Behavioural development in a matching-to-sample task and token use by an infant chimpanzee reared by his mother

We investigated the behavioural and cognitive development of a captive male infant chimpanzee, Ayumu, raised by his mother, Ai. Here we report Ayumu's achievements up to the age of 2 years and 3 months, in the context of complex computer-controlled tasks. From soon after birth, Ayumu had been present during an experiment performed by his mother. The task consisted of two phases, a matching-to-sample task in which she received token rewards, and the insertion of these tokens into a vending machine to obtain food rewards. Ayumu himself received no reward or encouragement from humans for any of the actions he exhibited during the experiment. At the age of 9 months and 3 weeks, Ayumu performed his first matching-to-sample trial. At around 1 year and 3 months, he began to perform them consistently. Also during this period, he frequently stole food rewards from his mother. At 2 years and 3 months, Ayumu succeeded for the first time in inserting a token into the vending machine. Once he had succeeded in using a token, he performed both phases of the task in sequence 20 times consecutively. The infant's behaviour was not shaped by food rewards but by a strong motivation to copy his mother's behaviour. Our observations of Ayumu thus mirror the learning processes shown by wild chimpanzees.     

Matching-to-sample accuracy on fixed-ratio schedules.

Pigeons performing on a matching-to-sample procedure were exposed to six fixed-ratio (FR) schedules (FR 1, 5, 10, 20, 40, and 60) of food reinforcement for correct matching responses. During both a correction and a noncorrection procedure without an intertrial interval (ITI), matching accuracy was lower on FR 1 and FR 60 than at intermediate ratios. With the FR 1 schedule, both a 5-sec and a 25-sec ITI resulted in higher matching accuracy than without an ITI; accuracy, with an ITI, was fairly constant for ratios of 1 to 20 but declined at higher ratios. The results suggest that the presence or absence of an ITI in matching to sample may account for inconsistencies obtained in earlier studies of the relationship of matching accuracy to ratio size.     

Verbal self-reports about matching to sample: effects of the number of elements in a compound sample stimulus.

Adults' self-reports about their choices in a delayed matching-to-sample task were studied as a function of the number of elements (one, two, or three) in a compound sample stimulus. Signal-detection analyses were used to examine control of self-reports by the number of sample elements, by the speed and accuracy of choices reported about, and by several events contingent on self-reports. On each matching-to-sample trial, a sample element appeared as one of two comparison stimuli. Choice of the matching element, if made within 500 ms of the onset of the comparison stimuli, produced points worth money or chances in a drawing for money, depending on the subject. After each choice, subjects pressed either a "yes" or "no" button to answer a computer-generated query about whether the choice met the point contingency. The number of sample elements in the matching-to-sample task varied across trials, and events contingent on self-reports varied across experimental conditions. In Experiment 1, the conditions were defined by different combinations of feedback messages and point consequences contingent on self-reports, but self-reports were systematically influenced only by the sample-stimulus manipulation. Self-report errors increased with the number of sample elements. False alarms (inaccurate reports of success) were far more common than misses (inaccurate reports of failure), and false alarms were especially likely after choices that were correct but too slow to meet the point contingency. Sensitivity (A') of self-reports decreases as the number of sample elements increased. In addition, self-reports were more sensitive to choice accuracy than to choice speed. All subjects showed a pronounced bias (B'H) for reporting successful responses, although the bias was reduced as the number of sample elements increased and successful choices became less frequent. Experiment 2 demonstrated that the failure of point contingencies to influence self-reports in the first experiment was not due to a general ineffectiveness of the point consequences. Rates of inaccurate self-reports decreased when they resulted in point losses and increased when they resulted in point gains.     

The effect of increased response requirements on discriminative performance of the domestic hen in a visual acuity task.

