Search

This research note is a case study that called into question police conduct and policy injustice discovered in two American big cities. The path to learn about Indianapolis (IN) and Baltimore (MD) policing patterns and crime events was due to availability of detailed data that focused on use-of-force. A specific goal was to conduct geospatial data analysis aimed at these two cities using location, force, and race as variables. A modest sampling of open data permitted statistical groundwork for iterations of a powerful method known as exploratory spatial data analysis (ESDA). Bivariate scatterplots revealed possible police misconduct. Parallel coordinate plotting – an innovative multivariate tool – was then used to plot use-of-force and racial variables associated with key police districts in Indianapolis and Baltimore. Even “small data” can surprise if they are supported by descriptive statistics along with detailed visualizations that cartographically and dramatically compared force and race variables by way of co-occurring plots, graphs, and maps. Action items suggested were 1) a “social-justice” framework for future data-visualization, 2) significant heightening of standards for law enforcement reform, and 3) a compelling need to make a hypothetical “citizen’s arrest” of any future police misconduct. A conclusion offered a four-part model whereby this research report was situated within the mission, purpose, and founders’ values of the Environmental Design Research Association (EDRA) in the specific context of EDRA 52.

OBJECTIVE: We tried to identify the mechanisms through which demographic changes and socio-economic inequalities affect the use and choice of contraception in currently married women of reproductive age over the last decades. METHODS: The samples were collected from two of the 2005-06 and 2015-16 National Family Health Surveys (NFHSs). Bivariate analysis was used in tandem with Pearson’s chi-squared test to analyse the relationships between socio-demographic variables and two dependent variables. The dependent variables were active use of contraceptives and contraceptive choice, defined as a parameter “Yes / No” and “Traditional / Modern” respectively. We consider a statistical model suitable for the binary response to select the selected factors’ adjusted effects, namely the binary logistic regression model in a multivariate setup. RESULTS: Nearly half of the respondents were below 35 years of age in both rounds of the survey. It has been found that contraception usage among currently married women aged 15-49 declined from 56.33% in 2005-06 to 53.54% in 2015-16. All the variables are significantly associated (p

Starting from the Cholesky-GARCH model, recently proposed by Darolles, Francq, and Laurent (2018), the paper introduces the Block-Cholesky GARCH (BC-GARCH). This new model adapts in a natural way to the asset pricing framework. After deriving conditions for stationarity, uniform invertibility and beta tracking, we investigate the finite sample properties of a variety of maximum likelihood estimators suited for the BC-GARCH by means of an extensive Monte Carlo experiment. Finally, we illustrate the usefulness of the BC-GARCH in two empirical applications. The first tests for the presence of beta spillovers in a bivariate system in the context of the Fama and French (1993) three factor framework. The second empirical application consists of a large scale exercise exploring the cross-sectional variation of expected returns for 40 industry portfolios.

This study seeks to examine factors influencing direct flotation costs for public issuance of securities in Kenya’s capital markets since no benchmark exists that potential issuers can utilize for estimating flotation expenses. The research seeks to identify the quantum as well as understand the effects of offer size, offer method, underwriter (lead transaction advisor) reputation, market segment, offer complexity and firm size on flotation costs. Secondly, it seeks to develop a flotation cost function that can be applied to estimate direct flotation costs. Finally, it seeks to understand whether the flotation cost, certification and market power hypothesis are pertinent in Kenya’s securities markets. The study adopts a quantitative approach consisting of univariate analysis, as well as hypothesis testing using bivariate and multivariate regression, applied on a longitudinal panel dataset for public issues between 2007-2019. The study finds that the mean and trimmed mean for flotation cost as a percentage of offer size is 3.4% and 3.1% of offer size, with a median of 2.98% for the review period. The correlations show that offer size has the highest correlation to flotation cost with (0.610), followed by firm size at (0.521), offer complexity with (0.411), market segment at (0.246), underwriter experience with (0.175) and offer method with (-0.143). The results indicate all predictor variables have a positive correlation with flotation cost ranging from strong - weak except offer method with a weak negative correlation. The bivariate regression results indicate that offer size, firm size, offer complexity and market segment have significant influence on flotation costs for securities offerings. However, offer method and underwriter reputation have no significant influence on flotation costs. The regression results for the combined effect of the overall model are significant where p value is 0.000. This confirms that predictor variables in the model have a significant combined effect on flotation cost. The study also found clear evidence in favor of the economies of scale view and certification hypothesis.

In this working paper, we analyze factors that may explain gender differences in the allocation of time to household production in sub-Saharan Africa. The study uses time use survey data to analyze the determinants of time spent on household production by husbands and wives in nuclear families in Ethiopia, Ghana, Tanzania, and South Africa. We assume that the time spent by each spouse is a function of personal and household characteristics. A bivariate Tobit model is used to estimate the marginal impact of a set of key variables that figure recurrently in the literature on time allocation. We observe a high degree of variability in the results for the set of countries, which does not allow us to draw hard general conclusions. We do find some weak evidence that supports time availability and gender ideology theory as well as for the hypothesis that bargaining power plays a role in explaining the intrahousehold allocation of household production.

