Individual differences in impulsive choice and timing in rats

Abstract

Individual differences in impulsive choice behavior have been linked to a variety of behavioral problems including substance abuse, smoking, gambling, and poor financial decision-making. Given the potential importance of individual differences in impulsive choice as a predictor of behavioral problems, the present study sought to measure the extent of individual differences in a normal sample of hooded Lister rats. Three experiments utilized variations of a delay discounting task to measure the degree of variation in impulsive choice behavior across individual rats. The individual differences accounted for 22-55% of the variance in choice behavior across the three experiments. In Experiments 2 and 3, the individual differences were still apparent when behavior was measured across multiple choice points. Large individual differences in the rate of responding, and modest individual differences in timing of responding were also observed during occasional peak trials. The individual differences in timing and rate, however, did not correlate consistently with individual differences in choice behavior. This suggests that a variety of factors may affect choice behavior, response rate, and response timing.

Keywords: choice; delay discounting; impulsive behavior; rats; timing.

Fig. 1

Mean (and individual rat) percentage of choices made to the SS lever for each of the four different groups of rats. Groups are labeled according to the SS and LL duration received during training in Experiment 1. Note that the rats within each group are different animals as this was a between-subjects design (e.g., Rat 1 in Group 5/15 is a different animal from Rat 1 in Group 5/20).

Fig. 2

Responses/min as a function of time since peak trial onset (in seconds) on SS (left column) or LL (right column) trials for individual rats in each of the four groups in Experiment 1. The vertical axes have been scaled for each panel to enhance readability of the figures and avoid compression of data associated with lower response rates.

Fig. 3

Low-high-low analysis results from the fixed-interval SS and LL peak trials in Experiment 1 for each of the four groups 5/15, 5/20, 10/30, and 15/30. Start time, middle time, end time, high-state duration, and response rate during the high state of responding as determined by a low-high-low algorithm (see Data Analysis). Each dot in the figure represents an individual rat in each group and the solid gray bars display the mean for each group.

Fig. 4

SS increment for individual rats (lines) and the group mean (bars) as a function of phase of Experiment 2: 60S-4P = 60 S LL fixed interval with a four-pellet reinforcer, 60S-2P = 60 S LL fixed interval with a two-pellet reinforcer, 60S-1P = 60 S LL fixed interval with a one-pellet reinforcer.

Fig. 5

Responses/min as a function of time since peak trial onset (in seconds) for individual rats in Experiment 2. The vertical axes have been scaled for each panel to enhance readability of the figures and avoid compression of data associated with lower response rates.

Fig. 6

Low-high-low analysis results from the fixed-interval peak trials in Experiment 2. Start time, middle time, end time, high-state duration, and response rate during the high state of responding as determined by a low-high-low algorithm (see Data Analysis). Each line in the figure is the function for an individual rat and the bars indicate the mean of the 12 rats.

Fig. 7

SS increment duration for individual rats (lines) and for the group (bars) as a function of phase in Experiment 3: 60S-1P = 60 S LL duration with a one-pellet reward, 60S-2P = 60 S LL duration with a two-pellet reward, 60S-4P = 60 S LL duration with a four-pellet reward.

Fig. 8

Responses/min as a function of time since peak trial onset (in seconds) for individual rats in Experiment 3. The vertical axes have been scaled for each panel to enhance readability of the figures and avoid compression of data associated with lower response rates.

Fig. 9

Low-high-low analysis results from the fixed-interval peak trials in Experiment 3. Start time, middle time, end time, high-state duration, and response rate during the high state of responding as determined by a low-high-low algorithm (see Data Analysis). Each line in the figure is the function for an individual rat and the bars are the means across rats.