10,050 reputation
11125
bio website
location
age 50
visits member for 3 years, 2 months
seen 4 hours ago

1d
comment Regresssion of Accurate Data
Is there a non-linearity issue here? If your measurements are accurate but the device produces non-linear effects then linear regression will certainly make inaccurate predictions.
Apr
13
comment Posterior Density in R
Your prior density is for what parameter(s)? Perhaps the mean where you know the variance?
Mar
30
comment Estimating the number of streets in $CITY?
Look at the index of a city streetmap
Mar
30
comment Can unimodal prior and unimodal sampling distributions lead to a multimodal posterior distribution?
Heavy tails in the distribution make non-unimodality more likely
Mar
30
comment Can unimodal prior and unimodal sampling distributions lead to a multimodal posterior distribution?
@Tim: "Can a unimodal multivariate distribution has some multimodal marginal distribution?" is a different question and should probably be asked separately.
Mar
30
comment Can unimodal prior and unimodal sampling distributions lead to a multimodal posterior distribution?
$\frac{x\pm\sqrt{x^2-4}}{2}$ has a $\pm$ and so gives two maxima
Mar
30
comment Can unimodal prior and unimodal sampling distributions lead to a multimodal posterior distribution?
@Tim: do you think my example meets the conditions in your comment?
Mar
27
comment Basic R script/package with lots of automated calculations
@Manuel: your $\alpha_n$ and $\beta_n$ are $n$-th moments, about zero and centred about the mean respectively
Mar
18
comment Sampling from an arbitrary distribution with unknown CDF
What is the expression for the probability density?
Mar
15
comment Error of data fitting by gamma.fit() in Python
What would happen if you tried param = gamma.fit(float(samp)) ?
Mar
15
comment How to compute Prior Variance
If these are votes in an election, than "Swing" usually means change since the previous election rather than actual votes.
Mar
15
comment Linear regression: Evaluate probability of $Y>y| X=x$
I doubt linear regression would work then without some adjustments to justify a linear model and perhaps deal with any autocorrelation.
Mar
15
comment Linear regression: Evaluate probability of $Y>y| X=x$
Yes: if the model is $y_i= x_i \beta+ \varepsilon_i$ with the $\varepsilon_i$ normally distributed with mean zero and a constant variance, then what you have done looks reaonable, though of course the numbers are overprecise. plot(Sepal.Length~Petal.Length, data=iris); abline(h=5) gives you a view of the information you actually have.
Mar
14
comment Bayesian inference with the wrong distribution
Related but not the same as math.stackexchange.com/questions/712040/…
Mar
14
comment How to write this cost equation?
So you are saying that "preventive maintenance" both costs money and reduces the expected time to the next failure? What is it preventing?
Mar
14
comment About normal distribution, solve function issue
You might start by finding $d_1$ for which $P ( 20-d_1 \lt X ) = 0.998$ and then consider how to adjust it
Mar
13
comment Relation between mean of the hypergeometric distribution and binomial
You have the same expectation for a binomial distribution with parameters $n$ and $p=\frac{K}{N}$. What happens when $N$ increases while $n$ and $K$ do not?
Mar
4
comment Regression with “unidirectional” noise
Do you know the form of $f(x)$? Can $\epsilon$ get close to $0$?
Mar
2
comment Can univariate linear regression be used to identify useful variables for a subsequent multiple logistic regression?
Normalising the data should not change $r^2$
Feb
26
comment Why is a symmetric distribution sufficient for the sample mean and variance to be uncorrelated?
No - just what you have said in the question