FORECASTING WITH SOCIAL MEDIA: EVIDENCE FROM TWEETS ON SOCCER MATCHES

Social media is now used as a forecasting tool by a variety of firms and agencies. But how useful are such data in forecasting outcomes? Can social media add any information to that produced by a prediction/betting market? We source 13.8 million posts from Twitter, and combine them with contemporaneous Betfair betting prices, to forecast the outcomes of English Premier League soccer matches as they unfold. Using a microblogging dictionary to analyze the content of Tweets, we find that the aggregate tone of Tweets contains significant information not in betting prices, particularly in the immediate aftermath of goals and red cards. (JEL G14, G17)     

In search of the wage-labour/service contract: new evidence on the validity of the Goldthorpe class schema

In this paper we examine new empirical evidence on the coherence and magnitude of the main classes in the Goldthorpe class schema. Particular attention is paid to issues that have recently been a source of academic dispute: the coherence and size of the service class and the distinction between the service class and intermediate classes. Using recently available British data collected by the Office for National Statistics we examine: (i) the extent to which measures of class-relevant job characteristics are empirically discriminated by the categories of the schema; (ii) the structure of a 'contract type' dimension of employment relations conceived of as a categorical latent variable; and (iii) the association between this latent variable and both the Goldthorpe class schema and a related measure socio-economic group (SEG). We find that the data are consistent with the existence of a three category latent 'contract type' variable largely corresponding to the notions of service, intermediate and wage-labour contracts explicit in discussions of the theoretical rationale for the Goldthorpe schema. We further find a substantial degree of fit between the latent 'contract types' and the schema. However, the service class fault line appears to lie within class I and II of the schema rather than between them and the intermediate classes which suggests a revised, smaller service class would better capture the reality of the contemporary British occupational structure.     

INFERENCE USING QUALITATIVE AND QUANTITATIVE INFORMATION WITH AN APPLICATION TO MONETARY POLICY

I propose a framework for drawing inferences about an unobserved variable using qualitative and quantitative information. Using this framework, I study the timing and persistence of monetary policy regimes and compute probabilistic measures of the qualitative indicator's reliability. These estimates suggest that (1) it is over one and one-half times more likely that monetary policy is not restrictive at any point in time, (2) Boschen and Mills's [1995] policy index is a reliable indicator of the stance of monetary policy, and (3) certain qualitative indicators of monetary policy improve interest rate forecasts that are based on linear forecasting models. (JEL C22, E52)     

ECONOMIC LOSSES DUE TO FORECASTING ERROR AND THE U.S. POPULIST MOVEMENT

A farmer's crop mix is affected by the expected relative prices of the crops. A price forecasting error results in economic loss from planning a suboptimal mix. A new method of estimating economic loss due to forecasting error indicates that economic loss increased during the height of the Populist movement and then decreased. Using data for Kansas counties from 1882 to 1907, I estimate agricultural crop mix functions using a SUR (Seemingly Unrelated Regression) procedure and calculate the economic loss due to forecasting error. Although new market opportunities must have made farmers better oth these nnnnrtunities increased the cost of price uncertainly.     

FORECASTING CRUDE OIL PRICE MOVEMENTS WITH OIL‐SENSITIVE STOCKS

This paper uses monthly data from 1984:M10 to 2012:M8 to show that oil‐sensitive stock price indices, particularly those in the energy sector, have strong power in predicting nominal and real crude oil prices at short horizons (1‐month‐ahead predictions), using both in‐ and out‐of‐sample tests. In particular, the forecasts based on oil‐sensitive stock price indices are able to outperform significantly the no‐change forecasts. For example, using the NYSE Arca (AMEX) oil index as a predictor, the 1‐month‐ahead forecasts for nominal crude oil prices reduce the mean squared prediction error by between 22% (for the West Texas Intermediate oil price) and 28% (for the Dubai oil price). Moreover, we find that the directional forecast based on the AMEX oil index is significantly better than a 50:50 coin toss. The novelty of this analysis is that it proposes a new and valuable predictor that both reflects timely market information and is readily available for forecasting the spot oil price.(JEL G17, Q43, Q47, C53)     

Sexual victimization and substance abuse in psychiatrically hospitalized adolescents

This article investigates the relationship between substance abuse and sexual abuse in a population of 260 psychiatrically hospitalized adolescents. Seven hypotheses are set forth to test a model that uses parental alcohol abuse, sexual abuse status, and gender as exogenous variables, perceived benefit of alcohol or drugs as an endogenous mediating variable, and substance abuse as the dependent variable. Using these variables, a path model was constructed and revised based on empirical testing. The revised model achieved an adjusted R2 of .38, thus explaining 38 percent of the variance in this sample's abuse of alcohol or drugs. The model suggests that within clinical populations, sexually abused adolescents should be screened for substance abuse, and attention should be given to parental alcohol abuse as well as the degree to which adolescents perceive benefits from their alcohol or drug use.     

