No description available.

No description available.

Although previous studies on structural equation modeling (SEM) have indicated that the second-order latent growth model (SOLGM) is a more appropriate approach to longitudinal intervention effects, its application still requires researchers to collect at least three-wave data (e.g. randomized pretest, posttest, and follow-up design). However, in some circumstances, researchers can only collect two-wave data for resource limitations. With only two-wave data, the SOLGM can not be identified and researchers often choose alternative SEM models to fit two-wave data. Recent studies show that the two-wave longitudinal common factor model (2W-LCFM) and latent change score model (2W-LCSM) can perform well for comparing latent change between groups. However, there still lacks empirical evidence about how accurately these two-wave models can estimate the group effects of latent change obtained by three-wave SOLGM (3W-SOLGM). The main purpose of this dissertation, therefore, is trying to examine to what extent the fixed effects of the tree-wave SOLGM can be recovered from the parameter estimates of the two-wave LCFM and LCSM given different simulation conditions. Fundamentally, the supplementary study (study 2) using three-wave LCFM was established to help justify the logistics of different model comparisons in our main study (study 1). The data generating model in both studies is 3W-SOLGM and there are in total 5 simulation factors (sample size, group differences in intercept and slope, the covariance between the slope and intercept, size of time-specific residual, change the pattern of time-specific residual). Three main types of evaluation indices were used to assess the quality of estimation (bias/relative bias, standard error, and power/type I error rate). The results in the supplementary study show that the performance of 3W-LCFM and 3W-LCSM are equivalent, which further justifies the different models' comparison in the main study. The point estimates for the fixed effect parameters obtained from the two-wave models are unbiased or identical to the ones from the three-wave model. However, using two-wave models could reduce the estimation precision and statistical power when the time-specific residual variance is large and changing pattern is heteroscedastic (non-constant). Finally, two real datasets were used to illustrate the simulation results. / Doctor of Philosophy / To collect and analyze the longitudinal data is a very important approach to understand the phenomenon of development in the real world. Ideally, researchers who are interested in using a longitudinal framework would prefer collecting data at more than two points in time because it can provide a deeper understanding of the developmental processes. However, in real scenarios, data may only be collected at two-time points. With only two-wave data, the second-order latent growth model (SOLGM) could not be used. The current dissertation compared the performance of two-wave models (longitudinal common factor model and latent change score model) with the three-wave SOLGM in order to better understand how the estimation quality of two-wave models could be comparable to the tree-wave model. The results show that on average, the estimation from two-wave models is identical to the ones from the three-wave model. So in real data analysis with only one sample, the point estimate by two-wave models should be very closed to that of the three-wave model. But this estimation may not be as accurate as it is obtained by the three-wave model when the latent variable has large variability in the first or last time point. This latent variable is more likely to exist as a statelike construct in the real world. Therefore, the current study could provide a reference framework for substantial researchers who could only have access to two-wave data but are still interested in estimating the growth effect that supposed to obtain by three-wave SOLGM.