Indonesia is currently still facing serious problems regarding stunting. The high prevalence of stunting in Indonesia is a chronic problem related to poverty, low education, and inadequate environmental and health services. Efforts made are improving the nutritional status of the community. The role of parents is very important in fulfilling children's nutrition. For this reason, treatment is needed through an approach to the family that can have an impact on behavior change within the family in carrying out family functions caring for family members with stunting, one of which is implementing family psychoeducation therapy. The purpose of this study was to determine the effect of family psychoeducation therapy on height gain in stunting children. This study used a quasi experimental research method with a pretest-posttest design. The sampling technique used purposive sampling of 34 respondents consisting of 2 groups, namely 17 respondents in the intervention group and 17 respondents in the control group. Assessment using instruments from the WHO-NCHS Standard deviation Z-Score TB / U. The data analysis used was the dependent sample t 2 test and independent sample t 2 test for bivariate. The results showed that there was an effect of family psychoeducation therapy on height gain and there was a significant difference in the average height increase in stunting children between the intervention group and the control group.

Multivariate analysis can help to focus on economic phenomena, including trend and cyclical movements. To allow for potential correlation with seasonality, the present paper studies a three component multivariate unobserved component model, focusing on the case of quarterly data and showing that economic restrictions, including common trends and common cycles, can ensure identification. Applied to seasonal aggregate gender employment in Australia, a bivariate male/female model with a common cycle is preferred to both univariate correlated component and bivariate uncorrelated component specifications. This model evidences distinct gender-based seasonal patterns with seasonality declining over time for females and increasing for males.

Risk-taking in sex work is related to financial gains from condom-protected and condomless-acts alongside vulnerabilities, including socio-economic factors, which influence the safety of sex workers. Large international sporting events have been shown to significantly impact the economies of host countries, but there is a dearth of studies that examine how major sporting events may affect the economics of sex work and the risks taken by sex workers and clients. This study examines the determinants of the price of commercial sex alongside the price premium for and correlates of, condomless sex before, during and after the 2010 world cup in South Africa. We analysed data from three phases of repeated cross-sectional surveys with sex workers. Bivariate and multivariable logistic regression models were fitted to examine the predictors of condomless sex. We also fitted fixed-effect regression models to examine the determinants of the price of commercial sex across each survey phase. Findings suggest that the price of sex was higher during the world cup compared to before and after, whilst the price premium for condomless-sex increased from 36% before the world cup to 40% (p-value

We study the predictability of cross-sectional uncertainty (CSU) proposed by Dew-Becker and Giglio (2021) for stock returns. We find that CSU exhibits significant power for predicting monthly stock returns with annual out-of-sample R^2 of 6.34%, greater than popular predictors. CSU generates significant economic gains for a mean-variance investor with annualized utility gain of 7.92% and a Sharpe ratio of 1.19. The predictability of CSU is better in good than bad times, and a bivariate combination forecast using CSU with one of Goyal and Welch (2008) variables produces annual out-of-sample R^2 ranging from 16.22% to 42.88%. A vector autoregression decomposition shows that the source of predictability mainly comes from a cash flow channel.

In order to improve the dynamic assessment of financial market interdependencies, we develop a new Markov switching approach to multivariate volatility modelling. More specific, we take advantage of the flexible copula multivariate GARCH model of Lee and Long (2009), and allow state dependence with regard to the dependence structure governed by copula functions. We show some asymptotic features of the new model and motivate a two-step approach to maximum likelihood (ML)-estimation. As an empirical illustration, we consider a bivariate series comprising the returns of a high-yield equity index (MSCI World Developed Markets) and a traditional safe-haven asset (gold), and compare the goodness-of-fit of the new model with existing multivariate GARCH approaches. The new model offers advantages when it comes to detect and depict flows between financial assets in order to reduce portfolio risks in extreme market situations. We find that the suggested Markov switching generalization of the copula-MGARCH model of Lee and Long (2009) benefits from capturing structural changes in the non-linear dependence patterns, and helps to uncover flight-to-safety effects in times of economic turmoil.

We present new estimates of the causal effect of homeownership on residential relocation. In theory, risk in individuals' lifetime budgets discourages homeownership, but the risk of future income shocks should not directly affect current relocation decisions. We thus use estimates of workers' lifetime-budget risk, conditional on their current income risk, to obtain independent variation in homeownership that does not directly predict relocation. Estimates from bivariate probits corroborate this strategy and imply that homeownership reduces workers' probability of moving within the next two years by about 30 percentage points.

This paper provides new evidence on the relationship between public debt and economic growth in Brazil. We used Granger causality tests, in multivariate and bivariate analyses using respectively VEC and ARDL methodologies, and monthly data over the period 1998:1-2019:11. We find that: i) debt-to-GDP and GDP growth rate have a bi-directional Granger causality relationship; ii) debt can improve growth in the short run and becomes harmful in the long run; iii) GDP growth always reduces debt, both in the short and long run; iv) the dynamic between debt and growth in the long run is influenced by the inflation rate, exchange rate and the Emerging Markets Bond Index Plus (Embi+). info:eu-repo/semantics/publishedVersion

The paper investigates the export-led growth hypothesis for four South Asian countries e.g. Bangladesh, China, India and Myanmar (BCIM) using PMG regression technique and Pairwise DH Panel Causality tests over the years 1980-2017. Employing the bivariate (GDP and exports), the trivariate (GDP, exports and exchange rate; and the multivariate (GDP, exports, exchange rate and gross government consumption expenditure and investment) models, the study finds that exports have positive impact on the GDP growth in all BCIM economies in the long run. However, DH Panel Causality tests show bidirectional causal relationship between exports and GDP, implying that export-led growth hypothesis is stable in BCIM economies. In this backdrop, policy makers of these countries should continue the existing momentum of export promotion and search for new destinations by diversifying both export markets and commodities including services to reach spectacular growth trajectory.

