http://repub.eur.nl/res/aut/2223/ List of Publications en http://repub.eur.nl/static-eur/img/logo.png http://repub.eur.nl http://repub.eur.nl/res/pub/37677/ 2012-03-01T00:00:00Z In this study we analyze daily data on television viewing in the Netherlands. We postulate hypotheses on supply and demand factors that could impact the amount of daily viewing time. Although the general assumption is that supply and demand often correlate, we see that for television this is only marginally the case. Especially diversity of program supply, often deemed very important in media markets, does not affect (positively or negatively) television viewing behavior. Most variation in television viewing can be attributed to habit and to regular events (e. g. weekends, Christmas) and to unexpected events (e. g. the 9/11 WTC attack). We also find that weather conditions interact with program types, so that, for example, in winter times people favor entertainment programs even more, suggesting that people use television for mood management. http://repub.eur.nl/res/pub/22110/ 2011-07-01T00:00:00Z This study examines the impact of daily atmospheric weather conditions on daily television use in the Netherlands for the period 1996-2005. The effects of the weather parameters are considered in the context of mood and mood management theory. It is proposed that inclement and uncomfortable weather conditions are associated with lower human mood, and that watching entertainment and avoiding informational programs may serve to repair such mood. We consequently hypothesize that people spend more time watching television if inclement and uncomfortable weather conditions (low temperatures, little sunshine, much precipitation, high wind velocity, less daylight) coincide with more airtime for entertainment programs, but that they view less if the same weather conditions coincide with more airtime devoted to information fare. We put this interaction thesis to a test using a time series analysis of daily television viewing data of the Dutch audience obtained from telemeters (T = 3,653), merged with meteorological weather station statistics and program broadcast figures, whilst controlling for a wide array of recurrent and one-time societal events. The results provide substantial support for the proposed interaction of program airtime and the weather parameters temperature and sunshine on aggregate television viewing time. Implications of the findings are discussed. http://repub.eur.nl/res/pub/13758/ 2005-05-02T00:00:00Z This paper considers the implementation of a non-stationary, heterogeneous Markov model for the analysis of binary dependent variables in a time series of repeated cross-sectional (RCS) surveys. The model offers the opportunity to estimate entry and exit transition probabilities and to examine the effects of time-constant and time-varying covariates on the hazards. We show how maximum likelihood estimates of the parameters can be obtained by Fishers method-of-scoring and how to estimate both fixed and time-varying covariate effects. The model is exemplified with an analysis of the labor force participation decision of Dutch and West German women using ISSP (and other) data from 10 annual Dutch surveys conducted between 1987 and 1996 and 7 annual West German surveys conducted between 1988 and 1994. Some open problems concerning the application of the model are discussed. http://repub.eur.nl/res/pub/13531/ 2002-01-01T00:00:00Z This paper discusses a nonstationary, heterogeneous Markov model designed to estimate entry and exit transition probabilities at the micro level from a time series of independent cross-sectional samples with a binary outcome variable. The model has its origins in the work of Moffitt and shares features with standard statistical methods for ecological inference. We outline the methodological framework proposed by Moffitt and present several extensions of the model to increase its potential application in a wider array of research contexts. We also discuss the relationship with previous lines of related research in political science. The example illustration uses survey data on American presidential vote intentions from a five-wave panel study conducted by Patterson in 1976. We treat the panel data as independent cross sections and compare the estimates of the Markov model with both dynamic panel parameter estimates and the actual observations in the panel. The results suggest that the proposed model provides a useful framework for the analysis of transitions in repeated cross sections. Open problems requiring further study are discussed. http://repub.eur.nl/res/pub/560/ 2002-01-01T00:00:00Z This paper presents a Markov chain model for the estimation of individual-level binary transitions from a time series of independent repeated cross-sectional (RCS) samples. Although RCS samples lack direct information on individual turnover, it is demonstrated here that it is possible with these data to draw meaningful conclusions on individual state-to-state transitions. We discuss estimation and inference using maximum likelihood, parametric bootstrap and Markov chain Monte Carlo approaches. The model is illustrated by an application to the rise in ownership of computers in Dutch households since 1986, using a 13-wave annual panel data set. These data encompass more information than we need to estimate the model, but this additional information allows us to assess the validity of the parameter estimates. We examine the determinants of the transitions from 'have-not' to 'have' (and back again) using well-known socio-economic and demographic covariates of the digital divide. Parametric bootstrap and Bayesian simulation are used to evaluate the accuracy and the precision of the ML estimates and the results are also compared with those of a first-order dynamic panel model. To mimic genuine repeated cross-sectional data, we additionally analyse samples of independent observations randomly drawn from the panel. Software implementing the model is available. http://repub.eur.nl/res/pub/1687/ 2001-08-08T00:00:00Z This paper outlines a nonstationary, heterogeneous Markov model designed to estimate entry and exit transition probabilities at the micro-level from a time series of independent cross-sectional samples with a binary outcome variable. The model has its origins in the work of Moffitt (1993) and shares features with standard statistical methods for ecological inference. We show how ML estimates of the parameters can be obtained by the method-of- scoring, how to estimate time-varying covariate effects, and how to include non-backcastable variables