We re-examine the determinants of institutional ownership (IO) from a segmentation perspective -- i.e. accounting for a hypothesized systematic exclusion of stocks that cause high implementation or agency costs. Incorporating segmentation effects substantially improves both explained variance in IO and model parsimony (essentially requiring just one input: market capitalization). Our evidence clearly establishes a role for both implementation costs and agency considerations in explaining segmentation effects. Implementation costs bind for larger, less diversified, and higher turnover institutions. Agency costs bind for smaller institutions and clienteles sensitive to fiduciary diligence. Agency concerns dominate; characteristics relating to the agency hypothesis have far more explanatory power in identifying the cross-section of segmentation effects than characteristics relating to the implementation hypothesis. Importantly, our study finds evidence for interior optimum with respect to the institution's scale, due to the counteracting effect between implementation and agency frictions. We then explore three implications of segmentation for the equity market. First, a mass exodus of publicly listed stocks predicted to fall outside institutions' investable universe helps explain the listing puzzle. There has been no comparable exit by institutionally investable stocks. Second, institutional segmentation can lead to narrow investment opportunity sets, which limit money managers' ability to take advantage of profitable opportunities outside their investment segment. In this respect, we construct pricing factors that are feasible (ex-ante) for institutions and benchmark their performance. We find evidence consistent with the demand-based asset pricing view. Specifically, IO return factors yield higher return premia and worsened institutional performance relative to standard benchmarks in an expanding institutional setting (pre-millennium). Third, we use our logistic model and examine the effect of aggregated segmentation on the institutions' portfolio returns. Our findings suggest that investment constraints cut profitable opportunities and restrict institutions from generating alpha. In addition, we find that stocks with abnormal institutional ownership generate significant positive returns, suggesting institution actions are informed. / Doctor of Philosophy / We demonstrate that implementation and agency frictions restrict professional money managers from ownership of particular stocks. We characterize this systematic exclusion of stocks as segmentation and show that a specification that accommodates the segmentation effect substantially improves the empirical fit of institutional demand. The adjusted R-squared increases substantially; the residuals are better behaved, and the dimensionality of institutions' demands for stock characteristics reduces from a list of 8-10 standard characteristics (e.g., market cap, liquidity, index membership, volatility, beta) to just one: a stock's market capitalization. Our evidence identifies a prominent role for both implementation costs and agency costs as determinants of institutional segmentation. Implementation costs bind for larger, less diversified, and higher turnover institutions. Agency costs bind for smaller institutions and clienteles sensitive to fiduciary diligence. In fact, we find that segmentation arises from a trade-off between implementation costs (which bind for larger institutions) and agency considerations (which bind for smaller institutions). Agency concerns dominate; characteristics relating to the agency hypothesis have far more explanatory power in identifying the cross-section of segmentation effects than characteristics relating to the implementation hypothesis. More importantly, we find evidence for interior optimum with respect to the institution's scale, due to the counteracting effect between implementation and agency frictions. This conclusion is important to considerations of scale economies/diseconomies in investment management. The agency story goes in the opposite direction to the conventional wisdom underlying scale arguments. We then explore three implications of segmentation for the equity market. First, our evidence suggests that institutional segmentation coupled with growing institutional dominance in public equity markets may have had a truncating effect on the universe of listed stocks. Stocks predicted to fall outside of institutions' investable universe were common prior to the 1990s, but are now almost nonexistent. By contrast, stocks predicted to fall within institutions' investable universe have not declined over time. Second, institutional segmentation can lead to narrow investment opportunity sets, which limit money managers' ability to take advantage of profitable opportunities outside their investment segment. In this respect, we construct pricing factors that are feasible (ex-ante) for institutions and benchmark their performance. We find evidence consistent with the demand-based asset pricing view. Specifically, feasible return factors yield higher return premia and worsened institutional performance relative to standard benchmarks in an expanding institutional setting (pre-millennium). Third, we use logistic specification and examine the effect of aggregated segmentation on the institutions' portfolio returns. Our findings suggest that investment constraints cut profitable opportunities and restrict institutions from generating alpha. In addition, we find that stocks with high (low) abnormal institutional ownership generate significant positive (negative) returns, suggesting institution actions are informed.

The primary objective of this dissertation is to extend the classical Principal Components Analysis (PCA), aiming to reduce the dimensionality of a large number of Normal interrelated variables, in two directions. The first is to go beyond the static (contemporaneous or synchronous) covariance matrix among these interrelated variables to include certain forms of temporal (over time) dependence. The second direction takes the form of extending the PCA model beyond the Normal multivariate distribution to the Elliptically Symmetric family of distributions, which includes the Normal, the Student's t, the Laplace and the Pearson type II distributions as special cases. The result of these extensions is called the Generalized principal component analysis (GPCA). The GPCA is illustrated using both Monte Carlo simulations as well as an empirical study, in an attempt to demonstrate the enhanced reliability of these more general factor models in the context of out-of-sample forecasting. The empirical study examines the predictive capacity of the GPCA method in the context of Exchange Rate Forecasting, showing how the GPCA method dominates forecasts based on existing standard methods, including the random walk models, with or without including macroeconomic fundamentals. / Ph. D.