We introduce a novel way of modeling the dependence of coupled lifetimes, for the pricing of joint and survivor annuities. Using a well-known Canadian data set, our results are analyzed and compared with the existing literature, mainly relying on copulas. Based on urn processes and a one-factor construction, the proposed model is able to improve its performances over time, in line with the machine learning paradigm, and it also allows for the use of experts' judgements, to complement the empirical data.

This paper builds on Louis Bachelier model for option pricing work by the author. The focus is to generalise the option model for where both assets are price uncertain, adapting the bivariate normal to the model; the paper also works on defining the underlying asset values based on this model, in doing so proposes the option definition be revised to recognise as a contract to ‘complete’ a purchase or sale transaction. In applying the model to the underlying asset values the question on attributing the instability coefficient arises and a solution is proposed implying a revision within the pricing model for this purpose, also the necessary question of the appropriate rate is addressed.

Using a bivariate expected utility framework, we develop a two-period model where households determine, in the presence of risks, the parents' migration duration when children are left behind. Our model suggests that the optimal migration duration may respond differently to an increase in a given risk. We provide conditions under which it is optimal for households to decrease the parents' migration duration despite an income risk in the place of origin, and to increase it even though the income in the place of destination is risky. The idea of preference for "harm disaggregation" is used to explain the results. In the absence of uncertainty, we also show the role of the interaction between child human capital and wealth in the household's utility function in determining the optimal migration duration of parents. Empirical implications of this analysis are presented in the last part of the paper.

SummaryBackgroundPublic health efforts to determine population infection rates from coronavirus disease 2019 (COVID-19) have been hampered by limitations in testing capabilities and the large shares of mild and asymptomatic cases. We developed a methodology that corrects observed positive test rates for non-random sampling to estimate population infection rates across U.S. states from March 31 to April 7.MethodsWe adapted a sample selection model that corrects for non-random testing to estimate population infection rates. The methodology compares how the observed positive case rate vary with changes in the size of the tested population, and applies this gradient to infer total population infection rates. Model identification requires that variation in testing rates be uncorrelated with changes in underlying disease prevalence. To this end, we relied on data on day-to-day changes in completed tests across U.S. states for the period March 31 to April 7, which were primarily influenced by immediate supply-side constraints. We used this methodology to construct predicted infection rates across each state over the sample period. We also assessed the sensitivity of the results to controls for state-specific daily trends in infection rates.ResultsThe median population infection rate over the period March 31 to April 7 was 0.9% (IQR 0.64 1.77). The three states with the highest prevalence over the sample period were New York (8.5%), New Jersey (7.6%), and Louisiana (6.7%). Estimates from mod-els that control for state-specific daily trends in infection rates were virtually identical to the baseline findings. The estimates imply a nationwide average of 12 population infections per diagnosed case. We found a negative bivariate relationship (corr. = -0.51) between total per capita state testing and the ratio of population infections per diagnosed case.InterpretationThe effectiveness of the public health response to the coronavirus pandemic will depend on timely information on infection rates across different regions. With increasingly available high frequency data on COVID-19 testing, our methodology could be used to estimate population infection rates for a range of countries and subnational districts. In the United States, we found widespread undiagnosed COVID-19 infection. Expansion of rapid diagnostic and serological testing will be critical in preventing recurrent unobserved community transmission and identifying the large numbers individuals who may have some level of viral immunity.FundingSocial Sciences and Humanities Research Council.

We analyze the extent of comovement between daily price returns of nine major cryptocurrencies during the first three main phases of their development, from April 2013 to November 2018. We assess its evolution using bivariate and multivariate modeling approaches and detect pronounced time variation. Generally, comovement is initially low and positive, but increases between early 2017 and late 2018. We then adopt a right-tail version of the Augmented Dickey-Fuller unit root test to identify periods of mildly explosive behavior (statistical instability) in the Network Value to Transactions (NVT) ratio (a measure of the dollar value of cryptocurrency transaction activity relative to network value) of six cryptocurrencies. We show evidence of significant mild explosiveness in all of them. At the end of 2017 and in 2018, several cryptocurrencies experience often simultaneous instability associated with rising NVT ratios. Instability is a dominant feature of these markets.

