Goodness-of-fit example
Three Point Process Datasets
Time (sec)
Dataset 1:
Dataset 2:
Dataset 3:
Poisson Likelihood
0 5 10 15 20 25 30 35 40 45 50
0
2
4
6
8
10
12
14
x 1023
Lambda (Hz)
L
ik
el
ih
oo
d
( )
Spike Train Data
Time (sec)
Dataset 1:
Dataset 2:
Dataset 3:
Waiting Time Data
0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16 0.18 0.2
0
0.5
1
0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16 0.18 0.2
0
10
20
0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16 0.18 0.2
0
0.5
1
Time (sec)
Dataset 1:
Dataset 2:
Dataset 3:
Waiting Time Histograms
Dataset 1: Dataset 2: Dataset 3:
Waiting Time (sec) Waiting Time (sec) Waiting Time (sec)
C
ou
nt
s
0.04
Empirical Distributions
0 0.05 0.1 0.15 0.2 0.25
0
0.2
0.4
0.6
0.8
1
0 0.05 0.1 0.15 0.2 0.25
0
0.2
0.4
0.6
0.8
1
0 0.05 0.1 0.15 0.2 0.25
0
0.2
0.4
0.6
0.8
1
Waiting Time (sec)
KS Plots
Empirical CDF Empirical CDF Empirical CDF
M
od
el
C
D
F
Dataset 1: Dataset 2: Dataset 3:
KS Plots
Empirical CDF Empirical CDF Empirical CDF
M
od
el
C
D
F
Dataset 1: Dataset 2: Dataset 3:
KS Stat = 0.126 KS Stat = 0.632 KS Stat = 0.312
QQ Plots
Empirical Quantiles Empirical Quantiles Empirical Quantiles
M
od
el
Q
ua
nt
ile
s
Dataset 1: Dataset 2: Dataset 3:
Waiting Time Autocorrelation Functions
Dataset 1: Dataset 2: Dataset 3:
Lag Lag Lag
Fano Factor (1 msec bins)
Time (sec)
FF1,FF2,FF3
Fano Factor (40 msec bins)
FF1FF2 FF3
Time (sec)
Summary
Hist KS QQ Fano Factor ACF
Dataset 1 P P P P P
Dataset 2 X X
All
Quantiles
0.04
X X
Dataset 3 P X
Off by
Factor of
2
P P
Spike Train Data
Time (sec)
Dataset 1:
Dataset 2:
Dataset 3: