Maximally selected statistics for the estimation of simple cutpoint models are embedded into a generalized conceptual framework based on conditional inference procedures. This powerful framework contains most of the published procedures in this area as special cases, such as maximally selected chi-squared and rank statistics, but also allows for direct construction of new test procedures for less standard test problems. As an application, a novel maximally selected rank statistic is derived from this framework for a censored response partitioned with respect to two ordered categorical covariates and potential interactions. This new test is employed to search for a high-risk group of rectal cancer patients treated with a neo-adjuvant chemoradiotherapy. Moreover, a new efficient algorithm for the evaluation of the asymptotic distribution for a large class of maximally selected statistics is given enabling the fast evaluation of a large number of cutpoints. / Series: Research Report Series / Department of Statistics and Mathematics

The supLM test for structural change is embedded into a permutation test framework for a simple location model. The resulting conditional permutation distribution is compared to the usual (unconditional) asymptotic distribution, showing that the power of the test can be clearly improved in small samples. Furthermore, generalizations are discussed for binary and multivariate dependent variables as well as model-based permutation testing for structural change. The procedures suggested are illustrated using both artificial and real-world data (number of youth homicides, employment discrimination data, structural-change publications, and stock returns). / Series: Research Report Series / Department of Statistics and Mathematics

Student number : 0314533R MSc Project Report School of Mining Engineering Faculty of Engineering and the Built Environment / Globalization has created investment opportunities for enterprises around the world. Attracting foreign investment into developing regions has been a key challenge in the strategies for economic growth and poverty reduction of developing countries. Overall, the results of foreign investment have been disappointing in some countries. Recent studies confirm that factors such as corruption, political instability, armed conflict, and other non-commercial risks have negatively impacted foreign direct investment inflows. However, there is renewed hope among government personnel that private investment can play an increasingly significant role in helping economic` growth. As host governments, international corporations, investment banks and multilateral insurance agencies learn from the mistakes of the past and commit themselves to improve the environment for business for mining industry, the prospect for the future brightens. Moreover, foreign investors are recognizing that if the host government can create a competitive environment, investments in developing countries have the potential to be highly profitable. It is hoped that this research effort will contribute in some way to better understand the inability of some countries to attract FDI. The current situation in developing countries is of particular relevance to the theme of this research project. The study compares non-commercial risk ratings for foreign direct investment inflows compiled for ten selected countries. The matrix provides a comparative assessment of noncommercial risk ratings, and highlights the importance of country risk and event risk as components of a composite risk rating.

Flow meters are used to measure flow accurately. There are many different flow meters and it is necessary to know which will function best for specific situations. A wide variety of flow meters were selected for the study to assist in showing that each flow meter has its tradeoffs. The selected meters include: three types of Venturi meters, a wedge meter, a V-cone meter, an electromagnetic flow meter, and an ultrasonic flow meter. The characteristics researched in this study are discharge coefficient (Cd) over a range of Reynolds numbers (Re), head loss across each flow meter, life, and cost of meter. Each meter was tested over a wide range of Re to find the corresponding Cd and head loss. The life and cost of each meter were researched and estimated based on the flow meter companies and local distributor’s findings. With the findings, the tradeoffs are illustrated and will assist buyers in selecting a flow meter that will best fit their needs. While there are more flow meters available than was tested, the current study can direct buyers in a correct process of selecting meters for all situations.