The national accounts provide a coherent and exhaustive description of the current state of the economy, but are available at the quarterly frequency and are released with a nonignorable publication lag. The paper illustrates a method for nowcasting and forecasting the sixteen main components of Gross Domestic Product (GDP) by output and expenditure type at the monthly frequency, using a high-dimensional set of monthly economic indicators spanning the space of the common macroeconomic and financial factors. The projection on the common space is carried out by combining the individual nowcasts and forecasts arising from all possible bivariate models of the unobserved monthly GDP component and the observed monthly indicator. We discuss several pooling strategies and we select the one showing the best predictive performance according to a pseudo-real-time forecasting experiment. Monthly GDP can be indirectly estimated by the contemporaneous aggregation of the value added of the different industries and of the expenditure components. This enables the comparative assessment of the indirect nowcasts and forecasts vis-a-vis the direct approach and a growth accounting exercise. Our approach meets the challenges posed by the dimensionality, since it can handle a large number of time series with a complexity that increases linearly with the cross-sectional dimension, while retaining the essential heterogeneity of the information about the macroeconomy. An application to the Italian case leads to several interesting discoveries concerning the time-varying predictive content of the information carried by the monthly indicators.

Gross domestic product (GDP) is the most comprehensive and authoritative measure of economic activity. The macroeconomic literature has focused on nowcasting and forecasting this measure at the monthly frequency, using related high-frequency indicators. We address the issue of estimating monthly GDP using a large-dimensional set of monthly indicators, by pooling the disaggregate estimates arising from simple and feasible bivariate models that consider one indicator at a time in conjunction to GDP. Our base model handles mixed-frequency data and ragged-edge data structure with any pattern of missingness. Our methodology enables to distil the common component of the available economic indicators, so that the monthly GDP estimates arise from the projection of the quarterly figures on the space spanned by the common component. The weights used for the combination reflect the ability to nowcast quarterly GDP and are obtained as a function of the regularized estimator of the high-dimensional covariance matrix of the nowcasting errors. A recursive nowcasting and forecasting experiment with data on euro area GDP illustrates that the optimal weights adapt to the information set available in real time and vary according to the phase of the business cycle.

We disentangle liquidity-constrained default and the incentives for strategic default using Deep Neural Network (DNN) methodology on a proprietary Trepp data set of commercial mortgages. Our results are robust (insensitive) to severe Financial Crisis (2008) and plausible economic catastrophe ensuing from COVID-19 pandemic (2020-2021). We demonstrate an identification strategy to retrieve the motive of default from observationally equivalent delinquency classes by bivariate analysis of default rate on Net operating income (NOI) and Loan-to-Value (LTV). NOI, appraisal reduction amount, prepayment penalty clause, balloon payment amongst others co-determine the delinquency class in highly nonlinear ways compared to more statistically significant variables such as LTV. Prediction accuracy for defaulted loans is higher when DNN is compared with other models, by increasing flexibility and relaxing the specification structure. These findings have significant implications for investors, rating agencies and policymakers.

We present a new modelling framework for the bi-variate hidden Markov model. The proposed specification is composed by five latent Markovian chains which drive the evolution of the parameters of a bi-variate Gaussian distribution. The maximum likelihood estimator is computed via an expectation conditional maximization algorithm with closed form conditional maximization steps, specifically developed for our model. Identification of model parameters, as well as consistency and asymptotic Normality of the maximum likelihood estimator are discussed. Finite sample properties of the estimator are investigated in an extensive simulation study. An empirical application with the bi-variate series of US stocks and bond returns illustrates the benefits of the new specification with respect to the standard hidden Markov model.

In this paper we document how the dynamics of linkages between major exchange rates changes during a day, depending on the activity of different groups of traders, and show the impact of important events and news on the dependence structures. The subject of analysis are linkages between the exchange rates EUR/USD, AUD/USD, GBP/USD and NZD/USD. For each hour of the day, we model the conditional dependence between the daily returns calculated at that time. The analysis is performed separately for bid and ask prices, which enables us to obtain some results concerning the sellers and buyers behavior. The dynamics of the conditional dependence is modeled by means of bivariate Markov-switching copula models, and the strength of the linkages is described by means of dynamic Spearman’s rho coefficients. The rankings of the strength of the linkages, depending on the hour, which we obtain using the model confidence set methodology, can be useful in trade decision-making in the FOREX market.

The national accounts provide a coherent and exaustive description of the current state of the economy, but are available at the quarterly frequency and are released with a nonignorable publication lag. The paper proposes and illustrates a method for nowcasting and forecasting the sixteen main components of Gross Domestic Product (GDP) by output and expenditure type at the monthly frequency, using a high-dimensional set of monthly economic indicators spanning the space of the common macroeconomic and financial factors. The projection on the common space is carried out by combining the individual nowcasts and forecasts arising from all possible bivariate models of the unobserved monthly GDP component and the observed monthly indicator. We discuss several pooling strategies and we select the one showing the best predictive performance according to a pseudo real time forecasting experiment. Monthly GDP can be indirectly estimated by the contemporaneous aggregation of the value added of the different industries and of the expenditure components. This enables the comparative assessment of the indirect nowcasts and forecasts vis-a-vis the direct approach and a growth accounting exercise. Our approach meets the challenges posed by the dimensionality, since it can handle a large number of time series with a complexity that increases linearly with the cross-sectional dimension, while retaining the essential heterogeneity of the information about the macroeconomy. The application to the Italian case leads to several interesting discoveries concerning the time-varying predictive content of the information carried by the monthly indicators.

