Did Pearson reject the Neyman-Pearson philosophy of statistics?

I document some of the main evidence showing that E. S. Pearson rejected the key features of the behavioral-decision philosophy that became associated with the Neyman-Pearson Theory of statistics (NPT). I argue that NPT principles arose not out of behavioral aims, where the concern is solely with behaving correctly sufficiently often in some long run, but out of the epistemological aim of learning about causes of experimental results (e.g., distinguishing genuine from spurious effects). The view Pearson did hold gives a deeper understanding of NPT tests than their typical formulation as accept-reject routines, against which criticisms of NPT are really directed. The Pearsonian view that emerges suggests how NPT tests may avoid these criticisms while still retaining what is central to these methods: the control of error probabilities.A portion of this research was carried out during tenure of a National Endowment for the Humanities Summer Stipend Fellowship; I gratefully acknowledge that support. A version of this paper was presented at the 1987 meeting of the Society for Exact Philosophy. This paper benefited from discussions and communications with George Barnard and Isaac Levi. I thank Harlan Miller for helpful comments on earlier drafts.     

An automated test development of parallel tests from a seed test

Binary programming models are presented to generate parallel tests from an itembank. The parallel tests are created to match item for item an existing seed test and match user supplied taxonomic specifications. The taxonomic specifications may be either obtained from the seed test or from some other user requirement. An algorithm is presented along with computational results to indicate the overall efficiency of the process. Empirical findings based on an itembank for the Arithmetic Reasoning section of the Armed Services Vocational Aptitude Battery are given.The Office of Naval Research, Program in Cognitive Science, N00014-87-C-0696 partially supported the work of Douglas H. Jones. The Rutgers Research Resource Committee of the Graduate School of Management partially supported the work of Douglas H. Jones and Ing-Long Wu. A Thomas and Betts research fellowship partially supported the work of Ing-Long Wu. The Human Resources Laboratory, United States Air Force, partially supported the work of Ronald Armstrong. The authors benefited from conversations with Dr. Wayne Shore, Operational Technologies, San Antonio, Texas. The order of authors' names is alphabetical and denotes equal authorship.     

Reaction time and temporal serial judgment: corroboration or dissociation?]

Dissociations between a motor response and the subject's verbal report have been reported from various experiments that investigated special experimental effects (e.g., metacontrast or induced motion). To examine whether similar dissociations can also be observed under standard experimental conditions, we compared reaction times (RT) and temporal order judgments (TOJ) to visual and auditory stimuli of three intensity levels. Data were collected from six subjects, each of which served for nine sessions. The results showed a strong, highly significant modality dissociation: While RTs to auditory stimuli were shorter than RTs to visual stimuli, the TOJ data indicated longer processing times for auditory than for visual stimuli. This pattern was found over the whole range of intensities investigated. Light intensity had similar effects on RT and TOJ, while there was a marginally significant tendency of tone intensity to affect RT more strongly than TOJ. It is concluded that modality dissociation is an example of "direct parameter specification", where the pathway from stimulus to response in the simple RT experiment is (at least partially) separate from the pathway that leads to a conscious, reportable representation. Two variants of this notion and alternatives to it are discussed.     

Degree of learning,interpolated tests,and rate of forgetting

The purpose of the two experiments reported here was to observe the effects of degree of learning, interpolated tests, and retention interval, primarily on the rate of forgetting of a list of words, and secondarily on hypermnesia for those words. In the first experiment, all the subjects had one study trial on a list of 20 common words, followed by two tests of recall. Half of the subjects had further study and test trials until they had learned the words to a criterion of three correct consecutive recalls. Two days later, half of the subjects under each learning condition returned for four retention tests, and 16 days later, all the subjects returned for four tests. Experiment 2 was similar, except that all the subjects had at least three study trials followed by four recall tests on Day 1, intermediate tests were given 2 or 7 days later, and they all had final tests 14 days later. The results showed that rate of forgetting was attenuated by an additional intermediate set of tests but not by criterion learning. Hypermnesia was generally found over the tests that were given after a retention interval of 2 or more days. The best predictor of the amount of hypermnesia over a set of tests was the difference between overall cumulative recall and net recall on the first test of the set.     

