# Non-independence of trial likelihoods in a staircase procedure?

In psychometrics,
we often want to know, for instance,
a given participants’ perceptual threshold:
the intensity of a stimulus that they can detect 50% of the time.

It’s common to use staircase procedure,
where we adjust the stimulus according to the participant’s previous response,
making it more intense if they failed to detect it on the previous trial,
and less intense if they successfully detected it.
This produces a staircase like the one pictured below,
which converges on an intensity that can be detected 50% of the time.

We might then fit a logistic (or probit) regression model
$$P(y_i = 1) = text{logit}^{-1}(alpha + beta x_i)$$,
where $$y_i=1$$ if the stimulus was detected on trial $$i$$
and $$x_i$$ is the stimulus intensity on that trial,
to refine and obtain confidence intervals for our estimate of the threshold.

However, the standard GLM routines assume that each trial $$i$$ is independent,
$$log(P(Y|X, alpha, beta)) = sum_i log(P(y_i|x_i, alpha, beta))$$.

Does this assumption hold, and so are the GLM standard errors valid,
when the stimulus $$x_i$$ depends on the stimulus and response on the previous trial $$(x_{i-1}, y_{i-1})$$?

Cross Validated Asked on November 21, 2021

## Related Questions

### Does estimated standard error of the mean says something about the population mean?

1  Asked on January 21, 2021 by funkwecker

### Is the maximum entropy probability distribution only determined through comparison?

0  Asked on January 21, 2021

### Regression when $X$ is random and unobservable

0  Asked on January 20, 2021 by igor-f

### How to use a GAM to predict the probability in binomial data as a function of predictors

1  Asked on January 19, 2021 by wetlabstudent

### How to decode/understand the math behind ACF and PACF?

1  Asked on January 19, 2021 by raghavsikaria

### A/B Testing – Repeated Sampling

0  Asked on January 18, 2021 by thomas-moore

### Anomaly detection for multiple correlated variables (sensors)

0  Asked on January 18, 2021 by shawn-strasser

### Clustering with Likert items and N/A option

1  Asked on January 17, 2021 by matthias

### Case-Control Study Design for Longitudinal Analysis

0  Asked on January 17, 2021 by cat-cuddler

### Multivariate time series vs multi dimensional time series

0  Asked on January 16, 2021 by ss-varshini

### Relation between test and train error with gradient descent iterates

0  Asked on January 16, 2021 by sgg

### How to derive Bias of PCA estimator

0  Asked on January 16, 2021 by baz

### Using gradient information in minimizing error function, in Bishop’s Pattern Recognition

3  Asked on January 16, 2021 by sorcererofdm

### Mean squared error of OLS smaller than Ridge?

5  Asked on January 15, 2021 by aristide-herve

### How to deal with large combinations of factors

0  Asked on January 14, 2021 by mat

### Time series tracking queue optimization problem

1  Asked on January 14, 2021 by doxav

### Sample log geometric distribution from log probability

1  Asked on January 14, 2021

### what is the likelihood function $p(y|a,tau)$ of simple linear regression model?

1  Asked on January 14, 2021 by user261225