We test and report on time series modelling and forecasting using several U.S. Leading Economic Indicators (LEI) as an input to forecasting real U.S. GDP and the unemployment rate. These time series have been addressed before, but our results are more statistically significant using more recently developed time series modelling techniques and software. Montgomery, Zarnowitz, Tsay, and Tiao (1998) modeled the U.S. unemployment rate as a function of the weekly unemployment claims time series, 1948 – 1992. In this replication case study, we apply the Hendry and Doornik automatic time series PC-Give (AutoMetrics) methodology to the well-studied macroeconomics series, U.S. real GDP and the unemployment rate. The Autometrics system substantially reduces regression sum of squares measures relative to traditional variations on the random walk with drift model. The LEI are a statistically significant input to real GDP. A similar conclusion is found for the impact of the LEI and weekly unemployment claims series leading the unemployment rate series. We tested the forecasting ability of best univariate and best bivariate models over 60- and 120-period rolling windows and report considerable forecast error reductions. The adaptive averaging autoregressive model forecast ADA-AR and the adaptive learning forecast, ADL, produced the smallest root mean square errors and lowest mean absolute errors.

Background: The Coronavirus Disease 2019 (COVID-19) pandemic impacts each country and region differently as countries and regions vary in terms of socioeconomic capacity, healthcare systems capacity, and pre-existing population characteristics. In this study, we analysed the associations of country and region-level attributes with four COVID-19-related outcomes after controlling for testing response by delineated classes of countries and regions. Methods: Country and region-level data of the exposures and COVID-19-related outcomes were obtained from several sources. Two hundred eighteen countries and regions were delineated into three classes using latent class analysis (LCA) based on the following variables: total tests performed per million of the population, current health expenditure per capita, and International Health Regulations (IHR) core capacity index. Bivariate analysis and multivariable linear regression were conducted to detect the associations of country and region-level attributes with COVID-19-related outcomes after controlling for testing response by class. Findings: LCA revealed three classes of countries which we labelled post-hoc as low testing, moderate testing, and high testing. Multivariable linear regression revealed that measures of globalisation, such as the international migrant stock and the number of air travel passengers reported, were positively associated with both total COVID-19 cases and deaths. We also found that democracy, measured through the Freedom in the World index, was negatively associated with total COVID-19 cases per million of the population and positively associated with total COVID-19 deaths. Interpretation: Our findings show that countries and regions with a large migrant stock and air travel, as well as democratic governance structures, may have poorer COVID-19 outcomes, and there is a need for the re-evaluation of their pandemic response. Funding: No funding to declare. Declaration of Interests: None.

User satisfaction is a critical determinant of information systems success. Prior research has long conceptualized it as a bipolar continuum with a “neutral” midpoint and “extremely dissatisfied” and “extremely satisfied” as endpoints. Therefore, the bipolar view imposes the constraint that an increase in satisfaction implies an equal and opposite decrease in dissatisfaction. Consequently, a key limitation of the bipolar conceptualization is its inability to account for simultaneous processing of positivity and negativity, i.e., ambivalence. A bivariate perspective relaxes this constraint, permitting the representation of mixed feelings, which allows potential additional insights. It represents satisfaction and dissatisfaction as distinct unipolar constructs each ranging from “neutral” to “extremely satisfied” or “extremely dissatisfied”, respectively. Users commonly experience mixed feelings, and the bipolar approach discards potentially useful information about the true affective state and distinct antecedents and consequences of satisfaction and dissatisfaction. Results of our survey (n=214) support the unipolar conceptualization. Unipolar satisfaction and dissatisfaction are moderately correlated -0.48, well below the -1.00 implied by the bipolar view. Unipolar satisfaction and dissatisfaction have unique and distinct effects on behavioral intention. Bipolar satisfaction explains no additional variance beyond the unipolar constructs. Together, these findings suggest that the unipolar conceptualizations can better represent user satisfaction and dissatisfaction. This study highlights the significance of ambivalence, advances the understanding of user satisfaction and dissatisfaction as distinct unipolar constructs, and provides a basis for new research into the potentially differential relationships to key antecedents and consequences in nomological networks relating actionable design and implementation actions to user behavioral outcomes.

In this paper, we investigate the effect of the level of English skills on the labour market outcomes of Turkish women, using data from the Adult Education Survey of 2007. By adopting a bivariate equation framework, we jointly model the effect of English skills on labour market status and, conditional on being a wage earner, on monthly earnings and occupational status. The multinomial equation that explains labour market status allows for a different effect of language knowledge on the probability of being employed, unemployed but actively looking for a job, an unpaid family worker or involved in household tasks. The results indicate that being proficient in English is conditionally associated with a higher probability of being employed as a wage earner and, to a lesser extent, unemployed but looking for a job, whereas it decreases the likelihood of being involved in household tasks. Moreover, there is a significant conditional correlation between having a high level of skills in English and earnings, which is only modestly reduced when job-related variables and (especially) occupation dummies are included as additional controls. Indeed, being proficient in English barely affects occupational status when selection into employment status is controlled for. Therefore, the knowledge of foreign languages (in this case English) seems to stimulate labour market participation and earnings capacity, but does not substantially affect the occupational position of women in the Turkish labour market.

