Scanner Data

what has been referred to as theory applications (TA) research in which the main focus is on laboratory experiments with student subjects and high internal validity. In this article, the author argues that external validity concerns should be given more attention, particularly in TA research. Three recommendations are made for implementing these concerns: (1) consumer behavior articles should be required to have a section indicating how increased levels of external validity can be obtained with other studies, (2) "joint ventures" between consumer behavior and marketing science researchers can be profitable and should be encouraged, and analyses of electronic scanner panel data or other secondary data can be used to generate higher levels of external validity. Three examples are given from the marketing literature of how findings from experiments and scanner data can be combined to advance a stream of research.

Though it has been widely reported in the marketing literature that temporary price discounts generate substantial short-term sales increase, the shape of the deal effect curve constitutes a key research topic, for which there are still limited empirical results. To address this issue, a semiparametric regression approach is used to model the complex nature of this phenomenon. Our model is developed at the brand level using daily store-level scanner-data, which allows the study of several nonreported promotional effects, such as the influence of the day of the week both in promotional and nonpromotional periods. The results show that the weekend is the most effective in increasing promotional sales and that asymmetric and neighborhood effects hold. However, 9-ending promotional prices are not impactful. r

In this paper we investigate whether consideration of store-level heterogeneity in marketing mix effects improves the accuracy of the marketing mix elasticities, fit, and forecasting accuracy of the widely-applied SCAN ⁎ PRO model of store sales. Models with continuous and discrete representations of heterogeneity, estimated using hierarchical Bayes (HB) and finite mixture (FM) techniques, respectively, are empirically compared to the original model, which does not account for store-level heterogeneity in marketing mix effects, and is estimated using ordinary least squares (OLS). The empirical comparisons are conducted in two contexts: Dutch store-level scanner data for the shampoo product category, and an extensive simulation experiment. The simulation investigates how between-and within-segment variance in marketing mix effects, error variance, the number of weeks of data, and the number of stores impact the accuracy of marketing mix elasticities, model fit, and forecasting accuracy. Contrary to expectations, accommodating store-level heterogeneity does not improve the accuracy of marketing mix elasticities relative to the homogeneous SCAN ⁎ PRO model, suggesting that little may be lost by employing the original homogeneous SCAN ⁎ PRO model estimated using ordinary least squares. Improvements in fit and forecasting accuracy are also fairly modest. We pursue an explanation for this result since research in other contexts has shown clear advantages from assuming some type of heterogeneity in market response models. In an Afterthought section, we comment on the controversial nature of our result, distinguishing factors inherent to household-level data and associated models vs. general store-level data and associated models vs. the unique SCAN ⁎ PRO model specification.

a b s t r a c t X-ray fluorescence (XRF) scanning of unlithified, untreated sediment cores is becoming an increasingly common method used to obtain paleoproxy data from lake records. XRF-scanning is fast and delivers high-resolution records of relative variations in the elemental composition of the sediment. However, lake sediments display extreme variations in their organic matter content, which can vary from just a few percent to well over 50%. As XRF scanners are largely insensitive to organic material in the sediment, increasing levels of organic material effectively dilute those components that can be measured, such as the lithogenic material (the closed-sum effect). Consequently, in sediments with large variations in organic material, the measured variations in an element will to a large extent mirror the changes in organic material. It is therefore necessary to normalize the elements in the lithogenic component of the sediment against a conservative element to allow changes in the input of the elements to be addressed. In this study we show that Al, which is the lightest element that can be measured using the Itrax XRF-scanner, can be used to effectively normalize the elements of the lithogenic fraction of the sediment against variations in organic content. We also show that care must be taken when choosing resolution and exposure time to ensure optimal output from the measurements.

This study characterises the ‘deal-proneness’ of consumers by analysis of the consumer-level characteristics of price sensitivity and brand loyalty. The study first develops a multinomial logistic (MNL) latent class model suitable for use with universal product code (UPC) point-of-sale (hypermarket) scanner data. The model is then used to assess the deal-proneness of consumers with respect to monetary promotions (price reductions) and non-monetary promotions (store flyers). The results show that almost 47% of consumers can be considered deal-prone, in that both kinds of sales promotions have a significant effect on their choice behaviour. The findings provide important insights for retail management in seeking to optimise the results obtained from promotional budgets.

