Nine Ways to Detect Possible Scientific Misconduct in Research with Small (N < 200) Samples

Some scientists have fabricated their data, yet have published their fake results in peer-reviewed journals. How can we detect patterns typical of fabricated research? Nine relatively less complex ways for detecting potentially fabricated data in small samples (N < 200), are presented, using data from articles published since 1999 as illustrations. Even with smaller samples, there are several ways in which scholars, as well as their undergraduate and graduate students, can detect possible fabrication of data as well as other questionable research practices (QRPs). However, with larger samples, other techniques may be needed.

Multilevel Analysis of Protest: Application for Small N Designs

Protest is the result of complex multilevel processes. It is triggered by contextual factors such as political opportunities or events, it depends on organizations’ mobilizing capacity as well as on the type of people who protest, and it is shaped by the characteristics of the populations they come from. To effectively study the antecedents that operate at various levels, social movement research needs to integrate data from multiple analytical levels and systematically examine the relationships across the various levels. While large N statistical techniques of multilevel modelling are well understood, less is known about applying multilevel analysis research examining small number of cases. The article develops conceptual and methodological tools for multilevel analysis of protests in studies with a small number of cases. First, it demonstrates the empirical requirements associated with analyzing three types of multilevel effects: contextual effects, composition effects, and cross-level interactions. Next, specific multilevel small N designs that can be used to examine the three multilevel effects are presented. The last section uses the multilevel approach to examine the demobilization of anti-Iraq War protests in the United States.

When average is over: small N but many trials

Rouder &amp; Haaf (2021) provide a valuable recipe for testing whether there are qualitative differences. This should hasten the day when psychologists routine consider individual participant data, rather than just the average of the participants’ data. Work remains to be done, however, on how to approach the issue of individual differences with the small-N, many-trials tradition that dates back to the beginning of experimental psychology and continues today in some areas, particularly cognitive modelling and perception.

Party System Closure

The Introduction starts with some examples of pairs of old and new democracies, some larger, some smaller, some in the East, some in the South, and illustrates how party system development can differ despite very similar background conditions. We then proceed to identify four main factors that differ within each pair, as possible explanations of the way party politics in general, and partisan interaction in particular, evolved in different countries. After stating the aims of the book and how it builds on previous studies, we summarize its main conceptual, operational, and methodological innovations, putting specific emphasis on the importance of history and a combination of large- and small-N studies. Finally, we explain the logic and structure of the book with a brief summary of the content of each chapter.

Big-M-Small-N Temporal-Order Judgment Data

We present a large and precise data set of temporal-order judgments on visual stimuli.Stimulus asynchronies ranged from 0 to 80 ms in steps of 6.67 ms. The data setincludes an attention manipulation driven by one target’s orientation compared tobackground elements (either zero or 90 degrees). Each of 25 stimulus asynchronies wassampled with at least 196 repetitions (and more than 400 times in two participants).Furthermore, fixation, an important concern in studies on covert attention, wasmonitored. Precise data are helpful for answering theoretical questions in psychology.For some questions such as model comparisons, they may even be necessary. Threedifferent exemplary models are fitted to the data.

Elite Studies: For a New Approach

We provide a critical review of explanations given for the decline of elite studies in the later twentieth century and of related proposals for their revival. We then suggest an alternative approach to elite studies that could, we believe, prove sociologically more rewarding. This entails a broad understanding of elites, understood, however, as small-N entities. On this understanding, elites can then be characterised through prosopographical methods – the construction of collective biographies of their members. A better understanding may thus be gained of the degree of social exclusiveness of different elites, and on this basis further questions can be taken up of how far exclusiveness results from the varying processes through which elites are formally constituted and how far from the composition of the pools within which such elite recruitment occurs. Finally, questions can be addressed of the implications of social skewness in elite formation for equality of opportunity and for the wastage of talent that inequality entails, and then further for the so far sociologically neglected issue of the level of performance – the effectiveness – of elites in whatever field they exist.

Machine Learning Methods for "Small-n, Large-p" Problems: Understanding the Complex Drivers of Modern-Day Slavery

40 million people are estimated to be in some form of modern slavery across the globe. Understanding the factors that make any particular individual or geographical region vulnerable to such abuse is essential for the development of effective interventions and policy. Efforts to isolate and assess the importance of individual drivers statistically are impeded by two key challenges: data scarcity and high dimensionality. The hidden nature of modern slavery restricts available datapoints; and the large number of candidate variables that are potentially predictive of slavery inflates the feature space exponentially. The result is a highly problematic "small-n, large-p' setting, where overfitting and multi-collinearity can render more traditional statistical approaches inapplicable. Recent advances in non-parametric computational methods, however, offer scope to overcome such challenges. We present an approach that combines non-linear machine learning models and strict cross-validation methods with novel variable importance techniques, emphasising the importance of stability of model explanations via Rashomon-set analysis. This approach is used to model the prevalence of slavery in 48 countries, with results bringing to light the importance predictive factors - such as a country's capacity to protect the physical security of women, which has previously been under-emphasized in the literature. Out-of-sample estimates of slavery prevalence are then made for countries where no survey data currently exists.