Computing the Stochastic Complexity of Simple Probabilistic Graphical Models

Minimum Description Length (MDL) is an information-theoretic principle that can be used for model selection and other statistical inference tasks. There are various ways to use the principle in practice. One theoretically valid way is to use the normalized maximum likelihood (NML) criterion. Due to computational difficulties, this approach has not been used very often. This thesis presents efficient floating-point algorithms that make it possible to compute the NML for multinomial, Naive Bayes and Bayesian forest models. None of the presented algorithms rely on asymptotic analysis and with the first two model classes we also discuss how to compute exact rational number solutions.

Matrix Decomposition Methods for Data Mining : Computational Complexity and Algorithms

Matrix decompositions, where a given matrix is represented as a product of two other matrices, are regularly used in data mining. Most matrix decompositions have their roots in linear algebra, but the needs of data mining are not always those of linear algebra. In data mining one needs to have results that are interpretable -- and what is considered interpretable in data mining can be very different to what is considered interpretable in linear algebra. --- The purpose of this thesis is to study matrix decompositions that directly address the issue of interpretability. An example is a decomposition of binary matrices where the factor matrices are assumed to be binary and the matrix multiplication is Boolean. The restriction to binary factor matrices increases interpretability -- factor matrices are of the same type as the original matrix -- and allows the use of Boolean matrix multiplication, which is often more intuitive than normal matrix multiplication with binary matrices. Also several other decomposition methods are described, and the computational complexity of computing them is studied together with the hardness of approximating the related optimization problems. Based on these studies, algorithms for constructing the decompositions are proposed. Constructing the decompositions turns out to be computationally hard, and the proposed algorithms are mostly based on various heuristics. Nevertheless, the algorithms are shown to be capable of finding good results in empirical experiments conducted with both synthetic and real-world data.

Essays on Labor Market Frictions, Technological Change and Macroeconomic Fluctuations

The dissertation consists of an introductory chapter and three essays that apply search-matching theory to study the interaction of labor market frictions, technological change and macroeconomic fluctuations. The first essay studies the impact of capital-embodied growth on equilibrium unemployment by extending a vintage capital/search model to incorporate vintage human capital. In addition to the capital obsolescence (or creative destruction) effect that tends to raise unemployment, vintage human capital introduces a skill obsolescence effect of faster growth that has the opposite sign. Faster skill obsolescence reduces the value of unemployment, hence wages and leads to more job creation and less job destruction, unambiguously reducing unemployment. The second essay studies the effect of skill biased technological change on skill mismatch and the allocation of workers and firms in the labor market. By allowing workers to invest in education, we extend a matching model with two-sided heterogeneity to incorporate an endogenous distribution of high and low skill workers. We consider various possibilities for the cost of acquiring skills and show that while unemployment increases in most scenarios, the effect on the distribution of vacancy and worker types varies according to the structure of skill costs. When the model is extended to incorporate endogenous labor market participation, we show that the unemployment rate becomes less informative of the state of the labor market as the participation margin absorbs employment effects. The third essay studies the effects of labor taxes on equilibrium labor market outcomes and macroeconomic dynamics in a New Keynesian model with matching frictions. Three policy instruments are considered: a marginal tax and a tax subsidy to produce tax progression schemes, and a replacement ratio to account for variability in outside options. In equilibrium, the marginal tax rate and replacement ratio dampen economic activity whereas tax subsidies boost the economy. The marginal tax rate and replacement ratio amplify shock responses whereas employment subsidies weaken them. The tax instruments affect the degree to which the wage absorbs shocks. We show that increasing tax progression when taxation is initially progressive is harmful for steady state employment and output, and amplifies the sensitivity of macroeconomic variables to shocks. When taxation is initially proportional, increasing progression is beneficial for output and employment and dampens shock responses.

Linguistic grammars with very low complexity

We have presented an overview of the FSIG approach and related FSIG gram- mars to issues of very low complexity and parsing strategy. We ended up with serious optimism according to which most FSIG grammars could be decom- posed in a reasonable way and then processed efficiently.

Empirical Studies on Labor Market Matching (summary section only)

This thesis analyzes how matching takes place at the Finnish labor market from three different angles. The Finnish labor market has undergone severe structural changes following the economic crisis in the early 1990s. The labor market has had problems adjusting from these changes and hence a high and persistent unemployment has followed. In this thesis I analyze if matching problems, and in particular if changes in matching, can explain some of this persistence. The thesis consists of three essays. In the first essay Finnish Evidence of Changes in the Labor Market Matching Process the matching process at the Finnish labor market is analyzed. The key finding is that the matching process has changed thoroughly between the booming 1980s and the post-crisis period. The importance of the number of unemployed, and in particular long-term unemployed, for the matching process has vanished. More unemployed do not increase matching as theory predicts but rather the opposite. In the second essay, The Aggregate Matching Function and Directed Search -Finnish Evidence, stock-flow matching as a potential micro foundation of the aggregate matching function is studied. In the essay I show that newly unemployed match mainly with the stock of vacancies while longer term unemployed match with the inflow of vacancies. When aggregating I still find evidence of the traditional aggregate matching function. This could explain the huge support the aggregate matching function has received despite its odd randomness assumption. The third essay, How do Registered Job Seekers really match? -Finnish occupational level Evidence, studies matching for nine occupational groups and finds that very different matching problems exist for different occupations. In this essay also misspecification stemming from non-corresponding variables is dealt with through the introduction of a completely new set of variables. The new outflow measure used is vacancies filled with registered job seekers and it is matched by the supply side measure registered job seekers.