The purpose of this paper is to examine the dynamic effects of sales promotions. We create dynamic brand sales models (for weekly store-level scanner data) by relating store intercepts and a brand's own price elasticity to a measure of the cumulated previous price discountsamount and timefor that brand as well as for other brands. The brand's own non-price promotional response parameters are related to the time since the most recent promotion for that brand as well as for other brands. We demonstrate that these dynamic econometric models provide greater managerial relevance than static models can.

The introduction of a new brand may change the competitive structure, which concerns the market shares and the marketing instrument elasticities. For example, the new brand can cause intensified price competition and possibly also influence the relative effectiveness of price promotions for the incumbent brands.

This paper aims to analyze, utilizing scanner data, the relationships of competitive interdependency in the extra-virgin olive oil sector in Italy. One of the most important aspects of the competitiveness analysis is the concept of competitive interdependency, as the competitive performances of a product depend upon the number of competitors on the same shop shelf. The "Social Network Analysis" (SNA) has been applied to investigate these interdependencies by elaborating extra-virgin olive oil sales data from a national level survey. The SNA methodology has provided a useful tool to analyse the competitive relationships between each selected extra-virgin olive oil brand and the others on the same shop shelf. The conclusions aim to discuss the results of the study, which has provided useful information about high quality Italian olive oil segments, and to evaluate future opportunities and actual limits of this new methodology to approach the analysis of competitive brand networks.

While a significant literature has emerged recently on the longer-term effects of price promotions, as inferred from persistence models, there is very little if any attention paid to whether such longer-term effects vary across different types of consumers. This paper takes a first step in that direction by exploring whether the adjustment, permanent, and total effects of price promotions, and the duration of the adjustment period, differ between consumers segmented based on their usage rates in a product category and their loyalty to a brand. We also investigate whether such consumer segmentation will improve the forecasting performance of persistence models at both product category and brand levels. Expectations are developed based on consumer behavior theory on various effects of price promotions, such as the post-deal trough, the mere purchase effect, the promotion usage effect, and responsiveness to competitor's reactions. Evidence from household-level supermarket scanner data on four product categories is provided. We find substantial differences between consumer segments and provide insights on how managers can increase the longer-term effectiveness of price promotions by targeting each consumer segment with a different promotion program. In addition, consumer segmentation is found to significantly improve the forecasting performance of the persistence model for two of the four product categories. For the other two product categories, consumer segmentation provides forecasting performance similar to that obtained from aggregate-level persistence models. D

This paper employs a nation-wide sample of supermarket scanner data to estimate a large brand-level demand system for beer in the U.S. using the Distance Metric method of Pinkse, Slade and Brett [Pinkse, J., Slade, M., Brett, C., 2002. Spatial price competition: a semiparametric approach. Econometrica 70, . Unlike previous studies, this work estimates the own-and cross-advertising elasticities in addition to price elasticities. Positive and negative cross-advertising elasticities imply the presence of both cooperative and predatory effects of advertising expenditures across brands; however, the former effect appears to dominate suggesting that advertising increases the overall demand for beer. We discuss the implications of these results in this industry.

The effects of topography on the radiometric properties of multispectral scanner (MSS) data are examined in the context of the remote sensing of forests in mountainous regions. The two test areas considered for this study are located in the coastal mountains of British Columbia, ...

The results from different index number formulae can differ and can do so substantially. The main criteria for explaining such differences, and governing choice between them, are their ability to satisfy desirable test properties-the axiomatic approach-and their correspondence with plausible substitution behavior as predicted from economic theory. Yet the numerical differences between such formulae has been shown to be related to the extent of, and changes in, the dispersion of prices. However, within the index number literature there is, to the author's knowledge, no formal attempt to explain differences between the results from individual formulae in terms of theories and evidence on price dispersion. Explaining differences between formulae in terms of changes in the dispersion of prices benefits from the existence of economic theoretical frameworks to explain such dispersion, and thus improve our understanding of why differences from formulae occur. Such frameworks include search cost and menu cost theories and signal extraction models. This paper outlines the nature of the relationships between formulae in term of price dispersion, then considers economic theories of price dispersion and uses them to model price variation both within months and over time using an extensive scanner data set on television sets amounting to over 70,000 observations over 51 months. It concludes by considering the implications for index number construction.

