Terms Of Inference Research Articles

Genetic variability in banana diploids and nonparametric statistics of fragments associated with natural fruit finger drop

Natural fruit finger drop in bananas is one of the major concerns of producers as well as consumers. The aim of this study was to estimate the genetic diversity among 15 diploid bananas with different levels of resistance to finger drop (RFD) using SSR and ISSR (inter-simple sequence repeat) markers, and assess the possibility of association of bands with RFD variables (v1 and v2) via nonparametric methodologies. Molecular genetic analysis revealed that the dendrogram generated by SSR markers used as co-dominant markers better discriminated the genotypes as to genome constitution, genealogy, and RFD. Although nonparametric tests are limited in terms of inferences, they are very useful when data do not follow normal distribution, such as the case in our study. Bananas are parthenocarpic, which hinders obtainment of representative genetic linkage maps and linkage studies due to small number of segregating populations; a pre-requisite for mapping and QTL studies. Therefore, non-conventional methodologies, such as nonparametric tests, become an attractive alternative to overcome this barrier. In our study, the nonparametric tests, Kruskal-Wallis and Spearman correlation, revealed negative and positive associations with RFD for 12 bands (7 from ISSR markers and 5 from SSR markers) with high positive and negative correlations. The results show potential for future sequencing of bands, obtaining sequence-characterized amplified region markers, validation, and subsequent possibility for application in marker-assisted selection in banana genetic breeding programs. This is the first report of the use of nonparametric statistics in attempt to evaluate the association between fruit finger drop and ISSR bands in Musa spp.

Modeling jointly low, moderate, and heavy rainfall intensities without a threshold selection

AbstractIn statistics, extreme events are often defined as excesses above a given large threshold. This definition allows hydrologists and flood planners to apply Extreme‐Value Theory (EVT) to their time series of interest. Even in the stationary univariate context, this approach has at least two main drawbacks. First, working with excesses implies that a lot of observations (those below the chosen threshold) are completely disregarded. The range of precipitation is artificially shopped down into two pieces, namely large intensities and the rest, which necessarily imposes different statistical models for each piece. Second, this strategy raises a nontrivial and very practical difficultly: how to choose the optimal threshold which correctly discriminates between low and heavy rainfall intensities. To address these issues, we propose a statistical model in which EVT results apply not only to heavy, but also to low precipitation amounts (zeros excluded). Our model is in compliance with EVT on both ends of the spectrum and allows a smooth transition between the two tails, while keeping a low number of parameters. In terms of inference, we have implemented and tested two classical methods of estimation: likelihood maximization and probability weighed moments. Last but not least, there is no need to choose a threshold to define low and high excesses. The performance and flexibility of this approach are illustrated on simulated and hourly precipitation recorded in Lyon, France.

ALGUMAS CONSIDERAÇÕES PRÁTICAS SOBRE A PRECISÃO DOS ESIMADORES DE MÍNIMOS QUADRADOS E MÁXIMA VEROSSIMILHANÇA PARA OS PARÂMETROS DE REGRESSÃO LINEAR NORMAL

In this paper, we discuss some practical considerations on the use of different methods for the estimation of linear regression parameters and their impact on the obtained inferences. In practice, it is common to use some existing statistical software to obtain the least squares estimators (MSE) for the regression parameters and consider a non-biased estimator for the variance based on the residual squared sum of the residuals. Alternatively, we discuss the use of the maximum likelihood estimator (MLE) for the variance of the error (an unbiased estimator, but with smaller squared error) which may lead to different conclusions in terms of inferences. Two numerical examples are presented to illustrate the proposed method.