Six domestic hens were trained in a spatial discrimination task. A controlled reinforcement procedure insured that the ratio of scheduled and obtained reinforcement remained equal. Gray stimuli and gratings ranging in spatial frequency from 1 to 10 cycles per millimeter were presented in seven descending series of probes. The response requirement to the sample key was varied from fixed ratio 1 to fixed ratio 40 in seven experimental conditions. An increase in response requirements from fixed ratio 1 to fixed ratio 5 and fixed ratio 10 resulted in significantly higher accuracy at discriminable grating values. Further increases in response requirements did not consistently improve performance. Generally, response biases increased and occasionally became extreme for probes at finer gratings with increased response requirements.     

Transient effects of acquisition history on generalization in a matching-to-sample task

This study examined the role of learning history on the acquisition of a matching-to-sample task. Twelve preschool children learned four stimulus classes through instructions, shaping, or imitation. After reaching criterion, the subjects were exposed to changed discrimination contingencies to determine how each learning history affected the acquisition of responses appropriate to the new contingencies. All subjects reached criterion on the new relations, although the subjects with a shaping history adapted slightly more quickly than those subjects with a history of instructions or imitation. Given sufficient exposure to changed contingencies, rule-driven insensitivity to contingencies was overcome by experience with consequences. This result may be specific to younger subjects, but it suggests that instructions can be used in education without creating insensitivity to contingencies.     

Intuitions about sample size: the empirical law of large numbers

According to Jacob Bernoulli, even the ‘stupidest man’ knows that the larger one's sample of observations, the more confidence one can have in being close to the truth about the phenomenon observed. Two-and-a-half centuries later, psychologists empirically tested people's intuitions about sample size. One group of such studies found participants attentive to sample size; another found participants ignoring it. We suggest an explanation for a substantial part of these inconsistent findings. We propose the hypothesis that human intuition conforms to the ‘empirical law of large numbers’ and distinguish between two kinds of tasks–one that can be solved by this intuition (frequency distributions) and one for which it is not sufficient (sampling distributions). A review of the literature reveals that this distinction can explain a substantial part of the apparently inconsistent results. © 1997 John Wiley & Sons, Ltd.     

Concurrent validity of the DSM-IV scales Affective Problems and Anxiety Problems of the Youth Self-Report

This study investigated the concurrent validity of the DSM-IV scales Anxiety Problems and Affective Problems of the Youth Self-Report (YSR) in a community sample of Dutch young adolescents aged 10-12 years. We first examined the extent to which the YSR/DSM-IV scales reflect symptoms of DSM-IV anxiety disorders and DSM-IV Major Depressive Disorder, assessed with the Revised Child Anxiety and Depression Scale (RCADS). Second, we examined whether the association between the YSR/DSM-IV scales and the RCADS scales was stronger than the association between the empirically derived YSR narrow-band scales Anxious/Depressed and Withdrawn and the same RCADS scales. Results showed that the YSR/DSM-IV scale Affective Problems had a stronger association with symptoms of DSM-IV Major Depressive Disorder than the YSR narrow-band scales Withdrawn and Anxious/Depressed. However, the YSR/DSM-IV scale Anxiety Problems had a weaker association with symptoms of DSM-IV anxiety disorders, compared to the YSR narrow-band scale Anxious/Depressed. It was concluded that the construction of the DSM-IV scales improved the correspondence with DSM-IV Major Depressive Disorder, but not with DSM-IV anxiety disorders.     

Asymptotic identifiability of nonparametric item response models

The identifiability of item response models with nonparametrically specified item characteristic curves is considered. Strict identifiability is achieved, with a fixed latent trait distribution, when only a single set of item characteristic curves can possibly generate the manifest distribution of the item responses. When item characteristic curves belong to a very general class, this property cannot be achieved. However, for assessments with many items, it is shown that all models for the manifest distribution have item characteristic curves that are very near one another and pointwise differences between them converge to zero at all values of the latent trait as the number of items increases. An upper bound for the rate at which this convergence takes place is given. The main result provides theoretical support to the practice of nonparametric item response modeling, by showing that models for long assessments have the property of asymptotic identifiability. The research was partially supported by the National Institute of Health grant R01 CA81068-01.