In this paper we introduce a new flexible mixed model for multinomial discrete choice where the key individual-and alternative-specific parameters of interest are allowed to follow an assumptionfree nonparametric density specification while other alternative-specific coefficients are assumed to be drawn from a multivariate normal distribution which eliminates the independence of irrelevant alternatives assumption at the individual level. A hierarchical specification of our model allows us to break down a complex data structure into a set of submodels with the desired features that are naturally assembled in the original system. We estimate the model using a Bayesian Markov Chain Monte Carlo technique with a multivariate Dirichlet Process (DP) prior on the coefficients with nonparametrically estimated density. We employ a "latent class" sampling algorithm which is applicable to a general class of models including non-conjugate DP base priors. The model is applied to supermarket choices of a panel of Houston households whose shopping behavior was observed over a 24-month period in years 2004-2005. We estimate the nonparametric density of two key variables of interest: the price of a basket of goods based on scanner data, and driving distance to the supermarket based on their respective locations. Our semi-parametric approach allows us to identify a complex multi-modal preference distribution which distinguishes between inframarginal consumers and consumers who strongly value either lower prices or shopping convenience.

Management of brand equity has come to be viewed as critical to a brand's optimal long-term performance. The authors evaluate the usefulness of brand equity estimates obtained from store-level data for monitoring the health of a brand. They use a random coefficients logit demand model calibrated on store-level scanner data to track brand equity estimates over time in two consumer packaged goods categories that experienced several new product introductions during the period of the empirical investigation. Using these tracked measures, the authors also study the impact of marketing actions, such as advertising, sales promotions, and product innovations, on brand equity. They find that the brand equity estimates effectively capture the high equity of strongly positioned popular brands and brands that command a significant price premium in niche markets. Using an example, the authors illustrate how these brand equity estimates can be used to monitor changes in brand equity, which measures such as market share may fail to capture. The substantive results indicate that advertising has a positive effect on brand equity in both the product categories, whereas the effect of sales promotions is not significant in either category. Furthermore, the results reveal that new product innovations have a positive impact on brand equity and can explain a significant proportion of its variation. Overall, the analysis shows that a brand manager can track brand equity using store-level data, gain insights into the drivers of the brand's equity, and manage these drivers to achieve brand equity targets.

Retailers who wish to make decisions for a single store and have access to the scanner data of all purchases and to the scanner data of customer card-holders may worry about erroneous inferences when using one of the two databases and when using the same models to estimate the effects of their main marketing variables. The questions are: ''do the transactions reflected by the customer cards necessarily reflect the usual purchase behavior of all customers?''; and ''do the same customer response models apply equally to regular customers and for the rest of individuals shopping at the store?''. To answer these questions, a brand choice multinomial logit model choice is applied for the product category chosen (ground coffee). The major findings are that regular price elasticity of all brands in the customer segment is twice what was estimated when studying the total purchases. The effects on brand and type of coffee are greater in the customer card-holders segment than in the total purchases.

This paper employs a nation-wide sample of supermarket scanner data to estimate a large brand-level demand system for beer in the U.S. using the Distance Metric method of Pinkse, Slade and Brett [Pinkse, J., Slade, M., Brett, C., 2002. Spatial price competition: a semiparametric approach. Econometrica 70, . Unlike previous studies, this work estimates the own-and cross-advertising elasticities in addition to price elasticities. Positive and negative cross-advertising elasticities imply the presence of both cooperative and predatory effects of advertising expenditures across brands; however, the former effect appears to dominate suggesting that advertising increases the overall demand for beer. We discuss the implications of these results in this industry.