Regarding quantifying uncertainties in prediction, two projects with different perspectives and application backgrounds are presented in this dissertation. The goal of the first project is to predict the corporate default risks based on large-scale time-to-event and covariate data in the context of controlling credit risks. Specifically, we propose a competing risks model to incorporate exits of companies due to default and other reasons. Because of the stochastic and dynamic nature of the corporate risks, we incorporate both company-level and market-level covariate processes into the event intensities. We propose a parsimonious Markovian time series model and a dynamic factor model (DFM) to efficiently capture the mean and correlation structure of the high-dimensional covariate dynamics. For estimating parameters in the DFM, we derive an expectation maximization (EM) algorithm in explicit forms under necessary constraints. For multi-period default risks, we consider both the corporate-level and the market-level predictions. We also develop prediction interval (PI) procedures that synthetically take uncertainties in the future observation, parameter estimation, and the future covariate processes into account. In the second project, to quantify the uncertainties in the maximum likelihood (ML) estimators and compute the exact tolerance interval (TI) factors regarding the nominal confidence level, we propose algorithms for two-sided control-the-center and control-both-tails TI for complete or Type II censored data following the (log)-location-scale family of distributions. Our approaches are based on pivotal properties of ML estimators of parameters for the (log)-location-scale family and utilize the Monte-Carlo simulations. While for Type I censored data, only approximate pivotal quantities exist. An adjusted procedure is developed to compute the approximate factors. The observed CP is shown to be asymptotically accurate by our simulation study. Our proposed methods are illustrated using real-data examples. / Ph. D.

The thesis investigates if investors on the Swedish Stock Exchange, Nasdaq Stockholm, are compensated with a premium for holding shares in family firms due to family-specific agency costs between 2015 to 2019. The thesis uses a portfolio-based approach where the risk-adjusted returns are calculated with the Fama-French three-factor model and the Carhart’s four-factor model. A portfolio consisting of family firms displays a positive weekly alpha between 0,14 to 0,21 percent, 7,28 to 10,92 percent on a yearly basis, indicating a premium for holding shares in family firms. Additionally, the results show that firms where families control a majority of the votes lead to higher abnormal returns. A portfolio consisting of family firms with over 50 percent voting rights generate abnormal returns of 0,16 to 0,26 percent weekly, and 10,92 to 13,52 percent yearly. Higher abnormal returns when the control is higher further implies that investors are compensated with a premium for family-specific agency costs when buying shares in family-controlled firms.

Tänker du på det första intryck du får av någon du möter i vardagen? Kanske du funderar på hur dem är som person? Efter att ha sett någon för första gången bildas omedelbart ett första intryck och en uppfattning om dennes personlighet. Syftet med vår kvasiexperimentella studie är att undersöka hur bedömningen baserad på första intrycket av en individs personlighets stämmer överens med hur individen uppfattar sig själv. Urvalet bestod av 10 deltagare, sex kvinnor och fyra män. Åldersspannet låg mellan 23 till 55 år (M= 31,6; SD= 12,0). Deltagare har genomfört personlighetstest, fått se bilder av andra deltagare och sedan bedömt hur de uppfattat deras personlighet. Differensmåtten belyste att deltagare tenderade att självskatta högre poäng än vad de blev bedömda inom personlighetsdragen. Bedömningarna och självskattningarna inom några av personlighetsdragen visade en måttlig till stor effektstyrka (d.v.s. samvetsgrannhet, öppenhet, neuroticism). Men i studien förekom ingen signifikant korrelation mellan bedömd och självskattad personlighet. / Do you think about the impression you make of someone you meet in everyday life? Maybe you are thinking about what they are like as a person? Upon meeting someone, an impression of their personality swiftly develops. Our quasi- experimental study aimed to explore if assessment based on the first impression of an individual's personality is consistent with how the individual perceives themself. The sample consisted of 10 participants, six women and four men. Participants' age range was between 23 to 55 years old (M= 31,6; SD= 12,0). Participants underwent personality tests, viewed images of other participants, and then assessed how they perceived their personality. Differential measure showed that participants tended to self-assess higher scores than they were rated within the personality traits. The ratings and self-assessments in some of the personality traits showed a moderate to large effect size (i.e. conscientiousness, openness, neuroticism). However, there was no significant correlation between rated and self-assessed personality in the study.

