Assumptions behind scoring source versus item memory: Effects of age, hippocampal lesions and mild memory problems

Abstract

Source monitoring paradigms have been used to separate: 1) the probability of recognising an item (Item memory) and 2) the probability of remembering the context in which that item was previously encountered (Source memory), conditional on it being recognised. Multinomial Processing Tree (MPT) models are an effective way to estimate these conditional probabilities. Moreover, MPTs make explicit the assumptions behind different ways to parameterise Item and Source memory. Using data from six independent groups across two different paradigms, we show that one would draw different conclusions about the effects of age, age-related memory problems and hippocampal lesions on Item and Source memory, depending on the use of: 1) standard accuracy calculation vs MPT analysis, and 2) two different MPT models. The MPT results were more consistent than standard accuracy calculations, and furnished additional parameters that can be interpreted in terms of, for example, false recollection or missed encoding. Moreover, a new MPT structure that allowed for separate memory representations (one for item information and one for item-plus-source information; the Source-Item model) fit the data better, and provided a different pattern of significant differences in parameters, than the more conventional MPT structure in which source information is a subset of item information (the Item-Source model). Nonetheless, there is no theory-neutral way of scoring data, and thus proper examination of the assumptions underlying the scoring of source monitoring paradigms is necessary before theoretical conclusions can be drawn.

Keywords: Ageing; Item memory; Multinomial processing tree models; Source memory; Source monitoring.

Fig. 1

Venn diagrams (left) and Multinomial Processing Trees (MPTs, right) for different memory models. In Venn diagrams, “I” refers to memory system/process underlying Item memory, and “S + I” refers to memory system/process underlying both Source and Item memory. In MPTs, leftmost root of tree denotes trial type and rightmost ends of branches denote various response outcomes. MPTs in Panels A–C distinguish three models in their characterisation of responses to items studied in Source 1 (S1); MPT in Panel D captures responses to unstudied (new) items, and is shared across the three models. The Item-Source Model (A) assumes source memory is a subset of item memory, perhaps subserved by a single memory system/process. The Source-Item Model (B) assumes two memory systems/processes contribute to memory (in an exclusive fashion). The Independent-Source-Item Model (C) assumes two memory systems/processes contribute independently to memory. MPT parameters are: Ds = probability of remembering source, Di = probability of remembering item, Gs = probability of guessing item's source as S1, Gi = probability of guessing an item was studied, Db = probability of retrieving information about source and item, Dn = probability of concluding that an unstudied item is new. Response outcomes are labelled by: Src = Source, Cor = Correct, Inc = Incorrect, Alm = Alarm, Rej = Rejection.

Fig. 2

Full Item-Source MPT model from Fig. 1A with separate trees for each source. Panel A shows the Item-Source MPT for Paradigm 1, while Panel B shows the Item-Source MPT for Paradigm 2, which contained additional confidence data. S1 = Source 1, S2 = Source 2, N = New. The response category “S1—S2” means an item studied in Source 1 was judged (incorrectly) as studied in Source 2. Ds = probability of remembering source (assumed to be equal for both sources), Di = probability of remembering item, Gs = probability of guessing item's source as S1, Gi = probability of guessing an item was studied, Dn = probability of concluding that an unstudied item is new, Dh = probability of veridical recollection, Df = probability of false recollection, Dm = probability of missed encoding, Src = Source, Cor = Correct, Inc = Incorrect, Conf = Confidence, Alm = Alarm, Rej = Rejection.

Fig. 3

Full Source-Item MPT model from Fig. 1B with separate trees for each source. Panel A shows the Source-Item MPT for Paradigm 1, while Panel B shows the Source-Item MPT for Paradigm 2, which contained additional confidence data. S1 = Source 1, S2 = Source 2, N = New. The response category “S1—S2” means an item studied in Source 1 was judged (incorrectly) as studied in Source 2. Ds = probability of remembering source (assumed to be equal for both sources), Di = probability of remembering item, Gs = probability of guessing item's source as S1, Gi = probability of guessing an item was studied, Dn = probability of concluding that an unstudied item is new, Dh = probability of veridical recollection, Df = probability of false recollection, Dm = probability of missed encoding, Src = Source, Cor = Correct, Inc = Incorrect, Conf = Confidence, Alm = Alarm, Rej = Rejection.

Fig. 4

Paradigm 1: Object-Scene Paradigm. This was a continuous source monitoring paradigm, in which an object was presented either to the left or right of the centre of a scene. Each object-scene pair repeated at lags of between 8 and 22 intervening items. For repeated presentations, objects were either on the same left/right side (“stay” condition) or switched side (“move” condition).

Fig. 5

Source and Item memory Pr values from Object-Scene Paradigm for Young, Older, and Hippocampal Lesion (HL) groups. Group differences are marked: * = significant at p < .05 two-tailed; + = significant p < .05 one-tailed for a directional hypothesis. Error bars represent two-tailed 95% confidence intervals from a pooled error term (after inverse arcsine transformation), while individual scores are provided for the HL group.

Fig. 6

Individual parameter estimates averaged per group for MPT Item-Source and Source-Item models on the Object-Scene paradigm for Young, Older, and Hippocampal Lesion (HL) groups. Note that the Gs and Gi are constrained to be identical across the two models (see Supplementary Material). See Fig. 5 legend for more details.

Fig. 7

Paradigm 2: Object Location Paradigm. This was a study-test blocked source monitoring paradigm, in which items were studied at top or bottom locations while making “yes”/”no” judgement as to whether they would fit in a shoebox. A 40 s (sec) distractor task of counting backwards occurred between study and test blocks. In test blocks, participants reported whether items were “new” or had appeared in “top” or “bottom” locations, pressing the response key twice if highly confident.

Fig. 8

Object-Location Paradigm Source and Item memory Pr values for Young, Older, and Mild Memory Problem (MMP) groups. Group differences are marked * = significant at p < .05 two-tailed; + = significant p < .05 one-tailed for directional hypothesis. Error bars represent two-tailed 95% confidence intervals (after inverse arcsine transformation), after pooling error for a specific comparison of two groups: black bars come from comparison of Young and Older groups while green bars come from comparison of Older and MMP groups.

Fig. 9

Individual parameter estimates averaged per group for MPT Item-Source and Source-Item models applied to the Object-Location paradigm for Young, Older, and Mild Memory Problems (MMP). See Fig. 8 legend for more details.