Human behavior takes place in different contexts (e.g., organizations, schools, families, sports teams, and communities) whose properties (e.g., climate, culture, cohesion, leadership, communication networks, and structure) influence human behavior. To estimate this influence, researchers need appropriate methods that avoid the problems associated with the application of standard Ordinary Least Square (OLS) regression. Multilevel modeling methods offer researchers a way to estimate the aforementioned influence. These methods take into account that the variables involved reside at different levels. For instance, in the relationship between work unit climate and employee job satisfaction, the former variable resides at the work unit level (level 2) whereas the latter resides at the individual one (level 1). Moreover, multilevel modeling methods also take into account that the data analyzed to estimate this type of relationships have a nested structure in which individuals (e.g., employees) are nested into collectives (e.g., work units). Finally, these methods decompose variance into between-group and within-group components and allow researchers to model variability at the between and within levels. Specifically, multilevel modeling methods allow researchers to test hypotheses that involve, among others: 1. A relationship between a higher-level predictor (e.g., work unit climate) and a lower-level outcome (e.g., employee job satisfaction); a so-called “direct cross-level effect”, and 2. An influence of a higher-level moderator (e.g., work unit climate) on an individual level relationship (e.g., the relationship between employee job stress and job satisfaction); a so-called “cross-level interaction”. Multilevel modeling methods can also be used to test more complex models involving mediation (e.g., 2-2-1, 2-1-1, or 1-1-1 models, depending on whether the antecedent and the mediator are level 1 or level 2 variables) and moderated mediation. We show how to test these models by presenting examples with real data and the corresponding SPSS syntax that readers can use to practice.
Vicente González-Romá and Ana Hernández
Gabriel A. León and Ashley K. Randall
Increasing the representation of diverse voices in relationship science requires statistical methodologies that are inclusive of individuals in relationships who identify as a sexual minority (i.e., lesbian, gay, or bisexual) or gender diverse (i.e., transgender, nonbinary, genderqueer, etc.) individuals. Research questions related to the initiation, development, and maintenance of romantic relationships for these individuals should be explored using quantitative methods that are sensitive to diversity and individual differences within a population. Analytical tools relevant to the study of interdependent, yet indistinguishable dyads, including references to extended technical guides for those wishing to conduct this work are presented.
Michael T. Braun, Steve W. J. Kozlowski, and Goran Kuljanin
Multilevel theory (MLT) details how organizational constructs and processes operate and interact within and across levels. MLT focuses on two different inter-level relationships: bottom-up emergence and top-down effects. Emergence is when individuals’ thoughts, feelings, and/or behaviors are shaped by interactions and come to manifest themselves as collective, higher-level phenomena. The resulting higher-level phenomena can be either common, shared states across all individuals (i.e., compositional emergence) or stable, unique, patterned individual-level states (i.e., compilational emergence). Top-down effects are those representing influences from higher levels on the thoughts, feelings, and/or behaviors of individuals or other lower-level units. To date, most theoretical and empirical research has studied the top-down effects of either contextual variables or compositional emerged states. Using predominantly self-report survey methodologies collected at a single time point, this research commonly aggregates lower-level responses to form higher-level representations of variables. Then, a regression-based technique (e.g., random coefficient modeling, structural equation modeling) is used to statistically evaluate the direction and magnitude of the hypothesized effects. The current state of the literature as well as the traditional statistical and methodological approaches used to study MLT create three important knowledge gaps: a lack of understanding of the process of emergence; how top-down and bottom-up relationships change over time; and how inter-individual relationships within collectives form, dissolve, and change. These gaps make designing interventions to fix or improve the functioning of organizational systems incredibly difficult. As such, it is necessary to broaden the theoretical, methodological, and statistical approaches used to study multilevel phenomena in organizations. For example, computational modeling can be used to generate precise, dynamic theory to better understand the short- and long-term implications of multilevel relationships. Behavioral trace data, wearable sensor data, and other novel data collection techniques can be leveraged to capture constructs and processes over time without the drawbacks of survey fatigue or researcher interference. These data can then be analyzed using cutting-edge social network and longitudinal analyses to capture phenomena not readily apparent in hierarchically nested cross-sectional research.
Paula kwan and Yi-Lee Wong
Two commonly researched leadership practices in the education literature—instructional and transformational—can be linked to Schein’s multilevel model on organizational culture. There is a mediating effect of school leadership on the school structure and school culture relationships. The literature related to this subject confirms that the culture of a school, shaped by its principal, affects the competency and capacity of teachers; it also recognizes that school leadership practices affect student academic outcomes. Some studies, however, attempt to understand the impact a school principal can make on its student culture. If school culture is an avenue for understanding the behaviors and performance of school leaders and teachers, then student culture is a platform for understanding the affective and academic performance of students.
Lucas Monzani and Rolf Van Dick
Positive leadership is a major domain of positive organizational scholarship. The adjective “positive” applies to any leader behavioral pattern (style) that creates the conditions by which organizational members can self-actualize, grow, and flourish at work. Some examples of style are authentic, transformational, servant, ethical, leader–member exchange, identity leadership, and the leader character model. Despite the myriad constructive outcomes that relate to said positive leadership styles, positive leadership it is not without its critics. The three main criticisms are that (a) the field is fragmented and might suffer from conceptual redundancy, (b) extant research focuses on the individual level of analysis and neglects reciprocal and cross-level effects, and (c) positive leadership is naïve and not useful for managing organizations. Our multilevel model of positive leadership in organizations proposes that leaders rely on internalization and integration to incorporate meaningful life experiences and functional social norms into their core self. Further, through self-awareness and introspection, leaders discover and exercise their latent character strengths. In turn, positive leaders influence followers through exemplary role modeling and in turn followers validate leaders by adopting their attributes and self-determined behaviors. At the team level of analysis, positive team leaders elevate workgroups into teams by four mechanisms that shape a shared “sense of we,” and workgroup members legitimize positive leaders by granting them a leader role identity and assuming follower role identities. Finally, at the organizational level, organizational leaders can shape a virtuous culture by anchoring it on universal virtues and through corporate social responsibility actions improve their context. Alternatively, organizations can shape a virtuous culture through organizational learning.
Jeremy B. Yorgason, Melanie S. Hill, and Mallory Millett
The study of development across the lifespan has traditionally focused on the individual. However, dyadic designs within lifespan developmental methodology allow researchers to better understand individuals in a larger context that includes various familial relationships (husbands and wives, parents and children, and caregivers and patients). Dyadic designs involve data that are not independent, and thus outcome measures from dyad members need to be modeled as correlated. Typically, non-independent outcomes are appropriately modeled using multilevel or structural equation modeling approaches. Many dyadic researchers use the actor-partner interdependence model as a basic analysis framework, while new and exciting approaches are coming forth in the literature. Dyadic designs can be extended and applied in various ways, including with intensive longitudinal data (e.g., daily diaries), grid sequence analysis, repeated measures actor/partner interdependence models, and vector field diagrams. As researchers continue to use and expand upon dyadic designs, new methods for addressing dyadic research questions will be developed.