In recent years, manufacturers have become increasingly disposed toward the use of sales promotions, often at the cost of advertising. Yet the long-term implications of these changes for brand profitability remain unclear. In this paper, we seek to offer insights into this important issue. We consider the questions of i) whether it is more desirable to advertise or promote, ii) whether it is better to use frequent, shallow promotions or infrequent, deep promotions, and iii) how changes in regular prices affect sales relative to increases in price promotions. Additional insights regarding brand equity, the relative magnitude of short-and long-term effects, and the decomposition of advertising and promotion elasticities across choice and quantity decisions are obtained.

Knowledge of a high correlation between a consumerÕs residence and his place of grocery shopping has allowed researchers to use scanner data to assess the relationship between income and shopping behavior. This study addresses the shopping behavior of over 100,000 consumers who patronize six supermarkets weekly. Three of these supermarkets are best characterized as stores that service primarily lower-income shoppers, and three are best characterized as stores that service primarily higher-income shoppers. A key objective of this research is to determine if purchasing patterns differ for the two income groups and, if so, to determine if these differences are consistent with economic theory. The results show that the dominant income group for a given area makes purchase decisions that are so widespread and prominent that the confounding effects of other income shoppers are completely overshadowed. Simply stated, the statistical evidence is so strong that it overcomes all possible deviating effects which may result from data outliers.

This paper analyzes the effect of TV advertising and in-store displays on the sales of chocolates. I examine which method is more effective in gaining customers and in increasing total sales. Also, I look at the evidence to see whether the lack of advertising by a firm will hurt the industry as a whole. In this paper, I use a nested logit model on scanner data obtained by the Zwick Center for Food and Resource Policy at the University of Connecticut to examine the effect of TV advertising on chocolate sales. The results show that in-store displays and advertising both help increase the demand for chocolate.

The continuous control of the conservation state of outdoor materials is a good practice for timely planning conservative interventions and therefore to preserve historical buildings. The monitoring of surfaces composition, in order to characterize compounds of neo-formation and deposition, by traditional diagnostic campaigns, although gives accurate results, is a long and expensive method, and often micro-destructive analyses are required. On the other hand, hyperspectral analysis in the visible and near infrared (VNIR) region is a very common technique for determining the characteristics and properties of soils, air, and water in consideration of its capability to give information in a rapid, simultaneous and not-destructive way. VNIR Hypespectral analysis, which discriminate materials on the basis of their different patterns of absorption at specific wavelengths, are in fact successfully used for identifying minerals and rocks (1), as well as for detecting soil properties including moisture, organic content and salinity (2). Among the existing VNIR techniques (Laboratory Spectroscopy - LS, Portable Spectroscopy - PS and Imaging Spectroscopy - IS), PS and IS can play a crucial role in the characterization of components of exposed stone surfaces. In particular, the Imaging Spectroscopic (remote sensing), which uses sensors placed both on land or airborne, may contribute to the monitoring of large areas in consideration of its ability to produce large areal maps at relatively low costs. In this presentation the application of hyperspectral instruments (mainly PS and IS, not applied before in the field of monumental building diagnostic) to quantify the degradation of carbonate surfaces will be discussed. In particular, considering gypsum as the precursor symptom of damage, many factors which may affect the estimation of gypsum content on the surface will be taken into consideration. Two hyperspectral sensors will be considered: 1) A portable radiometer (ASD-FieldSpec FP Pro spectroradiometer), which continuously acquires punctual reflectance spectra in the range 350-2500 nm, both in natural light conditions and by a contact probe (fixed geometry of shot). This instrument is used on field for the identification of different materials, as well as for the definition of maps (e.g geological maps) if coupled with other hyperspectral instruments. 2) Hyperspectral sensor SIM-GA (Selex Galileo Multisensor Hyperspectral System), a system with spatial acquisition of data which may be used on an earth as well as on an airborne platform. SIM-GA consists of two electro-optical heads, which operate in the VNIR and SWIR regions, respectively, between 400-1000 nm and 1000-2500 nm (3). Although the spectral signature in the VNIR of many minerals is known, the co-presence of more minerals on a surface can affect the quantitative analysis of gypsum. Different minerals, such as gypsum, calcite, weddellite, whewellite, and other components (i.e. carbon particles in black crusts) are, in fact, commonly found on historical surfaces. In order to illustrate the complexity, but also the potentiality of hyperspectral sensors (portable or remote sensing) for the characterization of stone surfaces, a case study, the Facade of Santa Maria Novella in Florence - Italy, will be presented. References 1) R.N. Clark and G.A. Swayze, 1995, "Mapping minerals, amorphous materials, environmental materials, vegetation, water, ice, and snow, and other materials: The USGS Tricorder Algorithm", in "Summaries of the Fifth Annual JPL Airborne Earth Science Workshop", JPL Publication 95-1,1,39-40 2) E. Ben-Dor, K. Patin, A. Banin and A. Karnieli, 2002, "Mapping of several soil properties using DATS-7915 hyperspectral scanner data. A case study over clayely soils in Israel", International Journal of Remote Sensing, 23(6), 1043-1062 3) S. Vettori, M. Benvenuti, M. Camaiti, L. Chiarantini, P. Costagliola, S. Moretti, E. Pecchioni, 2008, "Assessment of the deterioration status of historical buildings by Hyperspectral Imaging techniques", in Proceedings of the "In situ Monitoring of Monumental Surfaces -SMS/08" Congress, Edifir-Edizioni Firenze 2008, 55-64

