Replication of Study 1 by Yeshurun & Levy (2003). Transient spatial attention degrades temporal resolution. Psychological Science

Author

Irmak Ergin (irmak.ergin@stanford.edu)

Published

October 25, 2023

Introduction

Justification: My research program focuses on speech comprehension, in which considering temporal factors is essential. I am planning to work with degraded/noisy speech signals, adn one way to introduce noise is by adding multiple sound sources positioned in various locations. Considering this, learning more about spatial attention, as well as temporal attention, might provide me with useful insights. I was working on attention and auditory object recognition during my master’s, and paradigms in the field were heavily influenced by the literature on visual object recognition. Therefore, I hope to find inspiration through this rescue project.

Required Stimuli & Procedures:“Two flashes of light were presented successively to the same location, and we determined the minimal interval between the flashes at which they were still perceived as two separate flashes, rather than as a single continuous flash. The shorter this critical interval is, the higher the temporal resolution. This measurement of temporal resolution was combined with a direct manipulation of transient spatial attention. In half the trials, the cued trials, a peripheral cue indicated the target’s onset and location. This exogenous cue, a small horizontal bar, allowed observers to focus their attention, in advance, on the target location, and was assumed to capture attention in a stimulus-driven, automatic manner. In the rest of the trials, the neutral trials, two long horizontal lines indicated the target’s onset but not its location (i.e., the target was equally likely to appear at any location).” (Yeshurun & Levy, 2003, p.226)

Link to Repo: https://github.com/psych251/yeshurun2003_rescue/tree/main Link to RPubs: https://rpubs.com/irmak_ergin/1102430 Link to Original Paper: https://github.com/psych251/yeshurun2003_rescue/blob/main/original_paper/Yeshurun%20%26%20Levy(2003).pdf

Summary of prior replication attempt

General summary of the prior replication attempt/original experient: As in the original study, each observer’s threshold of temporal resolution were measured in two different conditions (cued and neutral). In cued trials, a periphery cue were presented before the target onset, which indicates the target’s location. While in neutral trials, neutral cue with no indication of the target’s location were presented. The results from the original study was not replicated: * No main effect of cueing was observed in the prior replication attempt,unlike the original study. * The original study reported no interaction effect between cueing and ISI. Whereas, the first replication study found a significant interaction effect between cueing and ISI: In longer ISI conditions, spatial attention enhanced performance in the temporal resolution task, while in shorter ISI, spatial attention degraded the performance.

The original study had 18 participants while the 1st replication study had 10. The author of the 1st replication report notes that this was due to not being able to reach out to enough Psych1 students as they were collecting data in-person.This might be the reason behind not being able to replicate the original study. I aim to conduct the experiment online to be able to have the desired sample rate.

The original study did not report any exclusion from the sample. The 1st replication report states that no participant’s data was excluded from the study.

The original experiment and the 1st replication study have the same analysis methods.

Methods

Power Analysis

The effect size is not reported in the original paper.The first replication study had 10 participants although it aimed to have 18 as in the original study. Therefore, I aim to get 18 participants following the number of participant reported in the original paper and see if I can replicate the findings.

Planned Sample

There will be no pre-selection rules except for normal or corrected-to-normal vision. I will recruit data from 18 participants.

Materials

Two-flash fusion threshold: Measure of temporal resolution. “Two flashes of light were presented successively to the same location, and we determined the minimal interval between the flashes at which they were still perceived as two separate flashes, rather than as a single continuous flash. The shorter this critical interval is, the higher the temporal resolution (e.g., Artieda, Pastor, Lacruz, & Obeso, 1992;Reeves, 1996).”

Target: The target (37-cd/m2 disk with a diameter of 3 degrees) was composed of two flashes of light separated by a brief interval or a single continuous flash. “It appeared on a black background at one of 11 possible locations along the horizontal meridian, with eccentricity (distance from the center) ranging from 0 to 16.5 degrees. The cue in the cued trials was a 1 X 0.3 degrees green horizontal bar (43 cd/m2) appearing 0.5 degree above the target’s location. In the neutral trials, two 17 x 0.3 degree green horizontal lines appeared above and below the entire display.”