Modeling and evaluating Gaussian mixture model based on motion granularity

To model manipulation tasks, we propose a novel method for learning manipulation skills based on the degree of motion granularity. Even though manipulation tasks usually consist of a mixture of fine-grained and coarse-grained movements, to the best of our knowledge, manipulation skills have so far been modeled without considering their motion granularity. To model such a manipulation skill, Gaussian mixture models (GMMs) have been represented using several well-known techniques such as principal component analysis, k-means, Bayesian information criterion, and expectation-maximization (EM) algorithms. However, in this GMM, there is a problem in that when a mixture of fine-grained and coarse-grained movements is modeled as a GMM, fine-grained movements tend to be poorly represented. To resolve this issue, we measure a continuous degree of motion granularity for every time step of a manipulation task from a GMM. Then, we remodel the GMM by weighting a conventional k-means algorithm with motion granularity. Finally, we also estimate the parameters of the GMM by weighting the conventional EM with motion granularity. To validate our proposed method, we evaluate the GMM estimated using our proposed method by comparing it with those estimated by different GMMs in terms of inference, regression, and generalization using a robot arm that performs two daily tasks, namely decorating a very small area and passing through a narrow tunnel.

A Duet for one.

This paper considers communication in terms of inference about the behaviour of others (and our own behaviour). It is based on the premise that our sensations are largely generated by other agents like ourselves. This means, we are trying to infer how our sensations are caused by others, while they are trying to infer our behaviour: for example, in the dialogue between two speakers. We suggest that the infinite regress induced by modelling another agent - who is modelling you - can be finessed if you both possess the same model. In other words, the sensations caused by others and oneself are generated by the same process. This leads to a view of communication based upon a narrative that is shared by agents who are exchanging sensory signals. Crucially, this narrative transcends agency - and simply involves intermittently attending to and attenuating sensory input. Attending to sensations enables the shared narrative to predict the sensations generated by another (i.e. to listen), while attenuating sensory input enables one to articulate the narrative (i.e. to speak). This produces a reciprocal exchange of sensory signals that, formally, induces a generalised synchrony between internal (neuronal) brain states generating predictions in both agents. We develop the arguments behind this perspective, using an active (Bayesian) inference framework and offer some simulations (of birdsong) as proof of principle.

The Effects of Product Innovation on Online Search and Choice

We develop a probit choice model under optimal sequential search and apply it to the study of aggregate demand of consumer durable goods. In our joint model of search and choice, we derive a semi-closed form expression for the probability of choice that obeys the full set of restrictions imposed by optimal sequential search. Our joint model leads to a partial simulation-based estimation that avoids high-dimensional integrations in the evaluation of choice probabilities and that is particularly attractive when search sets are large. We illustrate the advantages of our approach using aggregate search and choice data from the camcorder product category at Amazon.com. We show that the joint use of search and choice data provides better performance in terms of inferences and predictions than using search data alone and leads to realistic estimates of consumer substitution patterns.

Local and global asymptotic inference in smoothing spline models

This article studies local and global inference for smoothing spline estimation in a unified asymptotic framework. We first introduce a new technical tool called functional Bahadur representation, which significantly generalizes the traditional Bahadur representation in parametric models, that is, Bahadur [Ann. Inst. Statist. Math. 37 (1966) 577-580]. Equipped with this tool, we develop four interconnected procedures for inference: (i) pointwise confidence interval; (ii) local likelihood ratio testing; (iii) simultaneous confidence band; (iv) global likelihood ratio testing. In particular, our confidence intervals are proved to be asymptotically valid at any point in the support, and they are shorter on average than the Bayesian confidence intervals proposed by Wahba [J. R. Stat. Soc. Ser. B Stat. Methodol. 45 (1983) 133-150] and Nychka [J. Amer. Statist. Assoc. 83 (1988) 1134-1143]. We also discuss a version of the Wilks phenomenon arising from local/global likelihood ratio testing. It is also worth noting that our simultaneous confidence bands are the first ones applicable to general quasi-likelihood models. Furthermore, issues relating to optimality and efficiency are carefully addressed. As a by-product, we discover a surprising relationship between periodic and nonperiodic smoothing splines in terms of inference.

