# Search results

1. ### Share your functions & code

This wasn't really a TIL but it's also RStudio specific. But there are a few examples of some helpful snippets you could include in RStudio to make your life easier - I'm too lazy to list them out so check out the blog posting https://jozefhajnala.gitlab.io/r/r906-rstudio-snippets/
2. ### Granular p-values

What context are you seeing this be discussed
3. ### 'relative difference' as dependent variable

What does the originally data look like? Do you have access to the original data?
4. ### Approximate 95% confidence interval- Practice exam question

I think C would be the typical answer if not for the word "approximate". That alone makes me think they want them to use 2 instead of the slightly more exact 1.96 when constructing the interval and in using 2 that does lead to (D).
5. ### Skewness coefficients

I don't understand - if you're fitting with a normal distribution then there isn't any skew being modeled.

Not quite. What are you using for the distribution of the sum

Do you know how to find the distribution of the sum of normally distributed random variables

Hint: start by using the info provided to figure out the standard deviation for one link
9. ### Summing number of "successes" over multiple related binary variables for a patient

For ten variables? Probably just easiest to treat each one on a case by case basis
10. ### Can you help me with this question

I'm not so sure about that. But that's partially because the original post is hard to follow. From the description it seems like multinomial might be more appropriate?
11. ### Is the mean of a kernel density estimator a valid estimator of the population mean?

Is the kernel symmetric and identical (other than location) for all points?

I think you're extremely misinterpreting what the correlation coefficient tells you
13. ### Can I use a Poisson distribution for non-normal binomial data?

I think you're confused on the rules of thumb. The binomial can be used in any case where it's appropriate. The normal approximation is typically assumed to be 'good enough' if p*n > 5 and (1-p)*n > 5. That is what you were checking so the normal distribution approximation to the binomial...
14. ### GIS

Yeah that's easy to do. Mapping actual addresses is a bit more challenging though
15. ### How to find the statistical significance between percentages in two different samples

Chi-square test of Independence
16. ### GIS

How many addresses do you need to do this for
17. ### Paired Samples t test

Do you have the number of sentences looked at for each child
18. ### Heterodastic thread on heteroskedasticity

I didn't look too much into it but if your data is arranged such that observations in the same group are in consecutive rows then serial correlation being detected makes sense since consecutive rows share a common random effect.
19. ### Finding Standard Deviation in a binomial distribution : Help Please

If you can calculate the expected value can you figure out the success probability (p)?
20. ### Results interpretation 3 or more dummy variable

If you're only getting a single coefficient for your variables then you're doing it wrong