Landmark-based navigation of autonomous mobile robots or vehicles has been widely adopted in industry. Such a navigation strategy relies on identification and subsequent recognition of distinctive environment features or objects that are either known a priori or extracted dynamically. This process has inherent difficulties in practice due to sensor noise and environment uncertainty. This paper is to propose a navigation algorithm that simultaneously locates the robots and updates landmarks in a manufacturing environment. A key issue being addressed is how to improve the localization accuracy for mobile robots in a continuous operation, in which the Kalman filter algorithm is adopted to integrate odometry data with scanner data to achieve the required robustness and accuracy. The Kohonen neural networks have been used to recognize landmarks using scanner data in order to initialize and recalibrate the robot position by means of triangulation when necessary.

We investigate the theoretical possibility and empirical regularity of two troublesome anomalies that frequently arise when cross-price elasticities are estimated for a set of brands expected to be substitutes. These anomalies are the occurrence of: (a) negatively signed cross-elasticities; and (b) sign asymmetries in pairs of cross price elasticities. Drawing upon the Slutsky equation from neoclassical demand theory, we show how and why these anomalies may occur when cross elasticities are estimated for pairs of brands that are substitutes. We empirically examine these issues in the context of the widely used Multiplicative Competitive Interaction (MCI) and Multinomial Logit (MNL) specifications of the fully extended attraction models (Cooper and Nakanishi 1988). Utilizing a database of store-level scanner data for 25 categories and 127 brands of frequently purchased branded consumer goods, we find that about 18% of a total of 732 cross elasticity estimates are negative and approximately 40% of the 366 pairs of cross elasticities are sign asymmetric. Finally, we find that the occurrence of negatively signed cross elasticities can be partially explained by a set of hypothesized relationships between cross-price elasticities and brand share and elasticities of income and category demand. * 1 I What is not well understood is how often and under what circumstances that negative cross elasticities arise. It is also not well known how this relation translates into

A criticism of purchase-based brand loyalty measures is that they are confounded by the marketing mix variables that affect brand choice. This paper investigates the magnitude and direction of the associations for share of category requirements (SCR), defined as each brand's share among the group of households who bought the brand at least once during the time period under consideration.

Both the recent advances in econometric analysis of panel data in economics and the availability of scanner panel data in marketing have motivated marketing researchers to conduct internal analysis of market structure based on revealed preference data. This kind of analysis allows the analyst to infer brand positions in an attribute space from preference and choice data, given a market in which consumers have heterogeneous tastes for attributes. Extant market structure models based on disaggregate panel data are probabilistic models that provide spatial representations of market structure but if a few products share the same brand name across product categories, consumer perceptions of product locations sharing the same brand name may be interdependent. The main contribution of this paper is to present a probabilistic spatial panel data model that allows the positions of products sharing the same name to be correlated across product categories.

Using AC Nielsen scanner data on U.S. household consumption of selected fresh vegetables from 1999 to 2003, this study provides an overview of the organic fresh vegetable market by investigating market shares and price premiums of selected organic fresh vegetables and estimating the interrelationship between consumer demand for organic and conventional fresh vegetables. The linear Almost Ideal Demand System was found to fit the data best among other differential demand models.

While the utilization of scanner data for food demand analyses has become increasingly popular in the United States, few food demand studies, and in particular none on table wine, have been conducted using scanner data in Italy+ This paper presents a first attempt to estimate a demand system for selected brands of red tetra-packaged, plastic packaged, and bag-in-box table wine using scanner data providing new and useful insights into the marketing of Italian wine+ Price and expenditure elasticities of Italian red table wine demand drawn from a linear almost ideal demand system are provided+ Results suggest a partially loyal market of table wine, showing a tendency to substitution across brands and a degree of competition among the leading brands+ @EconLit citations: Q110, Q130#+

Extant research on the decomposition of unit sales bumps due to price promotions considers these effects only within a single product category. This article introduces a framework that accommodates specific crosscategory effects. Empirical results based on daily data measured at the item/SKU level show that the effects of promotions on sales in other categories are modest. Between-category complementary effects (20%) are, on average, substantially larger than between-category substitution effects (11%). Hence, a promotion of an item has an average net spin-off effect of (20 − 11=) 9% of its own effect. The number of significant cross-category effects is low, which means that we expect that, most of the time, it is sufficient to look at within-category effects only. We also find within-category complementary effects, which implies that competitive items within the category may benefit from a promotion. We find small stockpiling effects (6%), modest cross-item effects (22%), and substantial category-expansion effects (72%). The cross-item effects are the result of crossitem substitution effects within the category (26%) and within-category complementary effects (4%). Approximately 15% (= 11% / 72%) of the category-expansion effect is due to between-category substitution effects of dependent categories.

Baseline sales measure what retail sales would be in the absence of a promotion (Abraham and Lodish 1993), and models that measure baseline sales are widely used by managers to assess the profitability of promotions (Bucklin and Gupta 1999-this issue). Estimates of baseline sales and promotional response are typically independent of past promotional activity, even though there is evidence to suggest that increased discounting reduces off-promotion sales and increases the percentage of purchases made on deal (e.g., Krishna 1994). As a result, models that do not consider dynamic promotional effects can mislead managers to overpromote. Given the widespread use of "static" models to evaluate the efficacy of promotions, it is particularly desirable to calibrate a dynamic brand sales model and use it to establish an optimal course of action. Accordingly, we develop a descriptive dynamic brand sales model and use it to determine normative price promotion strategies. Our descriptive approach consists of estimating a varying-parameter sales response model. Letting model parameters vary with past discounting activity accommodates the possibility that market response changes with firms' discounting policies. In the normative model, we use the estimates obtained in the descriptive model to determine optimal retailer and manufacturer prices over time. The results of the descriptive model indicate that promotions have positive contemporaneous effects on sales accompanied by negative future effects on baseline sales. The results of the normative model suggest that the higher-share brands in our data tend to overpromote while the lowershare brands do not promote frequently enough. We project that the use of our model could improve manufacturers' profits by as much as 7% to 31%. More generally, the normative results indicate that i) if deals become more effective in the current period, i.e., if consumers are more price sensitive, promotions should be used more frequently; and ii) as the negative dynamic effect of discounts on sales increases, the optimal level of discounting should go down. Without our approach, it would be difficult to make this trade-off exact. Finally, we demonstrate that these dynamic effects provide another perspective to the marketing literature regarding the existence of promotions.

Estimating permeability from NMR well logs or mobile NMR core scanner data is an attractive method as the measurements can be performed directly in the formation or on fresh cores right after drilling. Furthermore, the method is fast and non-destructive. Compared to T 1 relaxation times, commonly measured T 2 distributions are influenced by external and internal magnetic field gradients. We performed two-dimensional T 1 and T 2 relaxation experiments on samples of Rhaetian sandstone, a rock with low porosity and small pore radii, using a mobile NMR core scanner which operates within a nearly homogeneous static magnetic field. Because small pore sizes are associated with high internal magnetic field gradients, standard methods from NMR logging in the oil industry cannot be applied for accurate permeability prediction. Therefore, a new model theory was developed, which describes the pore radius dependence of the surface relaxivity ρ 2 by both an analytical and a more practical empirical equation. Using corrected ρ 2 values, permeability can be predicted accurately from the logarithmic mean of the T 2 distribution and the physically based Kozeny-Carman equation. Additional core plug measurements of structural parameters such as porosity, permeability, specific inner surface area and pore radius distributions supported the NMR results.