A Disconfirming Strategy Is Not Necessarily Better Than a Confirming Strategy

College students were presented with 4 events to be explained. Each event was accompanied by either a target explanation or a target and an alternative, and all explanations were causal mechanistic. For each event, participants were also presented with 12 pieces of information. Four of the 12 pieces were causally consistent with the target, 4 with the alternative, and 4 were neutral. Participants were assigned to one of 3 strategy conditions, depending on what they were explicitly told to do: confirm, disconfirm, or evaluate the target explanation. People told to disconfirm were more likely than people in the other conditions to cite, as strategy appropriate, information that was in fact neutral. In addition, across strategy conditions, the presence of an alternative decreased the likelihood of identifying, as appropriate to the strategy, information that was strategy inappropriate. Results are discussed in terms of inference to the best explanation and in terms of confirmation bias.

Patterns of volatility transmissions within regime switching across GCC and global markets

Unlike previous studies, this paper examines volatility transmission patterns for pairs of six stock markets of countries of the Gulf Cooperation Council (GCC) and pairs of these markets with the three global markets (S&P 500 index, Oil-WTI prices and MSCI-world), using the Multi-Chain Markov Switching (MCMS) model. This approach allows for a distinction between well diverse transmission patterns including volatility spillover, interdependence, independence and co-movements, given changes from high to low volatility regimes and vice versa. The results find evidence of different transmission patterns between the GCC and the global markets, with stronger connections with the global equity than with the oil markets. These patterns are also highly sensitive to the regimes of the selected markets which are characterized by turbulence or tranquility. For the first global market (Oil-WTI), the results show evidence of strong interdependence between Oil and each of the Kuwait and Abu Dhabi markets. Additionally, there is spillover from Oil-WTI to Dubai whose economy depends on oil, real estate and tourism. Surprisingly, we find evidence of independence between Oil and each of the Saudi Arabia, Qatar and Oman markets. For the second global market (the U.S. S&P 500 index), the results support strong interdependence with Saudi Arabia, Dubai and Abu Dhabi. There is also spillover from the S&P 500 index to Kuwait and Oman. More interestingly, we find spillover from Qatar to the S&P 500 index. For the third global market (MSCI-World), there is interdependence between MSCI and Dubai. We also find evidence of spillover from the MSCI-world to Kuwait and Saudi Arabia. Finally, we provide results in terms of inference on the regimes of high and low volatility, allowing for the interpretation of the financial shocks and the dates in which they are transmitted from one market to another. Policy implications are also provided.

Making Inferences about Intention: Perceptual Control Theory as a “Theory of Mind” for Psychologists

Theory of Mind (ToM) assumes that humans and possibly other primates understand behavior in terms of inferences about intentions. While there is evidence that primates make such inferences, little attention has been paid to the question of their validity. In order to answer this question it is necessary to know the true intentions underlying behavior. The present paper shows that Perceptual Control Theory can provide a scientific basis for making such determinations using methods derived from control engineering. These methods--called the "Test for the Controlled Variable" (TCV)--are based on the assumption that intentional behavior is equivalent to the process of control. The TCV provides an objective approach to inferring the intentions underlying behavior in terms of the perceptual variables under control and the goal states of those variables. Thus, Perceptual Control Theory represents an empirical ToM for psychologists--one that can be used to understand behavior in terms of inferences about intention that are based on the results of active experimentation rather than passive observation.

The counterintuitive effects of thank-you gifts on charitable giving

Six experiments examined the effects of thank-you gifts on charitable giving. Results indicate that although people expect that the offer of thank-you gifts will increase donations, such offers actually reduce charitable donations. This effect was obtained across a wide variety of charities and gifts types, regardless of whether the donations were hypothetical or real, the gift was desirable or undesirable, the charity was familiar or unfamiliar, or the gift was more or less valuable. Moreover, such patterns cannot solely be explained in terms of inferences about the charity’s quality (e.g., either their efficacy or current wealth), the undesirability of the gift itself, or simple anchoring effects. These results are discussed within a broader theoretical framework concerning the effects of extrinsic incentives on altruistic behavior.