The effects of syntactic structure on letter detection in adjacent function words

In the present study, we examined letter detection in very frequent function-word sequences. It has been claimed that such sequences are processed in a unitized manner, thus preempting access to their constituent letters. In contrast, we showed that letter detection in the words for and the (1) was no more difficult when the words appeared in adjacent locations in a sentence (familiar) than when they appeared apart (less familiar sequence) and (2) was contingent upon the words' syntactic roles within the phrase. Thus, letter detection in for was easier when the sequence was separated by a clause boundary than when the words were part of the same clause. The advantage derived from clause separation was strongest when a comma divided clauses. These results challenge the unitization account of the "missing-letter" effect in common phrases and support a position where this phenomenon is seen to reflect the extraction of phrase structure during reading.     

Supernatural beliefs,natural kinds,and conceptual structure

This article presents cross-cultural evidence in support of the notion that adults' natural kind concepts are theory based but may be informed by knowledge/belief systems other than the biological. Three groups of subjects from western Nigeria--rural, urban, and elite--participated in the study. Subjects heard stories describing alterations of appearance; that is, one natural kind was made to resemble another in both ritual and nonritual contexts. Subjects then were required to judge the identity of the altered item and to give an explanation for the category judgment. It was predicted that subjects would make more nonpreservation-of-identity category judgments supported by supernatural explanations in the ritual contexts and that subjects' use of supernatural explanations would reflect the extent of their engagement with the supernatural. The first prediction was borne out; the second prediction was only partially supported. Discussion of the results emphasizes the importance of exploring the role of sociocultural factors in conceptual structure.     

Sentence encoding and implicitly activated memories

Some words have fewer direct associates than others, and, when words varying in set size are studied in a list-learning task, those with smaller sets are more likely to be recalled. This set-size effect is found in cued recall when the words are studied in the absence of related words, but not when studied in the presence of related words. Related words provide context and theoretically inhibit irrelevant associates. The present research determined that set-size effects are found when words are encoded in sentence contexts. In contrast to list-learning experiments, the results of three experiments found such effects even when lexically related words were present in the sentences. Other findings indicated that target-set-size effects were determined by the proximity of related words in the sentence and the nature of the test cue. The results are discussed in relation to a model for explaining set-size effects and to selective findings from the sentence-comprehension literature.     

The representation and integration in memory of spatial and nonspatial information

A series of experiments investigated whether people could integrate nonspatial information about an object with their knowledge of the object's location in space. In Experiments 1 and 3, subjects learned the locations of cities on a fictitious road map; in Experiments 2, 4, and 5, subjects were already familiar with the locations of buildings on a campus. The subjects then learned facts about the cities on the maps or the buildings on the campus. The question of interest was whether or not these nonspatial facts would be integrated in memory with the spatial knowledge. After learning the facts, subjects were given a location-judgment test in which they had to decide whether an object was in one region of the space or another. Knowledge integration was assessed by comparing levels of performance in two conditions: (a) when a city or a building name was primed by a fact about a neighboring city or building, and (b) when a city or a building name was primed by a fact about a distant city or building. Results showed that responses in Condition a were faster or more accurate, or both faster and more accurate, than responses in Condition b. These results indicate that the spatial and nonspatial information were encoded in a common memory representation.     

Cuing effects and associative information in recognition memory

Item recognition requires discrimination of studied words from nonstudied words. Associative recognition requires subjects to discriminate studied word groups from recombinations of words from different groups. Cued recognition requires the same old-new discrimination as item recognition, but list items are presented as cues along with the test item. The results from three experiments show (1) little or no effect of cuing for low-frequency words, but (2) positive cuing effects for high-frequency words; (3) increasing levels of overall performance with increases in study time, but (4) unchanging effects of cuing with study time; and (5) stronger positive cuing effects for two cues than for one cue. Five models (Independent Cue Model, Matrix model, MINERVA 2, SAM, and TODAM) were fit to the data of Experiment 1. Each model has trouble with at least one aspect of the results. Theoretical implications and modifications are discussed at length.     

Acoustic analysis in the differentiation of Parkinson's disease and major depression

In its early stages, Parkinson's disease (P.D.) may be difficult to distinguish from major depression (M.D.) leading to inappropriate management. Both illnesses are characterized by psychomotor retardation. The neurovegetative symptoms used to diagnose M.D. are not specific and in P.D. may be due to the physical illness itself. Currently, differentiation of the two disorders relies on subjective clinical observation. Improved diagnostic accuracy based on more objective data is needed. To this end, this study used computerized acoustic analysis to contrast speech patterns in P.D. and M.D. The sample consisted of 30 P.D. patients without depression or dementia, 30 patients with uncomplicated M.D., and 31 normal controls, each 60 years of age or over. Of the acoustic variables studied, M.D. patients had significantly reduced rates of speech compared with P.D. patients. The data suggest that this temporal measure of speech may be useful in the differentiation of P.D. and M.D.