The reflectance factors of the polyamide rods which were dyed with different concentrations of three commercial yellow, red, and blue disperse dyes are recovered from their RGB data obtained from scanning of the cross sections of rods with the desktop scanner. The RGB data are converted to device independent XYZ tristimulus values by simple polynomial regression technique. Then, the principal component analysis (abbreviated by PCA) technique is employed for the recovery of reflectance spectra from the tristimulus values by using three different datasets, i.e. using the reflectance factors of Munsell chips, MacBeth ColorChecker SG, and a dynamic dataset prepared from the reflectance factors of dyed rods samples. The first three eigenvectors of each dataset are extracted and employed in the reconstruction process of spectral reflectance from XYZ colorimetric data. Finally, the well known Kubelka-Munk function is implemented for estimation of concentration of dye from the recovered spectral reflectance. The root mean square (RMS) errors between the reconstructed and the actual reflectance data over the visible spectrum are calculated. According to results, the RMS errors for the reflectance recovery are within the acceptable range. Error of estimation of dye concentration in the rods varies for different hues as well as concentrations and changes with applied dataset.

This paper describes a new out-of-core multi-resolution data structure for real-time visualization, interactive editing and externally efficient processing of large point clouds. We describe an editing system that makes use of the novel data structure to provide interactive editing and preprocessing tools for large scanner data sets. Using the new data structure, we provide a complete tool chain for 3D scanner data processing, from data preprocessing and filtering to manual touch-up and real-time visualization. In particular, we describe an out-of-core outlier removal and bilateral geometry filtering algorithm, a toolset for interactive selection, painting, transformation, and filtering of huge out-of-core point-cloud data sets and a real-time rendering algorithm, which all use the same data structure as storage backend. The interactive tools work in real-time for small model modifications. For large scale editing operations, we employ a tworesolution approach where editing is planned in real-time and executed in an externally efficient offline computation afterwards. We evaluate our implementation on example data sets of sizes up to 63 GB, demonstrating that the proposed technique can be used effectively in real-world applications.

Four multi-method studies show that the more elongated a container, the lower its purchase quantity. Study 1, in the lab, shows beer bottles are perceived to contain more than beer cans, particularly for infrequent beer drinkers. Study 2 analyzes scanner data to show that the purchase quantity of cans is 63.66 percent higher than the purchase quantity of bottles. Study 3, a virtual shopping survey, demonstrates these effects are strongest when the context is socializing at home, and Study 4, in the lab, shows results hold only when desired consumption level is constant. Implications for retailers and product managers are offered.

We examine retail and wholesale prices for a large supermarket chain over seven and one-half years. We find that prices fall on average during seasonal demand peaks for a product, largely due to changes in retail margins. Retail margins for specific goods fall during peak demand periods for that good, even if these periods do not coincide with aggregate demand peaks for the retailer. This is consistent with "loss-leader" models of retailer competition. Models stressing cyclical demand elasticities or cyclical firm conduct are less consistent with our findings. Manufacturer behavior plays a limited role in the countercyclicality of prices. (JEL LI 3, E32, L81)

A study designed on the basis of a fixed-effects, three factor, two-level analysis or variance (ANOVA) was conducted to quantify the effect of Thematic Mapper (TM) sensor improvements on classification accuracy using TM data acquired over the Washinton, DC, area on November 2, 1982. The TM data were systematically degraded spatially, spectrally, and radiometrically to simulate the effect of changing each individual sensor parameter separately, and in conjunction with other sensor characteristics, to ultimately simulate Multispectral Scanner (MSS) data characteristics.