Measuring safety treatment effects using full Bayes non-linear safety performance intervention functions

Full Bayes linear intervention models have been recently proposed to conduct before–after safety studies. These models assume linear slopes to represent the time and treatment effects across the treated and comparison sites. However, the linear slope assumption can only furnish some restricted treatment profiles. To overcome this problem, a first-order autoregressive (AR1) safety performance function (SPF) that has a dynamic regression equation (known as the Koyck model) is proposed. The non-linear ‘Koyck’ model is compared to the linear intervention model in terms of inference, goodness-of-fit, and application. Both models were used in association with the Poisson-lognormal (PLN) hierarchy to evaluate the safety performance of a sample of intersections that have been improved in the Greater Vancouver area. The two models were extended by incorporating random parameters to account for the correlation between sites within comparison–treatment pairs. Another objective of the paper is to compute basic components related to the novelty effects, direct treatment effects, and indirect treatment effects and to provide simple expressions for the computation of these components in terms of the model parameters. The Koyck model is shown to furnish a wider variety of treatment profiles than those of the linear intervention model. The analysis revealed that incorporating random parameters among matched comparison–treatment pairs in the specification of SPFs can significantly improve the fit, while reducing the estimates of the extra-Poisson variation. Also, the proposed PLN Koyck model fitted the data much better than the Poisson-lognormal linear intervention (PLNI) model. The novelty effects were short lived, the indirect (through traffic volumes) treatment effects were approximately within ±10%, whereas the direct treatment effects indicated a non-significant 6.5% reduction during the after period under PLNI compared to a significant 12.3% reduction in predicted collision counts under the PLN Koyck model.

What is value-accumulated reward or evidence?

Why are you reading this abstract? In some sense, your answer will cast the exercise as valuable—but what is value? In what follows, we suggest that value is evidence or, more exactly, log Bayesian evidence. This implies that a sufficient explanation for valuable behavior is the accumulation of evidence for internal models of our world. This contrasts with normative models of optimal control and reinforcement learning, which assume the existence of a value function that explains behavior, where (somewhat tautologically) behavior maximizes value. In this paper, we consider an alternative formulation—active inference—that replaces policies in normative models with prior beliefs about the (future) states agents should occupy. This enables optimal behavior to be cast purely in terms of inference: where agents sample their sensorium to maximize the evidence for their generative model of hidden states in the world, and minimize their uncertainty about those states. Crucially, this formulation resolves the tautology inherent in normative models and allows one to consider how prior beliefs are themselves optimized in a hierarchical setting. We illustrate these points by showing that any optimal policy can be specified with prior beliefs in the context of Bayesian inference. We then show how these prior beliefs are themselves prescribed by an imperative to minimize uncertainty. This formulation explains the saccadic eye movements required to read this text and defines the value of the visual sensations you are soliciting.

General solutions to consistency problems in multiple hypothesis testing

Coherence and consonance are the two important concepts to ensure consistent conclusions drawn from multiple tests. Unlike coherence, consonance of a multiple testing procedure (MTP) has not yet received much attention. Although most of the MTPs used in practice are consonant, cases still exist that dissonant tests have to be used due to their unique advantages, for example, the likelihood ratio tests and sum tests. Consonance adjustments are necessary for such tests to avoid difficulty in interpretation. Moreover, in terms of detecting elementary hypotheses, a consonant test procedure is uniformly more powerful than the corresponding dissonant one. In this paper, several general methods using the partitioning principle to construct (strongly) consonant and strongly coherent MTPs are proposed. As a result, any dissonant (but coherent) multiple level α test can be improved by a consonant one without any cost in terms of inferences on elementary hypotheses.