in the model. The latter extension of the basic model is an important one as it strongly increases its potential application in a wide array of research contexts. The example illustration uses survey data on American presidential vote intentions from a five-wave panel study conducted by Patterson (1980) in 1976. We treat the panel data as independent cross sections and compare the estimates of the Markov model with the observations in the panel. Directions for future work are discussed. http://repub.eur.nl/res/pub/2158/ 2001-01-01T00:00:00Z Introduces a series of articles on the analysis of cross sections. Issues involved in the analysis of time-series-cross-section (TSCS) data; Modeling of spatial effects, heterogeneity and TSCS data; Use of the Markov chain Monte Carlo and non-linear least-square methods for ecological inference. http://repub.eur.nl/res/pub/2159/ 2001-01-01T00:00:00Z This paper considers the implementation of a nonstationary, heterogeneous Markov model for the analysis of a binary dependent variable in a time series of independent cross sections. The model, previously considered by MOFFITT (1993), offers the opportunity to estimate entry and exit transition probabilities and to examine the effects of time-constant and time-varying covariates on the hazards. We show how ML estimates of the parameters can be obtained by Fisher's method-of-scoring and how to estimate both fixed and time-varying covariate effects. The model is exemplified with an analysis of the labor force participation decision of Dutch women using data from the Socio-economic Panel (SEP) study conducted in the Netherlands between 1986 and 1995. We treat the panel data as independent cross sections and compare the employment status sequences predicted by the model with the observed sequences in the panel. Some open problems concerning the application of the model are also discussed. http://repub.eur.nl/res/pub/12295/ 1999-01-01T00:00:00Z This paper is an empirical study to the effects of economic outcomes on party choice for the Netherlands. In the first part of the paper we employ a multinomial logit model to examine the links between voters' characteristics and party choice. The results suggest that there are long-run movements in party choice which are unlikely be the result of changing economic outcomes. In the second part, we use time series analysis to determine the effects of economic conditions on short-run and medium-run movements in votes shares. The estimations results provide support for the responsibility hypothesis and for the predictions of the partisan voter model that left-wing (right-wing) parties benefit (suffer) from favourable economic growth prospects. http://repub.eur.nl/res/pub/2153/ 1999-01-01T00:00:00Z This paper considers out-of-sample forecasting of left–right political orientations of party affiliates in the Netherlands, using weekly data from 973 independent national Dutch surveys conducted between 1978 and 1996. The orientations of left-wing and right-wing party affiliates tend to converge over time in the sense that the differences between the average positions tend to decline. The left–right series also reveal long-memory properties in the sense that shocks appear to be highly persistent. We develop forecasting models that account for these data features and we derive the relevant forecast intervals. http://repub.eur.nl/res/pub/1408/ 1997-01-01T00:00:00Z A time series (t=921) of weekly survey data on vote intentions in the Netherlands for the period 1978-1995 shows that the percentage of undecided voters follows a cyclical pattern over the election calendar. The otherwise substantial percentage of undecided voters decreases sharply in weeks leading up to an election and gradually increases afterwards. This paper models the dynamics of this asymmetric electoral cycle using artificial neural networks, with the purpose of estimating when the undecided voters start making up their minds. We find that they begin to decide which party to vote for nine weeks before a first order national parliamentary election and one to four weeks before a second order election, depending on the type of election (European Parliament, Provincial States, City-councils). The effect of political campaigns and the implications for political analysis are discussed. http://repub.eur.nl/res/pub/1417/ 1997-01-01T00:00:00Z -Theory- Two theories about trends in left-right political orientations are juxtaposed: the persistence theory claiming that left-right orientations are highly resistant to change versus the irrelevance theory anticipating a move of mass publics towards the center of the left-right continuum. -Hypotheses- The left-right ideological differences between the Dutch political parties have declined since the early 1980s. We therefore assume that the left-right political self-placements of the Dutch electorate have converged to the center position over time. -Methods- Descriptive statistics and fractionally integrated time series (ARFIMA) models were used to analyze data from 921 independent national Dutch surveys conducted between 1978 and 1995. -Results- The overtime distributions of left-right self-placement exhibit a depopulation of the left and right poles as people slowly gravitate to the center position. The aggregate orientations of religious and party affiliates also reveal a move to the common mid-point. Fractionally integrated time series models support the convergence thesis with right-most and left-most party affiliates converging most rapidly. However, the convergence we find may be part of a nonperiodic wave-like pattern were periods of convergence are alternated by periods of divergence. Future political conflicts may therefore again result in left-right political divergence. http://repub.eur.nl/res/pub/2096/ 1996-01-01T00:00:00Z This paper investigates convergence in left-right ideological positions in The Netherlands using cointegration techniques. Our sample consists of 765 weekly observations on those positions as well as on the corresponding political party preference. The time series data display nonstationary patterns in the sense that their means are not constant over time. Therefore, we rely on recently developed techniques in the analysis of multivariate nonstationary time series to study convergence. One of our results is that the ideological positions, when considered relative to a benchmark, can be described by trend-stationary processes. This means that we cannot reject the presence of convergence. Implications of this result are discussed. http://repub.eur.nl/res/pub/2122/ 1996-01-01T00:00:00Z