Search

Multi-touch attribution (MTA) estimates the relative contributions of the multiple ads a user may see prior to any observed conversions. Increasingly, advertisers also want to base budget and bidding decisions on these attributions, spending more on ads that drive more conversions. We describe two requirements for an MTA system to be suitable for this application: First, it must be able to handle continuously updated and incomplete data. Second, it must be sufficiently flexible to capture that an ad's effect will change over time. We describe an MTA system, consisting of a model for user conversion behavior and a credit assignment algorithm, that satisfies these requirements. Our model for user conversion behavior treats conversions as occurrences in an inhomogeneous Poisson process, while our attribution algorithm is based on iteratively removing the last ad in the path.

This paper considers conducting inference about the effect of a treatment (or exposure) on an outcome of interest. In the ideal setting where treatment is assigned randomly, under certain assumptions the treatment effect is identifiable from the observable data and inference is straightforward. However, in other settings such as observational studies or randomized trials with noncompliance, the treatment effect is no longer identifiable without relying on untestable assumptions. Nonetheless, the observable data often do provide some information about the effect of treatment, that is, the parameter of interest is partially identifiable. Two approaches are often employed in this setting: (i) bounds are derived for the treatment effect under minimal assumptions, or (ii) additional untestable assumptions are invoked that render the treatment effect identifiable and then sensitivity analysis is conducted to assess how inference about the treatment effect changes as the untestable assumptions are varied. Approaches (i) and (ii) are considered in various settings, including assessing principal strata effects, direct and indirect effects and effects of time-varying exposures. Methods for drawing formal inference about partially identified parameters are also discussed., Comment: Published in at http://dx.doi.org/10.1214/14-STS499 the Statistical Science (http://www.imstat.org/sts/) by the Institute of Mathematical Statistics (http://www.imstat.org)

The purpose of this project is to identify how entities who have adopted the Common Core State Standards (CCSS) are addressing this option to add content to the standards. This report describes the policy decisions of adopters on the "15 percent question" as well as reports on and lists any such additional standards they have identified thus far. McREL discussed the adoption with representatives of six adopting state departments of education in the Central Region over the last several months and learned that how others have addressed this option is of interest. As additional states consider the question of whether they should add state material to the Common Core State Standards, this report may aid their considerations. Lists of state standards documents reviewed and sources consulted are included. Appended are: (1) Profiles of the 15 Percent Decision for States who Have Chosen to Add Content; (2) Math Content Added by States to the CCSS; and (3) English Language Arts Content Added by States. (Contains 3 figures and 1 footnote. )

This report is one in a series of reference documents designed to assist those who are directly involved in the revision and improvement of content standards, as well as teachers who use standards and benchmarks to guide everyday instruction. Reports in the series provide information about how benchmarks might best appear in a sequence of instruction and include information on how that content is organized within the state standards documents analyzed. This report is intended to to inform and guide state or district curriculum directors or others who, starting from content that is placed within broad grade bands, need to assign specific grades to benchmarks or objectives. The purpose of this study is to determine what instructional sequences might be revealed through an analysis of standards documents in the subject areas of geography and history. In order to compare geography and history content across the state documents, each of which varies somewhat in the content described, a uniform set of benchmarks was required for reference. To create this reference point, the authors of the study turned to an earlier McREL study on common content in geography and history. This collection of content sequenced by topic should prove useful for districts and schools seeking to assign their states grade-range content to specific grades for instruction.

This paper describes a practical method for identifying and communicating expectations of student performance in the classroom. The method has been used at McREL for clients who require a systematic approach to setting performance expectations and communicating these to their constituents. This document in organized in the following sections: (1) The Need for Performance Standards; and (2) A Systematic Approach to Establishing Performance Standards.

This study identifies a core set of exemplary standards and benchmarks that are accepted by a significant number of educators in the Mid-continent Research for Education and Learning (McREL) region. Specifically, the study provides a list of the knowledge and skills expected of students in most or all states in the Central Region (comprised of Colorado, Kansas, Missouri, Nebraska, North Dakota, South Dakota, and Wyoming) that are also found in state standards documents that have been rated as exemplary by national organizations. In short, this list of standards and benchmarks embodies content that is highly valued nationally as well as within the Central Region. Such a list may assist educators in the region in sharing educational materials that support the academic content they all value. Current school reform efforts create a significant demand for curriculum materials that help students achieve specific and worthwhile standards. A shared set of standards and benchmarks should provide educators with a useful focus for their efforts to find or share high-quality materials that support exemplary standards and benchmarks. (Author)

This document describes science benchmarks for grades K-8 in Earth and Space Science, Life Science, and Physical Science. Each subject area is divided into topics followed by a short content description and grade level information. Source documents for this paper included science content guides from California, Ohio, South Carolina, and South Dakota. This report intends to assist science instruction. (Contains 10 references.) (YDS)

This report reviews education programs and practices that have improved Native American student achievement in English language arts and mathematics. In Navajo tribal schools, teaching Indigenous language and literacy first, followed by teaching English and promoting bilingualism, helped students perform well on tests of vocabulary, comprehension, and writing. In Hawaii, a culturally congruent English language arts program significantly improved Native Hawaiian children's achievement in reading. Emphasis on comprehension over mechanics and phonics allowed children to learn in ways that were congruent with their everyday experiences outside of school. The use of ethnomathematics, based on the same principles of cultural congruence, led to improved student achievement for Native Hawaiian children and Alaskan rural middle school students. All these programs required extensive collaboration and time. Although limited in scope, the evidence suggests that congruency between the school environment and the culture of the community is critical to educational success. Collaborative research and development efforts, carried out at the local level, are needed. Seven action steps are recommended in this regard. An appendix outlines McREL's plan for further research. (Contains 31 references.) (TD)