A finite-population revenue management model and a risk-ratio procedure for the joint estimation of population size and parameters

Many dynamic revenue management models divide the sale period into a finite number of periods T and assume, invoking a fine-enough grid of time, that each period sees at most one booking request. These Poisson-type assumptions restrict the variability of the demand in the model, but researchers and practitioners were willing to overlook this for the benefit of tractability of the models. In this paper, we criticize this model from another angle. Estimating the discrete finite-period model poses problems of indeterminacy and non-robustness: Arbitrarily fixing T leads to arbitrary control values and on the other hand estimating T from data adds an additional layer of indeterminacy. To counter this, we first propose an alternate finite-population model that avoids this problem of fixing T and allows a wider range of demand distributions, while retaining the useful marginal-value properties of the finite-period model. The finite-population model still requires jointly estimating market size and the parameters of the customer purchase model without observing no-purchases. Estimation of market-size when no-purchases are unobservable has rarely been attempted in the marketing or revenue management literature. Indeed, we point out that it is akin to the classical statistical problem of estimating the parameters of a binomial distribution with unknown population size and success probability, and hence likely to be challenging. However, when the purchase probabilities are given by a functional form such as a multinomial-logit model, we propose an estimation heuristic that exploits the specification of the functional form, the variety of the offer sets in a typical RM setting, and qualitative knowledge of arrival rates. Finally we perform simulations to show that the estimator is very promising in obtaining unbiased estimates of population size and the model parameters.

Predicting random effects with an expanded finite population mixed model

Prediction of random effects is an important problem with expanding applications. In the simplest context, the problem corresponds to prediction of the latent value (the mean) of a realized cluster selected via two-stage sampling. Recently, Stanek and Singer [Predicting random effects from finite population clustered samples with response error. J. Amer. Statist. Assoc. 99, 119-130] developed best linear unbiased predictors (BLUP) under a finite population mixed model that outperform BLUPs from mixed models and superpopulation models. Their setup, however, does not allow for unequally sized clusters. To overcome this drawback, we consider an expanded finite population mixed model based on a larger set of random variables that span a higher dimensional space than those typically applied to such problems. We show that BLUPs for linear combinations of the realized cluster means derived under such a model have considerably smaller mean squared error (MSE) than those obtained from mixed models, superpopulation models, and finite population mixed models. We motivate our general approach by an example developed for two-stage cluster sampling and show that it faithfully captures the stochastic aspects of sampling in the problem. We also consider simulation studies to illustrate the increased accuracy of the BLUP obtained under the expanded finite population mixed model. (C) 2007 Elsevier B.V. All rights reserved.

Finite Population Inference for Causal Parameters

Thesis (Ph.D.)--University of Washington, 2016-08

Users’ dissatisfaction with dental care: a population-based household study

OBJECTIVE To examine whether demographic, socioeconomic conditions, oral health subjectivity and characterization of dental care are associated with users’ dissatisfaction with such are.METHODS Cross-sectional study of 781 people who required dental care in Montes Claros, MG, Southeastern Brazil, in 2012, a city with of medium-sized population situated in the North of Minas Gerais. Household interviews were conducted to assess the users’ dissatisfaction with dental care (dependent variable), demographic, socioeconomic conditions, oral health subjectivity and characterization of dental care (independent variables). Sample calculation was used for the finite population, with estimates made for proportions of dissatisfaction in 50.0% of the population, a 5.0% error margin, a non-response rate of 5.0% and a 2.0% design effect. Logistic regression was used, and the odds ratio was calculated with a 5% significance level and 95% confidence intervals.RESULTS Of the interviewed individuals, 9.0% (7.9%, with correction for design effect) were dissatisfied with the care provided. These were associated with lower educational level; negative self-assessment of oral health; perception that the care provider was unable to give dental care; negative evaluation of the way the patient was treated, the cleanliness of the rooms, based on the examination rooms and the toilets, and the size of the waiting and examination rooms.CONCLUSIONS The rate of dissatisfaction with dental care was low. This dissatisfaction was associated with socioeconomic conditions, subjectivity of oral health, skill of the health professionals relating to the professional-patient relationship and facility infrastructure. Educational interventions are suggested that aim at improving the quality of care among professionals by responsible agencies as is improving the infrastructure of the care units.

Lesser Scaup Population Dynamics: What Can Be Learned from Available Data?

