Search results for " Regression"
showing 10 items of 1835 documents
Using Daily Store-level Data to Understand Price Promotion Effects in a Semiparametric Regression Model
2009
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 promotion…
Assessing Online Collaborative Problem Solving Among School Children in Finland : A Case Study Using ATC21S TM in a National Context
2018
Online collaborative problem-solving tasks were piloted in five Finnish schools participating in the Assessment and Teaching of Twenty-first Century Skills (ATC21STM) project. Process stream data from online tasks were captured from 480 Finnish students who explored dyad problem spaces. The log file data were explored to identify indicative behaviours of collaborative problem solving (CPS), which were coded into a series of dichotomous indicators. The Rasch simple logistic model was used to analyse student performance across the social and cognitive dimensions of CPS. Analysis of the Finnish data indicated that the construct can be interpreted using a two-dimensional model, matching the fin…
Preliminary results on direct quantitative determination of cocaine in impregnated materials by infrared spectroscopy
2018
Abstract Partial least squares models were built for the direct determination of cocaine in seized impregnated smuggled materials. Measurements are based on the attenuated total reflectance middle infrared spectra (ATR-MIR) and diffuse reflectance spectra in the near range (DR-NIR) obtained directly from the surface of the impregnated materials. The aforementioned procedures offer fast, cheap and environmentally friendly green alternatives to the reference method based on the extraction of the drug and its quantification by gas chromatography. Additionally it has been verified that results found are statistically comparable with those obtained by the reference method with root mean square e…
Get into flow: Design of experiments as a key technique in the optimization of anodic dehydrogenative C,C cross-coupling reaction of phenols in flow …
2021
Abstract The optimization of electro-organic reactions poses a challenge due to the various parameters involved. Quite often those parameters are not independent from each other, leading the experimental scientist using linear approaches into an optimization loophole. We report a strategy for the optimization of the anodic oxidative dehydrogenative C,C cross-coupling reactions for the synthesis of biphenols based on Design of Experiments (DoE), which overcomes the drawbacks of linear optimization approaches. Using a fractional design, we increased the yield of a long-time investigated example reaction from 44% up to 85% and point out different suitable reaction conditions through to linear …
Testing the concentric-disk tension infiltrometer for field measurement of soil hydraulic conductivity
2010
Abstract The concentric-disk tension infiltrometer (CDTI) may be used to simultaneously measure the confined ( K c ) and the unconfined ( K u ) soil hydraulic conductivity, but it has received little testing. Comparison between K c and K u can be affected by the calculation approach applied to analyze unconfined steady-state infiltration rates. The objectives of this investigation were to: i) establish the effect of the calculation approach on the estimates of K u ; and ii) compare the K c and K u values measured by the CDTI. A clay soil, a structureless sandy loam soil, and a sandy loam soil with a relatively high gravel content were sampled using a disk of radius equal to 107.5 mm, compri…
Variable selection for the determination of total polar materials in fried oils by near infrared spectroscopy
2018
Total polar materials (TPM) content is considered as the best indicator and the most common parameter to check the quality of deep-frying oils. The development of simpler and quicker analytical techniques than the available methods to monitor oil quality in restaurants and fried food outlets is an important topic related to the human health. This paper reports a comparison of the variable selection of near infrared (NIR) spectra by multiple linear regression (MLR-NIR) with partial least squares (PLS-NIR) models for the quantification of TPM in fried vegetable oils. The use of PLS-NIR offers an alternative in laboratory bench equipment for the determination of TPM in oils employed for fryin…
Kinetic Parameters for Thermal Degradation of Green Asparagus Texture by Unsteady-state Method
1998
An unsteady-state method was developed for estimating texture degradation during heating-cooling of green asparagus spears. The method used a mathematical model of heat transmission for time-temperature history estimation, and a nonlinear regression of texture measurements of asparagus spears to estimate kinetic parameters. The specific heat, conductivity and convective coefficient of green asparagus were determined experimentally and used In the mathematical model for temperature estimation. Values obtained were Ea = 76.19±0.13 kJ/mol and k 1158°C = 0.00528±0.00005 s -1 . Good agreement was found between predicted and observed texture values. The method was compared with the classical stea…
Modelling of Reflectance Spectra of Skin Phototypes III
2011
In dermatology, study of human skin colour is related to skin phototype (SPT) in which the Fitzpatrick's scale is the most used skin photo type classification. Assessment of skin response to UV for various reasons plays an important role in dermatology. This is however not easy to be performed because of two reasons. Firstly, skin areas may have different skin tone resulting in different reflectance spectra and secondly, different modalities may produce different reflectance spectra. We hypothesize that the underlying pattern of reflectance spectra must be similar regardless of the modalities use and the skin areas where it is obtained, for a particular person. An observational clinical stu…
Generalized Multitarget Linear Regression with Output Dependence Estimation
2019
Multitarget regression has recently received attention in the context of modern, large-scale problems in which finding good enough solutions in a timely manner is crucial. Different proposed alternatives use a combination of regularizers that lead to different ways of solving the problem. In this work, we introduce a general formulation with several regularizers. This leads to a biconvex minimization problem and we use an alternating procedure with accelerated proximal gradient steps to solve it. We show that our formulation is equivalent but more efficient than some previously proposed approaches. Moreover, we introduce two new variants. The experimental validation carried out, suggests th…
Constrained Clusterwise Linear Regression
2005
In market segmentation, Conjoint Analysis is often used to estimate the importance of a product attributes at the level of each single customer, clustering, successively, the customers whose behavior can be considered similar. The preference model parameter estimation is made considering data (usually opinions) of a single customer at a time, but these data are usually very few as each customer is called to express his opinion about a small number of different products (in order to simplify his/her work). In the present paper a Constrained Clusterwise Linear Regression algorithm is presented, that allows simultaneously to estimate parameters and to cluster customers, using, for the estimati…