Studien utgick från femfaktorteorin som bygger på fem personlighetsfaktorer: samvetsgrannhet, öppenhet, extraversion, vänlighet och neuroticism. Syftet med studien var att undersöka om dessa personlighetsfaktorer påverkar studenters val mellan en kvantitativ eller kvalitativ forskningsmetod för en kandidatuppsats, samt om kön och andra studierelaterade variabler påverkar detta val. Tidigare forskning antyder att personlighet påverkar bland annat val av programinriktning på universitetet och yrke. Om personlighet påverkar val av forskningsmetod är däremot inte något som tidigare har undersökts. Etthundratre studenter deltog i enkätundersökningen som bestod av personlighetstestet Big Five Inventory, samt frågor om studierelaterade variabler. Data analyserades med hjälp av korrelationstest och regressionsanalys. Studien fann ingen koppling mellan personlighetsdimensionerna och val av forskningsmetod, däremot med kön och studierelaterade variabler, däribland universitetets genomgång av forskningsmetoderna samt huruvida studenten ansåg sitt program vara utmanande eller ej. Mer forskning behövs för att säkerställa att personlighet inte har någon koppling till val forskningsmetod för studenter.

Socially responsible investing has presented itself as a growing, multifaceted, advanced and sophisticated investment philosophy. Socially responsible investment (SRI) involves incorporating social, ethical and responsible investment objectives with financial investment objectives during the investment decision-making process. Social, ethical and responsible investment objectives are set in line with environmental, social and corporate governance (ESG) criteria which are established within the SRI strategy followed. SRI strategies include screening (negative, positive and best-of-sector), shareholder activism and cause-based investing. Although international SRI markets such as that of the United States of America and the United Kingdom are sophisticated and established markets, the South African SRI market is still relatively new and is yet to reach its full potential. Thus, as a growing market, little research regarding the long term risk-adjusted performance of SRI funds in South Africa has been conducted. The long term risk-adjusted performance of the sample of SRI funds was measured through the use of five risk-adjusted performance measures, namely the Treynor ratio, Sharpe ratio, Jensen’s alpha, Sortino ratio and Omega ratio, and through the use of three performance measurement models which included the capital asset pricing model (CAPM), Fama-French three-factor model and Carhart four-factor model. The risk-adjusted performance of the sample of SRI funds was measured with the intent to establish if these funds out- or underperformed against three benchmark categories, namely the Financial Times Stock Exchange/Johannesburg Stock Exchange (FTSE/JSE) SRI Index, a matched sample of conventional investment (non-SRI) funds and the FTSE/JSE All Share Index. The probable effect of the 2007/08 global financial crisis was also measured to analyse whether such a hazardous market event affected the performance of the SRI funds. According to the results and findings, the risk-adjusted performance of the SRI funds has improved over the research period. However, the SRI funds neither outperformed nor underperformed against the three benchmark categories over the research period. The performance measurement models’ analysis indicated that the SRI funds were less sensitive to market fluctuations, more exposed to small capitalisation portfolios, more growth-oriented, and exhibited significant momentum after the period of the 2007/08 global financial crisis. Furthermore, the analysis indicated that the SRI funds significantly underperformed against the non-SRI funds during the Performance of socially responsible investment funds in South Africa research period. Mixed results were obtained with regards to the probable effect of the 2007/08 global financial crisis on the performance of the SRI funds.