Populations of Lesser Scaup (Aythya affinis) have declined markedly in North America since the early 1980s. When considering alternatives for achieving population recovery, it would be useful to understand how the rate of population growth is functionally related to the underlying vital rates and which vital rates affect population growth rate the most if changed (which need not be those that influenced historical population declines). To establish a more quantitative basis for learning about life history and population dynamics of Lesser Scaup, we summarized published and unpublished estimates of vital rates recorded between 1934 and 2005, and developed matrix life-cycle models with these data for females breeding in the boreal forest, prairie-parklands, and both regions combined. We then used perturbation analysis to evaluate the effect of changes in a variety of vital-rate statistics on finite population growth rate and abundance. Similar to Greater Scaup (Aythya marila), our modeled population growth rate for Lesser Scaup was most sensitive to unit and proportional change in adult female survival during the breeding and non-breeding seasons, but much less so to changes in fecundity parameters. Interestingly, population growth rate was also highly sensitive to unit and proportional changes in the mean of nesting success, duckling survival, and juvenile survival. Given the small samples of data for key aspects of the Lesser Scaup life cycle, we recommend additional research on vital rates that demonstrate a strong effect on population growth and size (e.g., adult survival probabilities). Our life-cycle models should be tested and regularly updated in the future to simultaneously guide science and management of Lesser Scaup populations in an adaptive context.

Performance of balanced two-stage empirical predictors of realized cluster latent values from finite populations: A simulation study

Predictors of random effects are usually based on the popular mixed effects (ME) model developed under the assumption that the sample is obtained from a conceptual infinite population; such predictors are employed even when the actual population is finite. Two alternatives that incorporate the finite nature of the population are obtained from the superpopulation model proposed by Scott and Smith (1969. Estimation in multi-stage surveys. J. Amer. Statist. Assoc. 64, 830-840) or from the finite population mixed model recently proposed by Stanek and Singer (2004. Predicting random effects from finite population clustered samples with response error. J. Amer. Statist. Assoc. 99, 1119-1130). Predictors derived under the latter model with the additional assumptions that all variance components are known and that within-cluster variances are equal have smaller mean squared error (MSE) than the competitors based on either the ME or Scott and Smith`s models. As population variances are rarely known, we propose method of moment estimators to obtain empirical predictors and conduct a simulation study to evaluate their performance. The results suggest that the finite population mixed model empirical predictor is more stable than its competitors since, in terms of MSE, it is either the best or the second best and when second best, its performance lies within acceptable limits. When both cluster and unit intra-class correlation coefficients are very high (e.g., 0.95 or more), the performance of the empirical predictors derived under the three models is similar. (c) 2007 Elsevier B.V. All rights reserved.

Prediction with measurement errors in finite populations

We address the problem of selecting the best linear unbiased predictor (BLUP) of the latent value (e.g., serum glucose fasting level) of sample subjects with heteroskedastic measurement errors. Using a simple example, we compare the usual mixed model BLUP to a similar predictor based on a mixed model framed in a finite population (FPMM) setup with two sources of variability, the first of which corresponds to simple random sampling and the second, to heteroskedastic measurement errors. Under this last approach, we show that when measurement errors are subject-specific, the BLUP shrinkage constants are based on a pooled measurement error variance as opposed to the individual ones generally considered for the usual mixed model BLUP. In contrast, when the heteroskedastic measurement errors are measurement condition-specific, the FPMM BLUP involves different shrinkage constants. We also show that in this setup, when measurement errors are subject-specific, the usual mixed model predictor is biased but has a smaller mean squared error than the FPMM BLUP which points to some difficulties in the interpretation of such predictors. (C) 2011 Elsevier By. All rights reserved.

The Advantage of Arriving First: Characteristic Times in Finite Size Populations of Error-Prone Replicators

We study the evolution of a finite size population formed by mutationally isolated lineages of error-prone replicators in a two-peak fitness landscape. Computer simulations are performed to gain a stochastic description of the system dynamics. More specifically, for different population sizes, we compute the probability of each lineage being selected in terms of their mutation rates and the amplification factors of the fittest phenotypes. We interpret the results as the compromise between the characteristic time a lineage takes to reach its fittest phenotype by crossing the neutral valley and the selective value of the sequences that form the lineages. A main conclusion is drawn: for finite population sizes, the survival probability of the lineage that arrives first to the fittest phenotype rises significantly

Population viability analyses of Chamaecrista keyensis (Leguminosae: Caesalpinioideae), a narrowly endemic herb of the lower Florida Keys: Effects of seasonal timing of fires and the urban -wildland interface

