38 Questions 5K Answers 0 Followers
Questions related from Jochen Wilhelm
Consider data that is taken from a one-parametric distribution (e.g. Poisson) that can be parametrized by its mean (µ). The task is to get the 95% confidence interval (CI) or the estimate of...
09 September 2019 7,500 12 View
It's a weighted least-squares polynomial regression, so it's based on assuming normal errors, and the normal probability model is parametric. However, in some statistics book and online statistics...
10 October 2018 8,832 9 View
When calling x[1]
12 December 2016 1,600 6 View
I have two models to predict "Survival" (S in (0;1)) from a "Dose" (D, D≥0): a 2-parameter Weibull model:S(D) = exp( -exp(a*logD-b) ) and a so-called "multi-target model":S(D) = 1 - ( 1-exp(-D/t)...
01 January 2016 4,110 8 View
Consider following case: There are k different groups, but only the mean difference between 2 of these groups should be tested (t-test, consider the assumptions are met and alpha and beta are...
10 October 2015 5,890 12 View
From a frequentist's prespective, "probability" is the limiting relative frequency (of an event). In this philosophy, only results of repeatable processes can have probabilities. Observed data is...
01 January 2015 1,120 41 View
Short history: As I understood can the normalized (profile) likelihood be used to get the CI of an estimate. "Normalized" means that the function will have a unit integral. This works beautifully...
12 December 2014 6,929 5 View
Frequentists, as far as I understood, define probability as a limiting relative frequency. And they say that frequencies can only be defined for data (not for hypotheses), so probabilities can...
10 October 2014 7,952 15 View
The result of a Bernoulli trial is a variable with 2 possible outcomes. The respective probability distribution is calles the "Bernoulli distribution". Considering an experiment which result is a...
09 September 2014 430 39 View
I attached an example of what I mean. This plot was generated manually. The algorithm should determine which points can be labelled (where is enough space to add a label; this will be typically...
09 September 2014 2,322 7 View
I am looking for a way to select (and specifically redraw) one plot on a graphics device that is subdivided with layout(...). I know that this yould be possible after par(mfcol=...) with...
08 August 2014 2,514 4 View
I'd like to have or write a function that automatically provides "adjusted predictions" for a linear model. For simplicity I could accept that the models must not have any interactions. With...
07 July 2014 7,542 4 View
Is there a way at all?
06 June 2014 3,492 6 View
Is there a way to get the event when the user turns the mouse wheel over the active graphics device in Windows? Following the linked post it seems impossible using getGraphicsEvent, but I wonder...
06 June 2014 2,248 1 View
The function identify() allows to click on points in a scatterplot to add labels. R can automatically determine the "position" next to the point where the label should occur. Also, the distance of...
05 May 2014 2,941 2 View
I have the formula Y = (A-B)/m where A and B are averages from samples with sizes nA and nB, and m is a "slope" determined from a linear regression from q points. There are standard errors given...
04 April 2014 399 12 View
A parameter of a statistical model should be estimated from iid data. For simplicity, let's consider a single-parameter model. The likelihood principle sais that the best estimate for the...
03 March 2014 7,552 58 View
I have a table in Excel. Some cells contain texts with greek letters like "MIP-1β" (the last beta has is unicode 03B2). I often copy these tables to the clipboard and read them in R with...
02 February 2014 8,676 17 View
I want to plot data for a two-factorial experiment in a simple boxplot. The attached diagram shows an example. The grouping structure of the second factor should be indicated by horizontal lines...
02 February 2014 6,235 9 View
This question is not of any particular practical relevance, but it may help me to clarify a philosophical issue. A confidence interval (CI) as being a frequentit's tool for "inference" is...
02 February 2014 2,073 12 View
Let's consider the (standard) 2-sample t-test for a difference in means. The t-value is calculated from empirical difference in sample means divided by the SE of this difference (in turn derived...
02 February 2014 1,056 59 View
I used R and the function polr (MASS) to perform an ordered logistic regression. The model is simple: there is only one dichotomous predictor (levels "normal" and "modified"). The question was if...
01 January 2014 2,230 15 View
I knew a paper reporting that a high proportion of (anticancer) drugs did not prove effective in replicated studies. As I recall there were about 53 drugs tested and more than 40 turned out not to...
10 October 2013 640 3 View
If the means of several (2+) groups/samples are compared, many people perform an ANOVA to test (and hopefully reject) the H0 that all samples come from populations with the same means. Then it...
09 September 2013 5,376 13 View
How to get all Pathway annotations for the Agilent Probes (human, mouse, rat)? In Bioconductor there were are some packages availabe like mgug4122a.db, hgug4112a.db and rgug4131a, but they only...
05 May 2013 7,888 4 View
I have a linear model with several predictors (only main effects). One of them is a catagorical variable X with 4 levels (A...D). One level (A) is used as the reference level, so the model gives...
04 April 2013 4,460 4 View
I tried to find out why the deviance in GLMs is defined as -2*log(LR) (with LR being the likelihood ratio). Why the factor -2? Often, authors state that this way the deviance for a normal model...
04 April 2013 2,086 3 View
I am a noob in AUC analyses and would like to get some help with a probably quite stupid problem: Consider a population of cells, splitted to 5 plates. Each plate is treated with a different...
02 February 2013 1,366 2 View
Background: From a binomial experiment (k successes in n trials), the proportion of successes in the "population" is estimated by p = k/n. This estimate has a standard error of SE =...
02 February 2013 598 10 View
Consider a list with two items, "table" and "data". "table" is a (n x m) data.frame, "data" is a (r x n) matrix. The matrix has as many columns as there are rows in data.frame. I want to select...
12 December 2012 4,462 9 View
I am not familiar with the grid package. I usually use "plot" (graphics) to show data and set the arguments xlim and ylim to define the visible parts of the x- and y-axes. I would like to this for...
11 November 2012 1,214 8 View
This is still my old problem... Obviously, the likelihood and the "sampling distribution" are related. The shape of the likelihood converges against the shape of a normal distribution with mean =...
11 November 2012 554 2 View
I just came across the finding that the densities of chi² (n*x/s²; n+2) and scaled chi⁻²(x; n; s²) are similar up to a normalizing constant. I would like to see this "analytically" but I...
10 October 2012 4,931 9 View
In many texts I find the statement that the likelihood is a normal-Gamma, e.g. here: http://www.cs.ubc.ca/~murphyk/Papers/bayesGauss.pdf (3.1, 3.2). I never found anything explaining HOW this is...
10 October 2012 5,954 44 View
I know that Euler solved this somehow for a=1 and came to the value of e. I also found a series expansion that Euler developed. However, is there someone who could explain the derivation ending up...
09 September 2012 1,208 3 View
Does anyone know sources/references with derivations of the normal distribution, at best ones with explanations that can be understood by people without mathematical background? I am aware of the...
09 September 2012 4,621 3 View
There is a couple of error models (probability distributions) where I do understand the derivation in terms of going from simple processes where you have limited knowledge (uncertainty) to the...
09 September 2012 6,330 11 View
I am looking for an example to determine the coefficients of a GLM by maximizing the (log)likelihood, preferrably using R. The optimization (search algorithm) is not the problem; this can be done...
09 September 2012 921 7 View