While a significant literature has emerged recently on the longer-term effects of price promotions, as inferred from persistence models, there is very little if any attention paid to whether such longer-term effects vary across different types of consumers. This paper takes a first step in that direction by exploring whether the adjustment, permanent, and total effects of price promotions, and the duration of the adjustment period, differ between consumers segmented based on their usage rates in a product category and their loyalty to a brand. We also investigate whether such consumer segmentation will improve the forecasting performance of persistence models at both product category and brand levels. Expectations are developed based on consumer behavior theory on various effects of price promotions, such as the post-deal trough, the mere purchase effect, the promotion usage effect, and responsiveness to competitor's reactions. Evidence from household-level supermarket scanner data on four product categories is provided. We find substantial differences between consumer segments and provide insights on how managers can increase the longer-term effectiveness of price promotions by targeting each consumer segment with a different promotion program. In addition, consumer segmentation is found to significantly improve the forecasting performance of the persistence model for two of the four product categories. For the other two product categories, consumer segmentation provides forecasting performance similar to that obtained from aggregate-level persistence models.

Although a variety of approaches for inferring market segments exist, little, if any, effort has been devoted to comparing the relative validity of these approaches. This study conducts two extensive simulation experiments in a scanner data setting to empirically compare and validate alternative mixture model-based procedures for segmenting households using choice behaviors and household characteristics. Compared to existing two-stage approaches, a new method known as the joint approach produced 23 -27% less error in estimates of characteristics and 30 -38% less error in estimates of choice model parameters. Contrary to conventional wisdom, the joint approach, which simultaneously uses household choice and characteristic data, is shown to be superior even when one is interested in recovering only characteristic-based segments. D (I.S. Currim).

State of the art positron emission tomography (PET) systems allow for scatter and attenuation correction. However, the size of the structure being studied and the region of interest (ROI) chosen also influence the accuracy of measurements of radioactive concentration. Furthermore, the limited spatial resolution of PET tomographs, which depends, among other factors, on the range of positrons in matter, can also contribute to a loss in quantitation accuracy. In this paper we address the influence of positron range, structure size and ROI size on the quantitation of radioactive concentration using PET. ECAT EXACT HR+ (HR+) and ECAT 953B/31 (ECAT 953B) PET systems were used in phantom acquisitions performed with two radioisotopes with different positron ranges. The 3D Hoffman phantom was scanned on both scanners with both radioisotopes, to visually analyse the image quality. A resolution phantom having six spheres of different diameters in a Plexiglas cylinder was used to calculate the values of the contrast recovery coefficient or hot spot recovery coefficient and of the spill-over or cold spot recovery coefficient under different imaging conditions used in clinical routine at our institution. Activity ratios were varied between 2 and 30 or between 0.4 and 200 by filling the spheres with fluorine-18 or bromine-76 respectively and the cylinder with 11 C. Dynamic scans were performed on each scanner. Data were reconstructed using the same parameters as are used in clinical protocols. The variations in sphere and cylinder activities with time were fitted using the function

The data acquired from the hyperspectral airborne sensor DAIS-7915 over Izrael Valley in northern Israel was processed to yield quantitative soil properties maps of organic matter, soil eld moisture, soil saturated moisture, and soil salinity. The method adopted for this purpose was the Visible and Near Infrared Analysis ( VNIRA) approach, which yields an empirical model for predicting the soil property in question from both wet chemistry and spectral information of a representative set of samples (calibration set). Based on spectral laboratory data that show a signi cant capability to predict the above soil properties and populations using the VNIRA strategy, the next step was to examine this feasibility under a hyperspectral remote sensing (HSR) domain. After atmospherically rectifying the DAIS-7915 data and omitting noisy bands, the VNIRA routine was performed to yield a prediction equation model for each property, using the re ectance image data. Applying this equation on a pixel-bypixel basis revealed images that described spatially and quantitatively the surface distribution of each property. The VNIRA results were validated successfully from a priori knowledge of the area characteristics and from data collected from several sampling points. Following these examinations, a procedure was developed in order to create a soil property map of the entire area, including soils under vegetated areas. This procedure employed a random selection of more than 80 points along nonvegetated areas from the quantitative soil property images and interpolation of the points to yield an isocontour map for each property. It is concluded that the VNIRA method is a promising strategy for quantitative soil surface mapping, furthermore, the method could even be improved if a better quality of HSR data were used.