This research first evaluated the effects of urban wildland interface on reproductive biology of the Big Pine Partridge Pea, Chamaecrista keyensis, an understory herb that is endemic to Big Pine Key, Florida. I found that C. keyensis was self-compatible, but depended on bees for seed set. Furthermore, individuals of C. keyensis in urban habitats suffered higher seed predation and therefore set fewer seeds than forest interior plants. ^ I then focused on the effects of fire at different times of the year, summer (wet) and winter (dry), on the population dynamics and population viability of C. keyensis. I found that C. keyensis population recovered faster after winter burns and early summer burns (May–June) than after late summer burns (July–September) due to better survival and seedling recruitment following former fires. Fire intensity had positive effects on reproduction of C. keyensis. In contrast, no significant fire intensity effects were found on survival, growth, and seedling recruitment. This indicated that better survival and seedling recruitment following winter and early summer burns (compared with late summer burns) were due to the reproductive phenology of the plant in relation to fires rather than differences in fire intensity. Deterministic population modeling showed that time since fire significantly affected the finite population growth rates (λ). Particularly, recently burned plots had the largest λ. In addition, effects of timing of fires on λ were most pronounced the year of burn, but not the subsequent years. The elasticity analyses suggested that maximizing survival is an effective way to minimize the reduction in finite population growth rate the year of burn. Early summer fires or dry-season fires may achieve this objective. Finally, stochastic simulations indicated that the C. keyensis population had lower extinction risk and population decline probability if burned in the winter than in the late summer. A fire frequency of approximately 7 years would create the lowest extinction probability for C. keyensis. A fire management regime including a wide range of burning seasons may be essential for the continued existence of C. keyensis and other endemic species of pine rockland on Big Pine Key. ^

CONTRASTING PHYLOGEOGRAPHIC PATTERNS IN MITOCHONDRIAL DNA AND MICROSATELLITES: EVIDENCE OF FEMALE PHILOPATRY AND MALE-BIASED GENE FLOW AMONG REGIONAL POPULATIONS OF THE BLUE-AND-YELLOW MACAW (PSITTACIFORMES: ARA ARARAUNA) IN BRAZIL

Comparing the patterns of population differentiation among genetic markers with different modes of inheritance call provide insights into patterns of sex-biased dispersal and gene flow. The blue-and-yellow Macaw (Ara ararauna) is a Neotropical parrot with a broad geographic distribution ill South America. However, little is known about the natural history and current status Of remaining wild populations, including levels of genetic variability. The progressive decline and possible fragmentation of populations may endanger this species in the near future. We analyzed mitochondrial DNA (mtDNA) control-region sequences and six microsatellite 106 Of Blue-and-yellow Macaws sampled throughout their geographic range ill Brazil to describe population genetic Structure, to make inferences about historical demography and dispersal behavior, and to provide insight for conservation efforts. Analyses of population genetic structure based on mtDNA showed evidence of two major populations ill western and eastern Brazil that share a few low-frequency haplotypes. This phylogeographic pattern seems to have originated by the historical isolation of Blue-and-yellow Macaw populations similar to 374,000 years ago and has been maintained by restricted gene flow and female philopatry. By contrast, variation ill biparentally inherited microsatellites was not structured geographically, Male-biased dispersal and female philopatry best explain the different patterns observed in these two markers. Because females disperse less than males, the two regional populations with well-differentiated mtDNA haplogroups should be considered two different management units for conservation purposes. Received 4 November 2007 accepted 10 December 2008.

La percepció social entorn al delicte i els condicionants que operen en aquesta percepció al municipi de Sant Joan de Vilatorrada

L'objectiu general d'aquesta investigació social és aprofundir en el coneixement de la percepció social entorn al delicte, així com en els condicionants que operen en aquesta percepció al municipi de Sant Joan de Vilatorrada. S'incidirà en el coneixement d'aquesta percepció a partir de la por al delicte i la inseguretat ciutadana, dos fenòmens similars, però no exactament iguals. I els condicionants responen als factors que tenen una influència sobre la por al delicte i la inseguretat ciutadana. D'aquests factors se n'han detectat 34, i només s'estudiaran els nou més rellevants amb la finalitat de saber quin d'ells és el més influent. Tal com s'ha comentat, l'àmbit d'estudi és la població de Sant Joan de Vilatorrada, tot justificant-se pel fet de permetre incorporar el factor de tenir un centre penitenciari al mateix municipi en el qual es resideix. La metodologia escollida és la quantitativa, tot utilitzant la tècnica de l'enquesta. Per altra banda, la mostra és de 2.030 subjectes, tenint present que s'ha obtingut a partir d'una fórmula destinada a calcular les poblacions finites. Finalment, s'han presentat quatre limitacions de l'estudi, tot optant per aportar diverses solucions.

