or a national election year. For example, a single case would not be “Kejriwal,” but would instead be cases like “Kejriwal 2015” or “Kejriwal 2020.” This chapter, therefore, does not aim to provide elaborate accounts of the leaders, but tries to strike a balance with the details and their relevance and, in doing so, provide a narrative of each that is tenable for comparative analysis.

This “case by year” approach seems justified for a couple of reasons. First, while almost all populist leaders come to power riding a wave, they inevitably routinize into the mainstream over successive elections. The fever breaks. Second, it may appear that the period of such long-term leaders is linear, that is, from the heights of riding a wave to come to power, and subsequently routinizing into a banal steady but sustained popularity over time. Breaking this narrative into multiple periods provides space for curvilinear possibilities because it allows for a closer look into the ups and downs of political life in that declining trajectory.

This chapter provides a focused examination of spatio-temporal analysis using multilayer networks in which each layer represents the instantiation of a spatial network at a particular time of observation. The nodes in all layers may be the same with the only differences being of edges among layers (a multiplex network) or the nodes may change or move between layers and times. Multilayer characteristics such as versatility (multilayer centrality) and spectral properties are introduced. Several examples are described and reviewed as model studies for future ecological applications.

In this chapter, we describe how to jointly model continuous quantities, by representing them as multiple continuous random variables within the same probability space. We define the joint cumulative distribution function and the joint probability density function and explain how to estimate the latter from data using a multivariate generalization of kernel density estimation. Next, we introduce marginal and conditional distributions of continuous variables and also discuss independence and conditional independence. Throughout, we model real-world temperature data as a running example. Then, we explain how to jointly simulate multiple random variables, in order to correctly account for the dependence between them. Finally, we define Gaussian random vectors which are the most popular multidimensional parametric model for continuous data, and apply them to model anthropometric data.