Commonly used tests to assess evidence for the absence of autocorrelation in a univariate time series or serial cross-correlation between time series rely on procedures whose validity holds for i.i.d. data. When the series are not i.i.d., the size of correlogram and cumulative Ljung–Box tests can be significantly distorted. This paper adapts standard correlogram and portmanteau tests to accommodate hidden dependence and nonstationarities involving heteroskedasticity, thereby uncoupling these tests from limiting assumptions that reduce their applicability in empirical work. To enhance the Ljung–Box test for non-i.i.d. data, a new cumulative test is introduced. Asymptotic size of these tests is unaffected by hidden dependence and heteroskedasticity in the series. Related extensions are provided for testing cross-correlation at various lags in bivariate time series. Tests for the i.i.d. property of a time series are also developed. An extensive Monte Carlo study confirms good performance in both size and power for the new tests. Applications to real data reveal that standard tests frequently produce spurious evidence of serial correlation.

This paper proposes a new approach to the analysis of the reference cycle turning points, defined on the basis of the specific turning points of a broad set of coincident economic indicators. Each individual pair of specific peaks and troughs from these indicators is viewed as a realization of a mixture of an unspecified number of separate bivariate Gaussian distributions whose different means are the reference turning points. These dates break the sample into separate reference cycle phases, whose shifts are modeled by a hidden Markov chain. The transition probability matrix is constrained so that the specification is equivalent to a multiple changepoint model. Bayesian estimation of finite Markov mixture modeling techniques is suggested to estimate the model. Several Monte Carlo experiments are used to show the accuracy of the model to date reference cycles that suffer from short phases, uncertain turning points, small samples and asymmetric cycles. In the empirical section, we show the high performance of our approach to identifying the US reference cycle, with little difference from the timing of the turning point dates established by the NBER. In a pseudo real-time analysis, we also show the good performance of this methodology in terms of accuracy and speed of detection of turning point dates.

We construct a bivariate factor of political stability and economic policy confidence and show that it commands a significant premium of up to 15% per annum, in the global, developed, and emerging markets, robust to ICAPM, Fama-French five-factor model, Carhart, and ICAPM Redux. We propose an international capital asset pricing model incorporating the political factor, and test global and local estimations in developed and emerging economies. The model explains up to 77% of cross-sectional returns, has good predictive power, in several tests it performs better than the benchmark models in pricing equity indices and explains up to an incremental 25% of cross-sectional returns and is robust out of sample.

Using real-time data from 1985:Q1-2017:Q3 and simple VAR models, we show that there is substantial pay-off in combining credit supply indicators with house prices for forecasting real economic activity in the U.S. Consistent with the findings in the literature, we show that the forecasts from a bivariate VAR model of real activity and credit conditions dominate the forecasts from univariate model of real activity. The most interesting finding of the paper is that once real house price growth is added to the bivariate VAR model of real activity and credit conditions, the forecasting performance improves significantly. The forecasts from the model that contains credit supply indicator and real house price growth are also competitive with the forecasts of the Survey of Professional Forecasters. These results provide further evidence in support of the recent theoretical and empirical research on dynamic relationship between housing market and credit conditions and its role in explaining real economic activity fluctuations in the US.

Recently Chiba and Kobayashi (2013) have proposed the Lagrange multiplier (LM) test for the null hypothesis that volatilities of two asset return processes are driven by only one stochastic volatility (SV) process in a bivariate SV model. They apply their LM test to Asian stock market index returns, and find that the null hypothesis is not rejected for several pairs of those returns. They, however, derive the test statistic under an unconventional assumption that the conditional distribution of log squared return is normally distributed conditional on the SV, which seems inappropriate for a model of financial assets returns. This paper develops their analysis in two aspects. First, by a method of simulation, we examine the performance of their LM test under a conventional (bivariate) SV model in that each return (not log squared return) follows a normal distribution conditional on the SV. Second, because the null hypothesis examined in Chiba and Kobayashi (2013) is restrictive for many financial time series, we propose two LM tests for less restrictive but plausible null hypotheses. Our simulation study demonstrates that even for the conventional SV model, the actual size of their LM test is reasonably close to the nominal sizes and its power is high enough so that their LM test is useful for practical applications. Moreover, our empirical analysis with newly proposed LM tests finds that for many Asian stock market index returns, although their volatility processes themselves are not identical, they are likely to be driven by a common (or perfectly positively correlated) shock.

In this note, we build upon the asymptotic theory for GARCH processes, considering the general class of augmented GARCH(p, q) processes. Our contribution is to complement the well-known univariate asymptotics by providing a bivariate functional central limit theorem between the sample quantile and the r-th absolute centred sample moment. This extends existing results in the case of identically and independently distributed random variables. We show that the conditions for the convergence of the estimators in the univariate case suffice even for the joint bivariate asymptotics. We illustrate the general results with various specific examples from the class of augmented GARCH(p, q) processes and show explicitly under which conditions on the moments and parameters of the process the joint asymptotics hold.

In this paper we apply a novel approach to identifying the qualitative judgement of the rating committee in sovereign credit ratings. We extend the traditional regression with new measures - sentiment and subjectivity scores - obtained by textual sentiment analysis methods. By using an ordered logit with random effects for 98 countries in the period from 1996 to 2017, we find evidence that the subjectivity score provides additional information not captured by previously identified determinants of sovereign credit ratings, even after controlling for political risk, institutional strength and potential bias. The results from the bivariate and multivariate analysis confirm differences in textual sentiment between emerging markets and advanced economies, as well as before and after the 2008 global financial crisis.