The purpose of this study was to assess the extent to which selected variables are related to scores on the Utah State University Faculty Evaluation Questionnaire (USU FEQ). The variables examined were size of class, level of class, college under whose auspices a class is offered and whether the class is required or elective. In addition, the relationship between total mean score and responses to question 23, a percentage ranking of instructors, was assessed. The fall quarter, 1975, FEQ results were used in this assessment. Employing the same procedures as had been followed in previous quarters, 315 courses were evaluated. Courses at all levels (100-700) and within all colleges of the University were sampled. Through multiple regression analysis, it was found that 87% of the variance in total mean scores was explained by the selected variables. Question 23 was the outstanding contributor; therefore, the analysis was repeated with this variable removed. As a result, 21% of the variance was explained by the remaining variables. Question 23 was highly related to total mean score. Reasonably accurate prediction of instructors ratings can be made from a knowledge of responses to this question. A small negative correlation was found between sample size and total mean score. Instructors of larger classes tended to rate lower than instructors of smaller classes. A small contribution to the explained variance was made by the variable of class size. This contribution has little practical significance. Instructors of different colleges received different average ratings. Those colleges most closely related to high total mean scores were Education, Family Life and Humanities, Arts and Social Sciences. Those colleges receiving lowest ratings were Engineering and Science. Knowledge of the college under whose auspices a course exists improves prediction of instructors ratings on the USU FEQ. Whether a course was required or elective and the level of a course had little relation to the ratings instructors received. The outcomes of this investigation may be limited by any one or a combination of the following: The results of this study were obtained from fall quarter evaluations. Ratings may relate to the quarter in which the course was evaluated. The USU population was the only university used in the sampling. Results, therefore, will be generalizable to USU alone. This study has been concerned with environmental variables, i.e., class size, level, college, required vs. elective. Student, class, or teacher characteristics have not been considered. Significant relationships may exist in these areas. Within University policy, professors are allowed to choose the quarter in which they will be evaluated. Therefore, some volunteer effects may be present in this study. However, extra encouragement to evaluate fall quarter was given to teachers to help control for these effects. From this study of the relationship between selected variables and total mean scores, the following may be concluded; Question 23 could be used to obtain a quick, easy estimate of student ratings of an instructor. The significant differences between ratings of instructors in different colleges receive presents an area of concern. When comparing instructors from different colleges, precautions may need to be taken. Differential norms for the colleges could be considered. The size of an instructor's class is of no significant concern when interpreting FEQ results. The results of this study show no basis for the employment of differential norms for differing class sizes. No basis for considering whether a course is required or elective and level of a course when interpreting questionnaire results is given. From the above summary and conclusions the following recommendations are made; The college under whose auspices an instructor teaches should be considered when interpreting FEQ results. College norm groups should be considered for inclusion on results printouts. The significantly higher ratings received by instructors in the College of Education should be investigated. The following questions arise; A. Do students rate instructors higher if instructors give them higher grades? (Grades received in Education are higher.) B. Are the students in the college more empathetic to their instructors and, therefore, more lenient in their ratings? C. Is the course content less demanding or more interesting so as to receive higher student ratings? D. Are, in fact, the instructors in the College of Education better teachers? If so, what are the characteristics that make them better? These questions and others should be researched. 3. Since relationships may vary according to the particular aspect of teaching performance that the student is asked to rate (Clark & Keller, 1954), a factor analytic study including the selected variables of this study and all of the questions on the USU FEQ may be profitable. 4. Scores on the USU FEQ may be related to the department in which the course is taught. Correlations might be determined for the departments which have a large enough N. 5. Determination of whether students' subjective criteria in rating faculty match the faculty members' goals in teaching may disclose some valuable information about the USU FEQ. 6. The benefits from student evaluation of instruction can only exist to the extent that ratings represent valid appraisals of classroom instruction. Research must be conducted in answer to the question, "Is the USU Faculty Evaluation Questionnaire a valid instrument?"

Kinetic data is presented for a variety of ion-neutral reactions which are relevant to the atmosphere of Titan and to the chemistry occurring in interstellar clouds. The data were recorded with a Selected Ion Flow Tube (SIFT) operating at room temperature (294 ± 4 K) and at a pressure of 0.46 Torr. Results of the recent Cassini-Huygens mission to Saturn and Titan have identified several species in the atmosphere of Titan not predicted by pre-Cassini models of the atmosphere. In order to determine the fate of three of these species (methylenimine, propionitrile and cyanodiacetylene) in Titan's ionosphere, their reactivity with the principal ions in Titan's upper ionosphere has been examined. As expected, collision rate proton transfer reactions dominate the chemistry with association channels also observed with many of the hydrocarbon ions. The results of the Cassini mission also identified several individual reactions as being of potential importance to models of Titan's atmosphere and this chemistry has also been examined. The above studies are also relevant to the interstellar medium where each of the neutral reactants have also been detected. The results of some proton transfer equilibrium studies are also presented. The gas phase basicities of propyne and acetylene have been determined to be 681 kJ mol⁻¹ and 617.4 kJ mol⁻¹ respectively. Their relative proton affinities can be estimated from these values. A combined experimental/theoretical study of the proton affinity of cyanodiacetylene (HC₅N) has enabled this value to be estimated at 770 ± 20 kJ mol⁻¹. Details of an attempt to complete the first laboratory measurement of the crucial reaction between H₃⁺ and atomic carbon are presented. The generation of atomic carbon in sufficient quantities for reaction in the SIFT was not possible with the microwave discharge source used. Other generation methods have also been explored with the laser photolysis of carbon suboxide expected to provide a possible solution to the problems encountered. The results of an investigation into the applicability of lithium ions (Li⁺) to SIFT-MS are presented. The lithium ions associated with each of the twenty-one neutral analytes examined to form pseudo-molecular ions. The association reactions were rapid (k ~ 10⁻⁹ cm³ s⁻¹) for large hydrocarbons but were much slower for smaller analytes (k < 10⁻¹¹ cm³ s⁻¹). In order to clarify some unusual experimental observations, the effect of water molecules on the observed chemistry has been examined in detail. The measured chemistry has important consequences for the applicability of Li⁺ to SIFT-MS where the presence and detection of an identifiable ion of the analyte is essential. Details of new SIFT operating software which can be run on a modern computer are given. Mass spectra and kinetic data recorded with the new software are also presented.