The Demand for Credit Cards: Evidence from the Survey of Consumer Finances

We analyze data from the Survey of Consumer Finances estimate the response of credit card demand to standard price and income effects. We model credit card demand as a two-stage process, with consumers obtaining limits in the first stage and then borrowing some fraction of those limits in the second. We estimate this model with a nested tobit procedure. We also treat the demand for limits as one equation in a two-equation supply-demand model. We estimate this model with simple 2SLS, instrumenting for the price variable, the interest rate. The results of the first model suggest that most of the action in the market is in the demand for limits, not the demand for balances. (JEL D1 , G0 )     

FINANCIAL SECTOR WEAKNESS AND THE M2 VELOCITY PUZZLE

Deterioration in the link between M2 and GDP, along with large prediction errors, led the Federal Reserve to downgrade M2 as a reliable indicator in 1993. We argue that the financial condition of depository institutions was a major factor behind this unusual pattern of M2 growth. When constructing measures of M2 based on banks' and thrifts' capital positions, we obtain superior M2 forecasting results and a more stable relationship between M2 and the ultimate goals of policy. M2 may contain useful information when there are no major disturbances to depository institutions. (JEL E4 , E5 , G2 )     

The contribution of E.C. consumer surveys in forecasting consumer expenditures: An econometric analysis for four major countries

In this article we investigate the forecasting performance of alternative models of private consumption using the EEC consumer surveys. Two basic conclusions emerge from the study:(1) in absolute as well as in comparison with a standard economic model, consumption functions incorporating opinion variables perform surprisingly well given the important measurement problems (missing data, qualitative character of the responses, strong collinearity among responses), and(2) consumers' opinions are helpful guides only in very short-term forecasting (between 0 and 3 quarters).The article extends previous investigations both on the basic characteristics of opinion variables and on their relation with actual economic variables.     

Linking Migration Intentions with Flows: Evidence and Potential Use

In the absence of reliable, internationally available migration flow data necessary for statistical forecasting, policymakers increasingly turn to survey data on emigration intentions to evaluate future migration trends. The important assumption – i.e. that there is a measurable and systematic relationship between the intention to migrate and actual migration – has not been firmly established at the international level. We examine the association between estimated population averages of emigration intentions and official migration flow data based on data for more than 160 countries. The results show a strong association between emigration intentions and recorded bilateral flows to industrialized countries, as well as between intentions and aggregated out‐migration. The results provide policymakers with a reliability assessment of survey data on emigration intentions and encourage future attempts to incorporate survey data in formal statistical migration forecasting models.     

Improving Measurement of Workplace Sexual Identity Management

The purpose of this study was to advance measurement of sexual identity management for lesbian, gay, and bisexual workers. Psychometric properties of a revised version of the Workplace Sexual Identity Management Measure (WSIMM; Anderson, Croteau, Chung, & DiStefano, 2001) were examined on a sample of 64 predominantly White K‐12 teachers. Reliability and validity data support the usefulness of the revised WSIMM for measuring sexual identity management. Additional research is needed to improve measurement of passing strategies and to further examine dimensionality of sexual identity management.     

灰色模型在社会燃气事故预测中的应用

简要介绍灰色预测理论，以及GM（1，1）模型的建模过程。并应用灰色预测模型对南方某大型城市燃气公司管道燃气供应范围内的社会燃气事故死亡人数进行预测并实施检验。检验结果表明应用灰色预测模型预测社会燃气事故死亡人数的发展规律是可行有效的。     

Relative Distribution Methods

We present an outline of relative distribution methods, with an application to recent changes in the U.S. wage distribution. Relative distribution methods are a nonparametric statistical framework for analyzing data in a fully distributional context. The framework combines the graphical tools of exploratory data analysis with statistical summaries, decomposition, and inference. The relative distribution is similar to a density ratio. It is technically defined as the random variable obtained by transforming a variable from a comparison group by the cumulative distribution function (CDF) of that variable for a reference group. This transformation produces a set of observations, the relative data, that represent the rank of the original comparison value in terms of the reference group's CDF. The density and CDF of the relative data can therefore be used to fully represent and analyze distributional differences. Analysis can move beyond comparisons of means and variances to tap the detailed information inherent in distributions. The analytic framework is general and flexible, as the relative density is decomposable into the effect of location and shape differences, and into effects that represent both compositional changes in covariates, and changes in the covariate-outcome variable relationship.     

PREDICTING INFLATION: DOES THE QUANTITY THEORY HELP?

Various inflation forecasting models are compared for the period 1979–2003 using a simulated out-of-sample forecasting framework. Our findings are (1) M2 has marginal predictive content for inflation; (2) it is necessary to allow for the possibility that money, prices, and output are cointegrated; and (3) cointegration vector parameter estimation error is important when making out-of-sample forecasts. Consistent with previous work, we find a structural break in the early 1990s, but the break was easily detected and would not have affected out-of-sample inflation forecasts. Two Monte Carlo experiments that lend credence to our findings are also reported on.(JEL E31 , C32 )     

Control variables and causal inference: a question of balance

A common motivation for adding control variables to statistical models is to reduce the potential for spurious findings when analyzing non-experimental data and to thereby allow for more reliable causal inferences. However, as I show here, unless all potential confounding factors are included in an analysis (which is unlikely to be achievable with most real-world data-sets), adding control variables to a model in many circumstances can make estimated effects of the variable(s) of interest to the researcher on the dependent variable less accurate. Due to this fact, in some circumstances omitting control variables, even those that affect the dependent variable and are correlated with the variable(s) of interest, may allow for more accurate estimates of the effect(s) of the variable(s) of interest.     