Analysis of treatment response data from eligibility designs

In this paper, we develop and compare two alternative approaches for calculating the effect of the actual intake when treatments are randomized, but compliance with the assignment in the treatment arm is less than perfect for reasons that are correlated with the outcome. The approaches are based on different identification assumptions about these unobserved confounders. In the first approach, which stems from [Sommer, A., Zeger, S., 1991. On estimating efficacy in clinical trials. Statistics in Medicine 10, 45–52], the unobserved confounders are modeled by a discrete indicator variable that represents subject-type, defined in terms of the potential intake in the face of each possible assignment. In the second approach, confounding is modeled without reference to subject-type in the spirit of the Roy model. Because the two models are non-nested, and model comparison and assessment of the approaches in a real data setting is one of our central goals, we formulate the discussion from a Bayesian perspective, comparing the two models in terms of marginal likelihoods and Bayes factors, and in terms of inferences about the treatment effects. The latter we calculate from a predictive perspective in a way that is different from that in the literature, where typically only a point summary of that effect is calculated. Our real data analysis focuses on the JOBS II eligibility trial that was implemented to test the effectiveness of a job search seminar in decreasing the negative mental health effects commonly associated with job loss. We provide a comparative analysis of the data from the two approaches with prior distributions that are both reasonable in the context of the data and comparable across the model specifications. We show that the approaches can lead to different evaluations of the treatment.

An expert system using an extended AND–OR graph

The inference engine (IE) is a crucial component of expert systems (ES). As the management environment has become rapidly digitalized with the advent of the Internet, the traditional IE is now facing a severe criticism – i.e., that it cannot effectively provide an agile, knowledge-based decision support suitable for a wide variety of problems. The objective of this paper is to propose a new type of ES called IMIXAO (Integer-Matrix-driven Inference based on an eXtended AND–OR graph), with an integer-matrix-driven IE based on an extended AND–OR graph framework. Traditionally, the AND–OR graph is used for making inferences in the ES area. Theoretical backgrounds of IMIXAO are presented in this paper, focusing on what an extended AND–OR graph is in terms of inference. The experiment conducted in this study, with an illustrative example of dermatological diseases classification, revealed that the proposed IMIXAO can make precise and agile inferences in a complex situation.

Comparison of SNP tagging methods using empirical data: association study of 713 SNPs on chromosome 12q14.3–12q24.21 for asthma and total serum IgE in an African Caribbean population

Few comparison studies have been performed on single nucleotide polymorphism (SNP) tagging methods to examine their consistency and effectiveness in terms of inferences about association with disease. We applied several SNP tagging methods to SNPs on chromosome 12q (n=713) and compared the utility of these methods to detect association for asthma and serum IgE levels among a sample of African Caribbean families from Barbados selected through asthmatic probands. We found that a high level of information regarding association is retained in Clayton's htSNP, Stram's TagSNP, and de Bakker's Tagger. We also found a high degree of consistency between TagSNP and Tagger. Using this set of 713 SNPs on chromosome 12q, our study provides insight towards analytic strategies for future studies of complex traits.

How Sensitive Are Cost-Effectiveness Analyses to Choice of Parametric Distributions?

Cost-effectiveness analyses of clinical trial data are based on assumptions about the distributions of costs and effects. Cost data usually have very skewed distributions and can be difficult to model. The authors investigate whether choice of distribution can make a difference to the conclusions drawn. The authors compare 3 distributions for cost data-normal, gamma, and lognormal-using similar parametric models for the cost-effectiveness analyses. Inferences on the cost-effectiveness plane are derived, together with cost-effectiveness acceptability curves. These methods are applied to data from a trial of rapid magnetic resonance imaging (rMRI) investigation in patients with low back pain. The gamma and lognormal distributions fitted the cost data much better than the normal distribution. However, in terms of inferences about cost-effectiveness, it was the normal and gamma distributions that gave similar results. Using the lognormal distribution led to the conclusion that rMRI was cost-effective for a range of willingness-to-pay values where assuming a gamma or normal distribution did not. Conclusions from cost-effectiveness analyses are sensitive to choice of distribution and, in particular, to how the upper tail of the cost distribution beyond the observed data is modeled. How well a distribution fits the data is an insufficient guide to model choice. A sensitivity analysis is therefore necessary to address uncertainty about choice of distribution.

