Community Profile # Jeff Miller

Last seen: Today Active since 2013

#### Statistics

All
• • • • • • • • • • • #### Content Feed

View by

parfor variable classification issue revisited
Maybe something like this would be helpful, using the wonderful allcomb. idx = allcomb(1:5,1:6,1:7,1:8,1:9); nrows = size(idx,...

1 month ago | 0

Create .mat file which appends a variable each time a function is executed
Maybe you can use the function 'matfile' to do what you want. Here is a little example: % This is part of the main program / s...

1 month ago | 0

| accepted

Why are pool workers going inactive while many iterations remain?
What you would like is for any free processor to take up any waiting task (me too), but for some reason that's not how it works....

2 months ago | 0

| accepted

How to generate a Frechet distribution using Methods of Moments?
Here is how you might do it if with Cupid : %% Example for the 2-parameter Frechet distribution (minimum known to be 0) % M...

2 months ago | 0

How can I calculate True positive, False positive, True negative and False negative of real and predicted dataset?
First you need to map your 3 values 1-3 onto just two categories: positive and negative. For example, you might decide to call ...

2 months ago | 0

| accepted

Linear Regression with Only Dependent Variables
It sounds like you can get what you want from simply [rho, pval] = corr(matrixA(:,1),matrixB(:,1)) fitlm is for situations wit...

3 months ago | 1

| accepted

How to use chi2gof within CUPID
Yes, that is correct. The successive bin probabilities are the differences of the successive CDF values, and the expected numbe...

3 months ago | 1

| accepted

Goodness-of-Fit for a best-fitting distribution? (by using CUPID)
There are lots of different ways to evaluate the goodness of fit of a given theoretical distribution to a dataset (see, e.g., wi...

3 months ago | 1

| accepted

Fit a statistical distribution to truncated data
If you would like to fit a variety of truncated distributions in addition to the normal, you might find Cupid helpful. For inst...

3 months ago | 2

| accepted

Fit parameter to Weibull distribution
The problem is a bad choice of starting values. You will get much better parameter estimates with params = mle(A,'pdf',customp...

4 months ago | 0

| accepted

Using Psychtoolbox KbCheck() functions, how can I test for a renewed keypress?
One approach is to check timeSecs. This will be very small if the key is continuously held down from the previous trial, but pre...

4 months ago | 0

| accepted

How can I make heatmap scale fixed?
e.g., h1 = heatmap(); h1.ColorLimits = [0 1000];

5 months ago | 0

| accepted

Simple function for obtain a T statistic from sample mean, stdev & hypothetical mean
Here you go: t_observed = (sample_mean - hypothetical_mean) / sample_sd * sqrt(n); n is the number of scores averaged to get t...

5 months ago | 0

creating standard error of mean for bar graphs in code, can you please correct/modify/help my code?
Hard to say for sure without knowing what the original data were, but that doesn't look right to me. Can you explain how the va...

5 months ago | 0

| accepted

Generating correlated data for simulation
One option is to create the second array by adding a random number to each element of the first array. For example sigma = 1; ...

5 months ago | 0

I want to create a QQ & PP plot using L-Moments to fit the GEV but get this error: unable to perform assignment b/c the left & right sides have a different number of elements
Assign the problematic result to a new variable so that you can see what elements it has, like this: temp_var = psi + alpha*(1...

6 months ago | 0

question on repeated measure GLM model
I don't fully understand the design so I won't attempt to answer questions 2) or 3), but I think this is the answer to 1): If '...

6 months ago | 0

How to run the ANCOVA test with categorical covariate in matlab?
It doesn't really make sense to run ANCOVA with a categorical covariate. Instead, think of the categorical covariate as another...

6 months ago | 0

How can I perform wilcoxon Test with paired samples and vectors of differente sizes?
The Wilcoxon test is for data that come in pairs, so the vectors must be the same size. If you are just missing one score or th...

7 months ago | 0

Getting a percentile from a histogram
Usually this is done by linear interpolation within the relevant bin. To stick with your 95th percentile example, suppose you h...

7 months ago | 0

| accepted

A problem in the usage of multidimensional scaling (cmdscale)
You can't cancel that. With only the distance information in D, the mds function has no way of knowing what is up/down/left/rig...

8 months ago | 1

| accepted

How to integrate a lognormal pdf
It's hard to say for sure without seeing your xx and xxx values, but maybe it is just your expectations that are faulty? Certai...

8 months ago | 0

Find number of factors for factor analyses
My \$0.02 worth: I would suggest running facan with nBasis=8 and checking the resulting scree plot (plot of eigenvalue as a func...

8 months ago | 0

| accepted

linear mixed-effects model (fitlme) add array variable
I'm pretty sure the predictors have to be single values, so you can't feed in an array as a single unified predictor. You could...

8 months ago | 0

Using pdf to find threshold
I'm not entirely sure what you mean by "threshold", but maybe you are trying to identify the middle 95% of the distribution? If...

8 months ago | 0

| accepted

Anova-n outputs as not full rank. Returns NaN P-value.
The short answer is that you have to collect more data to fix this. Look here: >> crosstab(gX1,gX2,gX3) ans(:,:,1) = 7 ...

9 months ago | 0

| accepted

problem with the anova calculation
Just change one line to this mdl = fitlm(tbl,'pick~C_t')

10 months ago | 0

| accepted

Can I find likelihood function of an objective function?
A lot depends on the details of these models, but one way to proceed would be in terms of the error scores. Consider the full mo...

10 months ago | 1

ANOVA result No p-value.
The problem is that the full model has 90 parameters and predicts a separate mean for each of the 3*3*10 conditions. But you onl...

10 months ago | 0

| accepted