How accurately can final-year students majoring in statistics, physics, and finance label the vertical axis of a normal distribution, explain their label, identify units, and answer a question about the impact of horizontal-axis rescaling? Our survey finds that only 27 out of 148 students surveyed (i.e., 18.2%) could label the vertical axis of the normal distribution correctly, and of these, only five students (i.e., 3.4%) could explain their label. Performance on individual survey questions differed by degree program, as might be expected, but overall survey performance varied very little, ranging between only 8.8% and 12.5% of survey questions answered correctly across degree programs. Common misconceptions included labeling the vertical axis as "probability," "count," or "frequency." To address these demonstrated gaps in statistics education, we give counterexamples to show why these labels cannot be correct; we explain why "probability density" is the correct label; and we give an intuitive explanation of probability density and its units. We also discuss the impact of horizontal-axis rescaling, and we indicate how the units of probability density change if the probability density function is for a bivariate or trivariate distribution instead of a univariate distribution. This paper is intended for all levels of statistical education.

This paper extends the ongoing literature on the macroeconomic effects of money supply volatility. We use monthly data for the USA and a bivariate, Markov switching, structural vector error correction model that is modified to accommodate generalized autoregressive conditional heteroscedasticity-in-mean errors to isolate the effects of money growth volatility on output growth. The model allows us to study how monetary uncertainty affects economic growth across different macroeconomic regimes.

We introduce a simple and intuitive approach of modeling and forecasting correlations for use in portfolio optimization. The model is composite in nature and consists of elements based on a bivariate realized volatility model. Importantly, our framework allows for volatility spill-overs between assets which provide an edge compared to competing models when forming portfolios. We apply the model to high-frequency data for commodity markets and demonstrate significant economic gains for an investor basing portfolio decisions on our modeling framework. This gain is significant in economic terms, even after imposing realistic constraints on short selling and portfolio turnover.

This paper investigates the nature of the linkage that exist between the agricultural sector and industrial sector in Zimbabwe using unrestricted bivariate Vector Autoregressive (VAR) model. Using annual time series macroeconomic data for the periods between 1990 and 2015, obtained from the WorldBank.org, we controlled for structural blips and mean-shifts by employing structural break dummies following suggestions by Zivot and Andrews (1992) and Perron (1997). Using a single lag length period obtained from Akaike’s information criterion, we performed the unit root test on the modified Augmented Dickey Fuller specifications, controlling for trend, in level and first difference. We observed that the series are weakly stationery integrated of order 1 [I(1)]. Results and post-estimation diagnostics from the VAR system including autocorrelation, residual normality and stability tests confirm the existence of a stable but weak relationship between industrial and agricultural activities in Zimbabwe. However, we found no evidence to suggest that industry depends on agriculture. To the contrary, Granger causality tests confirmed that the joint lag values of industry cause agriculture. Furthermore, innovations in industry had a relatively more positive shock impact in agriculture than the other way around suggesting that more responsive agriculture to impulse in industry.

We propose a new bivariate nonnegative integer-autoregressive (BINAR) model for count process data. We first generalize the existing BINAR(1) model by allowing for dependence between different thinning operators. The extended family allows for intuitive interpretation, as well as tractable properties in terms of aggregation and stationarity. Then we also introduce higher order BINAR(p) and BINAR(∞) dynamics allowing for more flexible serial correlation pattern. So far, the literature has considered the standard BINAR(1) model and its potential extensions to be rather computationally intractable. Our biggest contribution is to show that the proposed extended BINAR family allows for (quasi-)closed-form predictive densities, which significantly facilitates non-linear forecasting and likelihood based estimation. Finally, a BINAR(∞) model with memory persistence is applied to mutual fund purchase/redemption order counts.

This paper develops a new positional momentum management strategy and introduces a new positional liquidity management strategy. The approach relies on the expected ranks of asset returns and trade volume changes predicted from a bivariate Vector Autoregressive (VAR) model. The new methods are applied to a panel data of 1330 stocks traded on the NASDAQ between 1999 and 2016. The new prediction-based positional momentum strategy with bivariate ranks is shown to outperform the standard momentum strategy and the equally weighted portfolio. This suggests that volume ranks help improve the performance of a positional momentum portfolio. Moreover, the positional liquidity portfolios are shown to produce even higher average and cumulative returns over time than the positional momentum portfolios based on bivariate ranks.

Using daily data for eight major cryptocurrencies and bivariate extreme value theory (peaks-over-threshold method), this study examines the extreme dependence between returns and trading volumes in the cryptocurrency market. It is shown that, irrespective of the cryptocurrency under consideration, the extreme correlation between return and volume decreases as we move towards the distribution tails, supporting previous claims of cryptocurrencies resembling assets. We also find evidence of asymmetric return-volume relationship in the cryptocurrency market, as a result of discrepancies in the correlation between positive and negative return exceedances across all the cryptocurrencies. Our results have significant implications for better understanding the activity of market participants during extreme events in cryptocurrency markets.

