Marketing Mix Modeling Using PLS-SEM, Bootstrapping the Model Coefficients

Partial least squares structural equations modeling (PLS-SEM) uses sampling bootstrapping to calculate the significance of the model parameter estimates (e.g., path coefficients and outer loadings). However, when data are time series, as in marketing mix modeling, sampling bootstrapping shows inconsistencies that arise because the series has an autocorrelation structure and contains seasonal events, such as Christmas or Black Friday, especially in multichannel retailing, making the significance analysis of the PLS-SEM model unreliable. The alternative proposed in this research uses maximum entropy bootstrapping (meboot), a technique specifically designed for time series, which maintains the autocorrelation structure and preserves the occurrence over time of seasonal events or structural changes that occurred in the original series in the bootstrapped series. The results showed that meboot had superior performance than sampling bootstrapping in terms of the coherence of the bootstrapped data and the quality of the significance analysis.

Analysis of the Spatial Distribution of Stable Oxygen and Hydrogen Isotopes in Precipitation across the Iberian Peninsula

The isotopic composition of precipitation provides insight into the origin of water vapor, and the conditions attained during condensation and precipitation. Thus, the spatial variation of oxygen and hydrogen stable isotope composition (δp) and d-excess of precipitation was explored across the Iberian Peninsula for October 2002–September 2003 with 24 monitoring stations of the Global Network of Isotopes in Precipitation (GNIP), and for October 2004–June 2006, in which 13 GNIP stations were merged with 21 monitoring stations from a regional network in NW Iberia. Spatial autocorrelation structure of monthly and amount weighted seasonal/annual mean δp values was modelled, and two isoscapes were derived for stable oxygen and hydrogen isotopes in precipitation with regression kriging. Only using the GNIP sampling network, no spatial autocorrelation structure of δp could have been determined due to the scarcity of the network. However, in the case of the merged GNIP and NW dataset, for δp a spatial sampling range of ~450 km in planar distance (corresponding to ~340 km in geodetic distance) was determined. The range of δp, which also broadly corresponds to the range of the d-excess, probably refers to the spatially variable moisture contribution of the western, Atlantic-dominated, and eastern, Mediterranean-dominated domain of the Iberian Peninsula. The estimation error of the presented Iberian precipitation isoscapes, both for oxygen and hydrogen, is smaller than the ones that were reported for the regional subset of one of the most widely used global model, suggesting that the current regional model provides a higher predictive power.

Geostatistical screening of flood events in the groundwater levels of the diverted inner delta of the Danube River: implications for river bed clogging

The efficient operation of shallow groundwater (SGW) monitoring networks is crucial to water supply, in-land water protection, agriculture and nature conservation. In the present study, the spatial representativity of such a monitoring network in an area that has been thoroughly impacted by anthropogenic activity (river diversion/damming) is assessed, namely the Szigetköz adjacent to the River Danube. The main aims were to assess the spatial representativity of the SGW monitoring network in different discharge scenarios, and investigate the directional characteristics of this representativity, i.e. establish whether geostatistical anisotropy is present, and investigate how this changes with flooding. After the subtraction of a spatial trend from the time series of 85 shallow groundwater monitoring wells tracking flood events from 2006, 2009 and 2013, variography was conducted on the residuals, and the degree of anisotropy was assessed to explore the spatial autocorrelation structure of the network. Since the raw data proved to be insufficient, an interpolated grid was derived, and the final results were scaled to be representative of the original raw data. It was found that during floods the main direction of the spatial variance of the shallow groundwater monitoring wells alters, from perpendicular to the river to parallel with it for over a period of about two week. However, witht the passing of the flood, this returns to its original orientation in ~2 months. It is likely that this process is related first to the fast removal of clogged riverbed strata by the flood, then to their slower replacement. In addition, the study highlights the importance of assessing the direction of the spatial autocorrelation structure of shallow groundwater monitoring networks, especially if the aim is to derive interpolated maps for the further investigation or modeling of flow.

Autocovariance and autocorrelation structures of the generalised autoregressive moving average (GARMA(1,3;δ,1)) model

Generalized ARMA (GARMA) model is a new class of model that has been introduced to reveal some unknown features of certain time series data. The objective of this paper is to derive the autocovariance and autocorrelation structure of GARMA(1,3;δ,1) model in order to study the behaviour of the model. It is shown that the results of this model can be reduced to the autocovariance and autocorrelation of the standard ARMA model as well as a special case. Numerical examples are used to illustrate the behaviour of the autocovariance and autocorrelation at different δ values to show the various structures that the model can represent

Stock return autocorrelation, day of the week and volatility

Purpose The main purpose of this paper is to investigate autocorrelation structure of stock and portfolio returns in a unique market setting of Saudi Arabia, where nearly all active traders are the retail individuals and the market operates under severe limits to arbitrage. Specifically, the authors examine how return autocorrelation of Saudi Arabian stock market is related to factors such as the day of the week, stock trading, performance on the preceding day and volatility. Design/methodology/approach The sample consists of the daily stock price and index data of 159 firms listed in Tadawul (Saudi Arabian Stock Exchange) for the period from January 2004 through December 2015. The methodology of Safvenblad (2000) is primarily used to investigate the autocorrelation structure of individual stock and index returns. The authors also use the Sentana and Wadhwani (1992) methodology to test for the presence of feedback traders in the Saudi stock market. Findings Results show that there is significantly positive autocorrelation in individual stock, size portfolio and market returns and that the last two are almost always larger than the first. Return autocorrelation is negatively related to firm size. Interestingly, return autocorrelation is positively related to trading frequency. For portfolios, autocorrelation of returns following a high absolute return day is significantly higher than that following a low absolute return day. Similarly, return autocorrelation during volatile periods is generally larger than that during tranquil periods. Return correlation between weekdays is usually larger than that between the first and last days of the week. Overall, the results suggest that the possible reason for positive autocorrelation in stock returns could be the presence of negative feedback traders who are engaged in frequent profit-taking activities. Originality/value This is the first paper that thoroughly investigates the autocorrelation structure of the returns of the Saudi stock market using both index and individual stock returns. As this US$583bn (as of August 21, 2014) market opened to foreign institutional investors in June 2015, the results of this paper should be of significant value for the potential uninformed foreign investors in this relatively lesser known and previously closed yet highly prospective market.

Autocorrelation structure at rest predicts value correlates of single neurons during reward-guided choice

Correlates of value are routinely observed in the prefrontal cortex (PFC) during reward-guided decision making. In previous work (Hunt et al., 2015), we argued that PFC correlates of chosen value are a consequence of varying rates of a dynamical evidence accumulation process. Yet within PFC, there is substantial variability in chosen value correlates across individual neurons. Here we show that this variability is explained by neurons having different temporal receptive fields of integration, indexed by examining neuronal spike rate autocorrelation structure whilst at rest. We find that neurons with protracted resting temporal receptive fields exhibit stronger chosen value correlates during choice. Within orbitofrontal cortex, these neurons also sustain coding of chosen value from choice through the delivery of reward, providing a potential neural mechanism for maintaining predictions and updating stored values during learning. These findings reveal that within PFC, variability in temporal specialisation across neurons predicts involvement in specific decision-making computations.