(taken from the original paper & the first replication attempt report)

Procedure

I am planning to follow the exact procedure of the original study, used by the 1st replication attempt as well. Quoting from the original article:

“Each trial began with a fixation point followed by the attentional cue. The cue was present until the target’s offset, to prevent confusion between the flickering of the cue and that of the target. The target was presented 94 ms after onset of the cue: On 50% of the trials, two disks appeared, each for 47 ms, separated by a variable interval (inter stimulus interval, ISI, of 11–34 ms). On the rest of the trials, a single disk was presented for a duration ranging from 105 to 130 ms. These brief durations ensured that eye movements could not occur between cue onset and target offset (Mayfrank, Kimmig, & Fischer,1987). Each observer viewed 864 trials presented in a randomized order. Both accuracy and reaction time (RT) were recorded.”

Fig.1. adapted from the original paper by the author of the 1st replication attempt, Insub Kim Link to experiment code: https://github.com/psych251/yeshurun2003_rescue/blob/main/data/spaital_temporal.m

Controls

What attention checks, positive or negative controls, or other quality control measures are you adding so that a (positive or negative) result will be more interpretable?

Analysis Plan

The original study do not mention any participant or data exclusion. Participants were required to have normal or corrected to normal vision.

“Dependent Variables:

  • Accuracy(d’) was calculated following equation: d’ = z(hit) - z(false alarm), (Macmillan & Creelman, 1991).
  • Criterion(c, measure of response bias) was calculated using: c = -0.5(z(hit) + z(false alarm)), (Macmillan & Creelman, 1991).
  • Reaction Time (RT)“*

Clarify key analysis of interest here

“- Differences between cued and neutral trials - The effect of inter-stimulus interval (ISI)”*

*Quoted sections are taken from the 1st replication report.

Differences from Original Study and 1st replication

The only difference I can see is that the first replication study had 10 participants although it aimed to have 18 as in the original study. This was dues to collecting data in-person and not being able to find enough participants in time.

Methods Addendum (Post Data Collection)

You can comment this section out prior to final report with data collection.

Actual Sample

Sample size, demographics, data exclusions based on rules spelled out in analysis plan

Differences from pre-data collection methods plan

Any differences from what was described as the original plan, or “none”.

Results

Data preparation

Link to plot A data: https://github.com/psych251/yeshurun2003_rescue/tree/main/data/_DATA/behavior/pilot_A

Link to data organization code (to be able to take transfer the data from MATLAB to R): https://github.com/psych251/yeshurun2003_rescue/blob/main/data/Mat2R.m

Data preparation plan: - Load the data - Cued and neural trials will be determined. (changing varible names to more “intuitive” ones) - Compute accuracy (d prime) value based on the equation satated in the analysis plan section. - Calculate the mean d primes per subgroups for analysis and plotting. E.g. for cuing conditions (cued vs neural), eccentricity x cue, ISI x cue, eccentricity x ISI.

The data preparationcode below has taken from the first replication report with minor changes.

####Load Relevant Libraries and Functions

library(tidyverse)
── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.3     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ ggplot2   3.4.4     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.0
✔ purrr     1.0.2     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(ggplot2)
library(ggthemes)
library(psycho)
library(ggpubr)
library(gridExtra)

Attaching package: 'gridExtra'

The following object is masked from 'package:dplyr':

    combine
library(cowplot)

Attaching package: 'cowplot'

The following object is masked from 'package:ggpubr':

    get_legend

The following object is masked from 'package:ggthemes':

    theme_map

The following object is masked from 'package:lubridate':

    stamp
####Import data

d <- read_csv("Pilot_A.csv")
Rows: 648 Columns: 9
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (2): sub, SDT
dbl (7): cue, numFlash, targetLoc, ISI, response, RT, accuracy

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#### Prepare data for analysis - create columns and change variable names
d$cue <- ifelse(d$cue == 1, 'cued', 'neutral')

#d[d$cue == 1, "cue"] <- 'cued'
#d[d$cue == 0, "cue"] <- 'neutral'

x=1:length(unique(d$sub))
new_subNames=sprintf("s0%02d",x)
subNames = unique(d$sub)
for(i in 1:length(subNames)) {
  d$sub[d$sub == subNames[i]] = new_subNames[i]
}


kk = sort(unique(d$targetLoc))
mask1=d$targetLoc ==kk[1]
mask2=d$targetLoc ==kk[2]
mask3=d$targetLoc ==kk[3]
mask4=d$targetLoc ==kk[4]
mask5=d$targetLoc ==kk[5]
mask6=d$targetLoc ==kk[6]

d$targetLoc[mask1] = 0
d$targetLoc[mask2] = 3
d$targetLoc[mask3] = 6
d$targetLoc[mask4] = 9
d$targetLoc[mask5] = 13
d$targetLoc[mask6] = 16


d <- d %>% mutate( 
  cue = factor(cue),targetLoc = factor(targetLoc), ISI = factor(ISI)
)