Sampling, WLS, and Mixed Models

Mixed models may be defined with or without reference to sampling, and can be used to predict realized random effects, as when estimating the latent values of study subjects measured with response error. When the model is specified without reference to sampling, a simple mixed model includes two random variables, one stemming from an exchangeable distribution of latent values of study subjects and the other, from the study subjects` response error distributions. Positive probabilities are assigned to both potentially realizable responses and artificial responses that are not potentially realizable, resulting in artificial latent values. In contrast, finite population mixed models represent the two-stage process of sampling subjects and measuring their responses, where positive probabilities are only assigned to potentially realizable responses. A comparison of the estimators over the same potentially realizable responses indicates that the optimal linear mixed model estimator (the usual best linear unbiased predictor, BLUP) is often (but not always) more accurate than the comparable finite population mixed model estimator (the FPMM BLUP). We examine a simple example and provide the basis for a broader discussion of the role of conditioning, sampling, and model assumptions in developing inference.

Limited memory and the essentiality of money

This paper investigates the relationship between memory and the essentiality of money. We consider a random matching economy with a large finite population in which commitment is not possible and memory is limited in the sense that only a fraction m E(0; 1) of the population has publicly observable histories. We show that no matter how limited memory is, there exists a social norm that achieves the first best regardless of the population size. In other words, money can fail to be essential irrespective of the amount of memory in the economy. This suggests that the emphasis on limited memory as a fundamental friction for money to be essential deserves a deeper examination.

FERRITINA: intervalos de referência para adultos no Estado do Rio Grande do Norte

Ferritin is a protein composed of heavy and light chains, non-covalently linked and which accommodates, in its core, thousands of atoms of iron. Furthermore, this protein represents the stock of iron in the body and it is characterized as an acute marker and predictor of diseases, such as iron deficiency anemia, hereditary hemochromatosis and others. Considering the variability of reference values and the analytical methods currently available, the aim of this work was to propose 95% confidence intervals for adults in the State of Rio Grande do Norte, Brazil, after determining the average concentration of serum ferritin for both sexes, beyond its correlation with the age. We analyzed 385 blood samples, collected by venipuncture from individuals residing in the State, after 12-14 hours of fast. The populational sample had 169 men and 216 women between 18-59 years old, which filled a questionnaire on socioeconomic, food habits and accounts about previous and current diseases. The sample collections were itinerant and the results of erythrogram, fasting glucose, alanine aminotransferase, aspartate aminotransferase, γ-glutamyl transferase, urea, creatinine, leukocyte count and platelets, beyond C-reactive protein, were issued to each participant, so that, after selection of the apparently healthy individuals, the dosage of serum ferritin was carried out. Statistical analysis was performed using the softwares SPSS 11.0 Windows version, Epi Info 3.3.2 and Graf instant pad (version 3.02), and the random population sample was single (finite population), for which the test of linear correlation and diagram of dispersion were also made. After selection of individuals and determination of serum ferritin, the most discrepant outliers were disregarded (N = 358, Men = 154/Women = 207) and the average value determined for the masculine sex individuals was 167,18 ng / dL; for the feminine sex individuals, the average value obtained was 81,55 ng / dL. Moreover, we found that 25% of men had values < 90,30 ng / dL; 50% ≤ 156,25 ng / dL and 75% ≤ 229,00 ng / dL. In the group of women, 25% had values < 38,80 ng / dL; 50% ≤ 65,00 ng / dL and 75% ≤ 119,00 ng / dL. Through the correlation coefficient (r = 0,23 with p = 0,003), it is possible to suggest the existence of positive linear correlation between age and serum ferritin for men. The correlation coefficient for women (r = 0,16 with p = 0,025) also confirms the existence of positive linear correlation between serum ferritin and age. Considering the analysis carried out and specific methods corroborating with the proposed benchmarks, we concluded that the average value found for men is higher than that found for women. Furthermore, this scenario rises with age for both sexes, and the 95% confidence intervals obtained were 74 ng/dL ≤ μ ≤ 89 ng/dL and 152ng/dL ≤ μ ≤183ng/dL for the feminine and masculine sex individuals respectively

Independência funcional de idosos no pós-operatório de cirurgia de fêmur proximal: papel do cuidador

Pós-graduação em Saúde Coletiva - FMB