Understanding the time evolution of the star formation in the Universe is one of the main aims of observational astronomy. Since a significant portion of the UV starlight is being absorbed by dust and re-emitted in the IR, we need to understand both of those regimes to properly describe the cosmic star formation history. In UV, the depth and the resolution of the data permits calculations of the star formation rate densities out to very high redshifts (z ∼ 8 − 9). In IR however, the large beam sizes and the relatively shallow data limits these calculations to z ∼ 2. In this thesis, I explore the SMA and PdBI high-resolution follow-up of 30 bright sources originally selected by AzTEC and LABOCA instruments at 1.1 mm and 870 μm respectively in conjunction with the SCUBA-2 Cosmology Legacy Survey (S2CLS) deep COSMOS and wide UDS maps, where 106 and 283 sources were detected, with the signal-to-noise ratio of > 5 and > 3.5 at 850 μm respectively. I find that the (sub)mm-selected galaxies reside and the mean redshifts of ¯z ≃ 2.5±0.05 with the exception of the brightest sources which seem to lie at higher redshifts (¯z ≃ 3.5 ± 0.2), most likely due to the apparent correlation of the (sub)mm flux with redshift, where brighter sources tend to lie at higher redshifts. Stellar masses, M⋆, and star formation rates, SFRs, were found (M⋆ & 1010M⊙ and SFR & 100M⊙ yr−1) and used to calculate the specific SFRs. I determine that the (sub)mm-selected sources mostly lie on the high-mass end of the star formation ‘main-sequence’ which makes them a high-mass extension of normal star forming galaxies. I also find that the specific SFR slightly evolves at redshifts 2−4, suggesting that the efficiency of the star formation seems to be increasing at these redshifts. Using the S2CLS data, the bolometric IR luminosity functions (IR LFs) were found for a range of redshifts z = 1.2 − 4.2 and the contribution of the SMGs to the total star formation rate density (SFRD) was calculated. The IR LFs were found to evolve out to redshift ∼ 2.5. The star formation activity in the Universe was found to peak at z ≃ 2 followed by a slight decline. Assuming the IR to total SFRD correction found in the literature the SFRD found in this work closely follows the best-fitting function of Madau & Dickinson (2014).

Outstanding scientific results and statistical overview of the Institute of Ion Beam Physics and Materials Research in 2008

The growing importance of trade internationally as well as for the United States (U.S.) spawned a body of literature concerning import demand, export supply, and trade balance. Most of the empirical work to date has employed estimates of commodity import demand functions derived from traditional linear and log-linear functional forms. These specifications of import demand impose separability restrictions on the consumer's choice between domestic and foreign goods, in addition to confining import demand elasticities to constant values. The policy recommendations made on the basis of the import demand elasticities derived from these traditional models may be misleading. In this study, a more flexible model of import demand is employed. The model allows a more flexible characterization of the underlying preference structure for both domestic and imported commodities. Import demand functions are then derived from the underlying model which possess the properties of the flexible characterization of consumer preference. Wheat import data by major source of supply to selected EEC countries and Japan are used to estimate the parameters of the derived wheat import demand relationships. The results of the estimation and tests suggest that the use of the traditional restricted model may be suspect even though such models are easily used in the analysis of trade policy. The traditional model was rejected by use of a likelihood ratio test of model specifications for all import demand functions for the selected importing countries analyzed. This suggests that the associated import demand and income elasticities are not constant but variable (derived from each data point) in contrast to previous assumptions regarding the behavior or import demand and associated elasticities. The compensated own-price elasticities of import demand for U.S. wheat in the Netherlands and Japan were found to be generally inelastic, close to unitary elastic in the United Kingdom (U.K.), and elastic in the Italian market during the time period studied. These estimated elasticities were then used to analyze the impacts of selected trade policies such as export subsidies and taxes, tariff reductions and threshold price systems, quotas and price stabilization.

The purpose of this study was to analyze the word processing procedures in the offices of the President and Provost at Utah State University. Seven secretaries participated in the survey by completing a questionnaire and keeping a record of all typing and nontyping tasks performed during two nonconsecutive weeks. A combined total of 9035 lines (average 12 words per line) of typing was completed by all workers. Ninety-nine percent of the typing was classified as text in format and originated in one of several ways including: copy type, shorthand, revision, self composition, machine dictation, and longhand. Recommendations based on the data collected were made regarding the word processing system analyzed. Recommendations included the implementation of a semi-consolidated word processing system and the addition of standardized dictating equipment and a magnetic medium typewriter.