Do countries with higher levels of national IQ experience less volatility in the growth of real economic output compared with lower-IQ countries? This issue has not been addressed. Using a large sample of countries, a simple bivariate correlation indicates that IQ and economic volatility are negatively related: the correlation is -0.54, significant at the five percent level of significance. Estimating a regression model of volatility, one that includes IQ with a number of control variables, the estimated coefficient on IQ is negative and significant. On average, a one-standard deviation increase in IQ is associated with about a 30 percent reduction in economic volatility. The evidence indicates that higher IQ countries tend to have more stable economies.

Long memory is a stylized fact found in most financial return series. In this paper, we seek to examine the impact of the presence of long memory on the dependence structure. First, we fit the multivariate dependence structure using R-vine copulas for pairs of raw and filtered returns. Second, we discuss whether or not changes in the fitted dependence may be driven by long memory. Based on the comparison results, we found that filtered returns of Dow Jones sub-indexes capture higher dependence in the conditional dependence structure. However, they capture lower dependence in bivariate dependence. Thus, the true degree of dependence is masked and such information is crucial for hedging and portfolios management.

The Pretrial Risk Assessment (PTRA) instrument was developed for use in the U.S. federal pretrial system. Specifically, this instrument was constructed to help federal officers assess the likelihood that defendants will commit pretrial violations including being re-arrested for any or violent crimes, failing to make court appearances, or having a revocation while on pretrial release. While previous studies have demonstrated the PTRA’s predictive validity, these efforts primarily used development and validation samples and did not investigate the PTRA for predictive bias by defendant demographic characteristics. The current research evaluates the PTRA’s capacity to predict various forms of pretrial violations on 85,369 defendants with officer completed PTRA assessments. Bivariate and multivariate models were estimated by race, ethnicity, and sex. Results show that the PTRA performs well at predicting pretrial violations as the area under the receiver operating characteristic curve ranged from 0.65 to 0.73 depending upon the subsamples and outcomes being predicted. Moreover, the PTRA predicted new criminal arrest activity equally well between non-Hispanic whites and blacks, while for Hispanics and females, findings show the instrument validly predicting re-arrest activity with some evidence of overprediction depending upon the outcome being examined.

The study evaluates the relationship of Pakistan Stock Exchange 1 (PSX) with progressing and well-established equity markets from 1997 to 2014. The Johansen’s multivariate cointegration tests i.e. maximum eigenvalue & trace statistics proposes three co-integrating vectors at 5% critical values with the progressing and well-established equity markets. Furthermore, vector correction model implies that PSX is positive and statistically robust in relation to India at lag 2, while negative and statistically significant in relation to China at lag 1 and USA at lag 2. Though, the bivariate co-integration trace and maximal eigenvalues recommends that the PSX individually have no relationship with other markets. This study further recommends that PSX is extremely unpredictable stock market in between from 44% to -24%. It might be desired by risky investors.

This paper proposes a novel copula-based local Kendall’s tau framework to uncover richer nonlinear local dependence between two financial return series. This framework nests the concepts of global dependence, tail dependence and local dependence. Closed form solutions of local Kendall’s tau in terms of copula link local dependence with their global dependence structure together, providing a generalized framework for investigating dependence between two return series. We further extend the copula-based local dependence framework to Spearman’s rho. Using this framework, we draw the local Kendall’s tau surfaces in different quadrants for some common used bivariate Archimedean copulas. Finally, we demonstrate the advantages of copula-based local Kendall’s tau relative to global Kendall’s tau with stock market data.

Making use of bivariate (α, β)-fractional power series expansion scheme, we provide an analytical solution to the spatial–temporal fractional Klein–Gordon equation that has many applications in physics such as quantum mechanics, solitons, and condensed matter physics. The twofold fractional derivative orders, namely α, β ∈ (0, 1], are described in the Caputo sense. Some examples are given to show the ability and efficiency of the proposed method for solving (non)linear (non)homogeneous Klein–Gordon equation in fractal space. The obtained closed-form solutions are found to be in a consensus with the exact solutions exist in the literature when α, β → 1, which demonstrates the feasibility and validity of the proposed method.

We address the issue of semiparametric efficiency in the bivariate regression problem with a highly persistent predictor, where the joint distribution of the innovations is regarded an infinite-dimensional nuisance parameter. Using a structural representation of the limit experiment and exploiting invariance relationships therein, we construct invariant point-optimal tests for the regression coefficient of interest. This approach naturally leads to a family of feasible tests based on the component-wise ranks of the innovations that can gain considerable power relative to existing tests under non-Gaussian innovation distributions, while behaving equivalently under Gaussianity. When an i.i.d. assumption on the innovations is appropriate for the data at hand, our tests exploit the efficiency gains possible. Moreover, we show by simulation that our test remains well behaved under some forms of conditional heteroskedasticity.

We study the sovereign bond market co-movements and spillovers within 10 EMU countries, the so-called “periphery” and “core” countries, during the period 1999:01 to 2016:07. Implementing Generalized Methods of Moments (GMM) within a panel setting and bivariate VAR analysis, we find that an increase in the lagged spreads of Italian and Austrian bonds negatively affect the spreads of the whole sample while the increase in the Irish, Portuguese, Belgian and French lagged yields increased the overall spreads. In the VAR analysis we find that spillover effects within the sample are mostly positive.