Gravitational lensing and Hacking's extragalactic irreality

In Extragalactic Reality: The Case of Gravitational Lensing Hacking resumes the discussion of scientific realism from the last chapter of Representing and Intervening. Since the criterion of manipulability cannot be applied to astronomical objects, experimental entity realism seems to be restricted to terrestrial entities. In fact, Hacking explicitly argues against astronomical realism. The case at issue is the existence of gravitational lenses. In this paper, I question Hacking's chief witness for astronomical antirealism: the gravitational lens system “0957+ 561”. It will be shown that Hacking's argumentation is misleading. Discussing astronomical realism as theory realism, Hacking focuses on the question of how to infer the existence of gravitational lenses from the truth of gravitational lens theory. But neither the reconstruction of gravitational lensing in terms of inference to the best explanation (IBE) nor the argument of underdetermination are tenable under closer inspection. My thesis is that a realist account of gravitational lensing can be given by relying on observation, causal capacities and home truths.

Some advantages of permutation tests.

AbstractThere are two especially useful models of statistical inference, although only one, the model, is universally taught. The less well known permutation model is contrasted with the model and the case made that the permutation model is often more appropriate for the analysis of psychological data. Inappropriate interpretations generated by teaching only the model are illustrated. It is recommended that both models be taught so that students and applied workers have a better chance both of understanding the nature of the hypothesis that is being tested, and of correctly discriminating the statistical conditions that support causal inference and generality inference.Nearly all statistical testing is introduced using the normal curve model that leads to analysis of data by t and F ratios and to a preoccupation with generalizability of research results. The model is so common that many applied workers assume that it is the only model for statistical testing. The model was originally designed for parameter estimation and expresses the null hypothesis in terms of population parameters. For example, the null hypothesis for assessing the difference between two means is often expressed as Equation. As we all know, the ideal conditions for using the model to test statistical hypotheses such as this involve cases randomly selected from normally distributed parent populations with equal variances.Even textbook authors who introduce statistical testing with the binomial test emphasize the necessity of random sampling from a specified population. In most empirical research however, the concept of population enters statistical analysis not because the experimenter has actually randomly sampled some population to which he or she wishes to generalize, but because the only way researchers have been taught to interpret the results of statistical tests is in terms of inferences about populations.Kempthorne (1979) proposed that attempts to place all inferential situations in the model are misguided. He suggests that trying to encompass all types of investigation under one framework has led to the pooling of different types of investigation that have strongly different logical natures. For example, surveys and comparative experiments have different methods of data collection and different inferential goals. A major concern of surveys is external validity and generality inference, whereas comparative experiments are more concerned with internal validity and causal inference. Thus, we may need different statistical models for different research contexts.The Permutation ModelAn alternative to the model is the permutation or randomization model initiated by Fisher (1935) and developed by Pitman (1937a, 1937b, 1938). The permutation model is because no formal assumptions are made about the population parameters of the reference distribution, i.e., the distribution to which an obtained result is compared to determine its probability when the null hypothesis is true. Typically the reference distribution is a sampling distribution for parametric tests and a permutation distribution for many tests.(f.1)For many applied workers, nonparametric has been equated with rank tests. That is, either the data are ranks, or scores are transformed to ranks before conducting a statistical test. It is important to point out that the familiar rank tests, such as the Wilcoxon Rank - Sum test or Mann - Whitney U test, are members of a family of tests called permutation tests or randomization tests. It is less well known that there are two sets of permutation tests, those based on ranks and those based on scores. The tests on ranks traditionally have been named after the persons who were important in their development (e.g., Mann - Whitney, Wilcoxon, Kruskal - Wallis, Friedman). Often, tests of scores are referred to just as permutation tests although some reference has been made to the Fisher - Pitman test (e. …