#### Compute dPrime

dp <- d %>% group_by(sub,cue,targetLoc,ISI) %>% summarize(nHit = sum(SDT == 'HI' ), nFA = sum(SDT == 'FA' ), nMiss = sum(SDT == 'MI' ), nCR = sum(SDT == 'CR' ), dPrime= dprime(nHit, nFA, nMiss, nCR)$dprime, criterion=dprime(nHit, nFA, nMiss, nCR)$c) 
`summarise()` has grouped output by 'sub', 'cue', 'targetLoc'. You can override
using the `.groups` argument.
#### Make sub-selection of the data for plotting 

dplot_cue <- dp %>% group_by(sub,cue) %>% summarize(dPrime = mean(dPrime))
`summarise()` has grouped output by 'sub'. You can override using the `.groups`
argument.
dplot_ecc <- dp %>% group_by(cue,targetLoc) %>% summarize(dPrime = mean(dPrime))
`summarise()` has grouped output by 'cue'. You can override using the `.groups`
argument.
dplot_ecc2 <- dp %>% group_by(targetLoc,ISI) %>% summarize(dPrime = mean(dPrime))
`summarise()` has grouped output by 'targetLoc'. You can override using the
`.groups` argument.
dplot_ISI <- dp %>% group_by(cue,ISI) %>% summarize(dPrime = mean(dPrime))
`summarise()` has grouped output by 'cue'. You can override using the `.groups`
argument.
dplot_stat_ISI <- dp %>% group_by(sub,cue,ISI) %>% summarize(dPrime = mean(dPrime))
`summarise()` has grouped output by 'sub', 'cue'. You can override using the
`.groups` argument.
dplot_ecc_sd <- dp %>% group_by(sub,targetLoc,ISI) %>% summarize(dPrime = mean(dPrime))
`summarise()` has grouped output by 'sub', 'targetLoc'. You can override using
the `.groups` argument.
dplot_ecc_sd
# A tibble: 54 × 4
# Groups:   sub, targetLoc [18]
   sub   targetLoc ISI   dPrime
   <chr> <fct>     <fct>  <dbl>
 1 s001  0         11     0    
 2 s001  0         23     0    
 3 s001  0         35     0.416
 4 s001  3         11     0    
 5 s001  3         23     0    
 6 s001  3         35     0    
 7 s001  6         11     0    
 8 s001  6         23     0    
 9 s001  6         35     0    
10 s001  9         11     0    
# ℹ 44 more rows

Results of control measures

There are no control measures planned for this study.

Confirmatory analysis

Following the original paper, and as it was done in the 1st replication attempt, a within-subject three-way analysis of variance (ANOVA; Cuing x Eccentricity x ISI) will be performed on the accuracy (d’) and RT data collected on trials with correct responses.

The key statistic of 3 way ANOVA anova was performed. The code below is taken by the first replicatio report.

# The key statistic: within-subject 3-way Anova
Result <- aov(dPrime ~ (cue*targetLoc*ISI) + Error(sub/cue*targetLoc*ISI), data=dp)

# main effect: Cuing
summary(Result[5])

Error: sub:cue
          Df Sum Sq Mean Sq F value Pr(>F)
cue        1 0.0940  0.0940   0.192  0.704
Residuals  2 0.9802  0.4901               
# interaction effect: Cuing X ISI
summary(Result[10])

Error: sub:cue:ISI
          Df Sum Sq Mean Sq F value Pr(>F)
cue:ISI    2 0.2402  0.1201   0.715  0.543
Residuals  4 0.6720  0.1680               

Three-panel graph with original, 1st replication, and your replication is ideal here

Exploratory analyses

Any follow-up analyses desired (not required).

Discussion

Mini meta analysis

Combining across the original paper, 1st replication, and 2nd replication, what is the aggregate effect size?

Summary of Replication Attempt

Open the discussion section with a paragraph summarizing the primary result from the confirmatory analysis and the assessment of whether it replicated, partially replicated, or failed to replicate the original result.

Commentary

Add open-ended commentary (if any) reflecting (a) insights from follow-up exploratory analysis, (b) assessment of the meaning of the replication (or not) - e.g., for a failure to replicate, are the differences between original and present study ones that definitely, plausibly, or are unlikely to have been moderators of the result, and (c) discussion of any objections or challenges raised by the current and original authors about the replication attempt. None of these need to be long.