Does Uncertainty Affect Investment and Labor Demand?

This paper analyzes the effect of uncertainty on investment and labor demand for Finnish firms during the time period 1987 – 2000. Utilizing a stock return based measure of uncertainty decomposed into systematic and idiosyncratic components, the results reveal that idiosyncratic uncertainty significantly reduces both investment and labor demand. Idiosyncratic uncertainty seems to influence investment in the current period, whereas the depressing effect on labor demand appears with a one-year lag. The results provide support that the depressing effect of idiosyncratic uncertainty on investment is stronger for small firms in comparison to large firms. Some evidence is reported regarding differential effects of uncertainty on labor demand conditional on firm characteristics. Most importantly, the depressing effect of lagged idiosyncratic uncertainty on labor demand tends to be stronger for diversified firms compared with focused firms.

Examining effectiveness of an immigrant labor market integration intervention. The role of acculturation, discrimination, self-efficacy, outcome expectances, action and coping planning.

The designing of effective intervention tools to improve immigrants’ labor market integration remains an important topic in contemporary Western societies. This study examines whether and how a new intervention tool, Working Life Certificate (WLC), helps unemployed immigrants to find employment and strengthen their belief of their vocational skills. The study is based on quantitative longitudinal survey data from 174 unemployed immigrants of various origins who participated in the pilot phase of WLC examinations in 2009. Surveys were administered in three waves: before the test, right after it, and three months later. Although it is often argued that the unemployment among immigrants is due either to their lack of skills and cultural differences or to discrimination in recruitment, scholars within social psychology of behavior change argue that the best way of helping people to achieve their goals (e.g. finding employment) is to build up their sense of self-efficacy, alter their outcome expectances in a more positive direction or to help them to construct more detailed action and coping plans. This study aims to shed light on the role of these concepts in immigrants’ labor market integration. The results support the theories of behavior change moderately. Having positive expectances regarding the outcomes of various job search behaviors was found to predict employment in the future. Together with action and coping planning it also predicted increase in job search behavior. The intervention, WLC, was able to affect participants’ self-efficacy, but contrary to expectations, self-efficacy was found not to be related to either job search behavior or future labor market status. Also, perceived discrimination did not explain problems in finding employment, but hints of subtle or structural discrimination were found. Adoption of Finnish work culture together with strong family culture was found to predict future employment. Hence, in this thesis I argue that awarding people diplomas should be preferred in immigrant integration training as it strengthens people’s sense of self-efficacy. Instead of teaching new information, more attention should be directed at changing people’s outcome expectances in a more positive direction and helping them to construct detailed plans on how to achieve their goals.

Reasonability and the Linguistic - Division of Labor in Institutional Work

We examine institutional work from a discursive perspective and argue that reasonability, the existence of acceptable justifying reasons for beliefs and practices, is a key part of legitimation. Drawing on philosophy of language, we maintain that institutional work takes place in the context of ‘space of reasons’ determined by widely held assumptions about what is reasonable and what is not. We argue that reasonability provides the main contextual constraint of institutional work, its major outcome, and a key trigger for actors to engage in it. We draw on Hilary Putnam’s concept ‘division of linguistic labor’ to highlight the specialized distribution of knowledge and authority in defining valid ways of reasoning. In this view, individuals use institutionalized vocabularies to reason about their choices and understand their context with limited understanding of how and why these structures have become what they are. We highlight the need to understand how professions and other actors establish and maintain the criteria of reasoning in various areas of expertise through discursive institutional work.

Language universals and linguistic complexity : Three case studies in core argument marking

In this dissertation I study language complexity from a typological perspective. Since the structuralist era, it has been assumed that local complexity differences in languages are balanced out in cross-linguistic comparisons and that complexity is not affected by the geopolitical or sociocultural aspects of the speech community. However, these assumptions have seldom been studied systematically from a typological point of view. My objective is to define complexity so that it is possible to compare it across languages and to approach its variation with the methods of quantitative typology. My main empirical research questions are: i) does language complexity vary in any systematic way in local domains, and ii) can language complexity be affected by the geographical or social environment? These questions are studied in three articles, whose findings are summarized in the introduction to the dissertation. In order to enable cross-language comparison, I measure complexity as the description length of the regularities in an entity; I separate it from difficulty, focus on local instead of global complexity, and break it up into different types. This approach helps avoid the problems that plagued earlier metrics of language complexity. My approach to grammar is functional-typological in nature, and the theoretical framework is basic linguistic theory. I delimit the empirical research functionally to the marking of core arguments (the basic participants in the sentence). I assess the distributions of complexity in this domain with multifactorial statistical methods and use different sampling strategies, implementing, for instance, the Greenbergian view of universals as diachronic laws of type preference. My data come from large and balanced samples (up to approximately 850 languages), drawn mainly from reference grammars. The results suggest that various significant trends occur in the marking of core arguments in regard to complexity and that complexity in this domain correlates with population size. These results provide evidence that linguistic patterns interact among themselves in terms of complexity, that language structure adapts to the social environment, and that there may be cognitive mechanisms that limit complexity locally. My approach to complexity and language universals can therefore be successfully applied to empirical data and may serve as a model for further research in these areas.