Improved Regression Estimation of A Multivariate Relationship with Population Data on the Bivariate Relationship

Regression coefficients specify the partial effect of a regressor on the dependent variable. Sometimes the bivariate or limited multivariate relationship of that regressor variable with the dependent variable is known from population‐level data. We show here that such population‐level data can be used to reduce variance and bias about estimates of those regression coefficients from sample survey data. The method of constrained MLE is used to achieve these improvements. Its statistical properties are first described. The method constrains the weighted sum of all the covariate‐specific associations (partial effects) of the regressors on the dependent variable to equal the overall association of one or more regressors, where the latter is known exactly from the population data. We refer to those regressors whose bivariate or limited multivariate relationships with the dependent variable are constrained by population data as being "directly constrained." Our study investigates the improvements in the estimation of directly constrained variables as well as the improvements in the estimation of other regressor variables that may be correlated with the directly constrained variables, and thus "indirectly constrained" by the population data. The example application is to the marital fertility of black versus white women. The difference between white and black women's rates of marital fertility, available from population‐level data, gives the overall association of race with fertility. We show that the constrained MLE technique both provides a far more powerful statistical test of the partial effect of being black and purges the test of a bias that would otherwise distort the estimated magnitude of this effect. We find only trivial reductions, however, in the standard errors of the parameters for indirectly constrained regressors.     

Psychometric Properties of the Differentiation of Self Inventory‐Revised in Turkish Adults

The purpose of the current study was to examine the validity and reliability of (Journal of Marital and Family Therapy 2003, 29, 209) Differentiation of Self Inventory‐Revised (DSI‐R; Skowron & Schmit, 2003) in Turkish adults. The DSI‐R was translated, independently back‐translated, and revised. Two independent samples of adults over the age of 25 were used. The original 46‐item DSI‐R was not supported by the data derived from Sample 1 (n = 221). However, a revised 20‐item, four‐factor model fit the data well. This 20‐item model was subsequently cross‐validated with a second sample of Turkish adults (n = 187). Scale scores showed adequate internal consistency, 5‐week test–retest reliability, and satisfactory convergent and criterion‐related validity. It was concluded that Turkish DSI‐R (DSI‐T) is a valid and reliable measure to assess an individual's differentiation level. In light of the findings, implications for the use of the DSI‐T and ideas for future research are discussed.     

The contribution of opinion surveys in forecasting aggregate demand in the four main EC countries

This paper presents for the four main EC countries forecasting models of aggregate demand components based on various tendency surveys. Its objective is to work out practical models both in terms of data requirement and computation as the models are to be used regularly for very short-term forecasting. In spite of a great simplicity of the specifications, the regression results prove quite acceptable. Forecasting exercises compare reasonably well with the results of more elaborate procedures.     

Re-examining a Landmark Research Study: A Teaching Editorial

A landmark research study from the 1950s was reanalyzed. Part of the study's results were confirmed, but other parts were found to have been incompletely analyzed and therefore incorrectly reported. Subsequent scholars who reviewed the study often did not distinguish between the accurate and inaccurate parts of the study. Furthermore, two of the main hypotheses of the study were that one variable (A) was not related to another variable (B) and that variable B was not related to another variable (C). In fact, both null hypotheses, insofar as data could be reconstructed from the original study, could be rejected. A reanalysis is presented here to encourage students in the family field to be bold and not accept published reports “just because” but to evaluate them carefully, perhaps even reanalyzing the data when available. It is hoped that scholars who submit reviews of the literature to Marriage and Family Review will use similar care and attention to assessing the scholarly literature in their particular areas of interest.     

Statistical Methods and Graphical Displays for Analyzing How the Association Between Two Qualitative Variables Differs Among Countries, Among Groups, Or Over Time: A Modified Regression-Type Approach

Many interesting sociological questions pertain to how the association between two variables depends on a third variable. In sociological applications, the third variable often pertains to countries, to subgroups of a population, or to time periods. We propose a regression-type approach that specifies that the log-odds- ratios that describe the two-way association of interest are a linear function of latent scores for the third variable. Additive and multiplicative models currently in use by researchers are special cases of the regression-type model. To illustrate the utility of the regression-type approach, we apply this approach to analyze (1) data on occupational mobility in the United States, Britain, and Japan (comparing mobility in these countries) and (2) data on the association between religion and voting behavior in U.S. presidential elections from 1968 to 1992 (comparing this association in the different elections). We also introduce here graphical displays that can be used to obtain worthwhile information about goodness-of-fit and to aid in substantive interpretation.