Nayef
  • Member for 7 years, 2 months
  • Last seen this week
2 answers
0 votes
20 views
When doing LASSO, do I need to leave a level out for a categorical variable?
1 votes

When using LASSO, you do not need to drop one level from your categorical variable. The practice of dropping a level is known as dummy coding. Here are a couple of references that say that dummy ...

View answer
1 answers
0 votes
35 views
OLS Regression equation
Accepted answer
0 votes

I'm not sure why you would start with the assumption that b doesn't exist. Regardless of whether or not the relationship between Y and the X variables is linear, it is usually possible to find a value ...

View answer
1 answers
0 votes
41 views
How best to deal with missing event data
1 votes

As @whuber mentioned, this is censored data. The lifelines python library is a very good one for survival analysis. It has excellent documentation that is a good place to start learning about the ...

View answer
2 answers
1 votes
1k views
selection of Kruskal-Wallis test for two groups
0 votes

This is not directly related to the specific test used, but it's worth being aware of the problem of "double dipping", and if necessary correcting for it. In this case you are double dipping ...

View answer
2 answers
3 votes
123 views
Regression not significant on univariate but significant when adding controls
Accepted answer
5 votes

To answer the question, no I don't think this means you are doing something wrong. In fact, I think this is a good demonstration of why it's useful to fit many regression models when exploring data. ...

View answer
2 answers
3 votes
84 views
Mathematical connection between hazard functions for e.g. Cox models and expected values in GLMs
0 votes

Just to clarify, can we rephrase the question as follows: "Why is the conditional hazard used as the response in the Cox model?" In which case, I would say that the answer is that this is an ...

View answer
1 answers
0 votes
26 views
What is the data type of speed limit of a road network segment?
1 votes

Speed limit could be treated as either continuous or categorical. It depends on the purpose of the model, and your expectations of how it will be applied. Let's say all the road segments in your data ...

View answer
1 answers
1 votes
50 views
Slicing series with t-test
1 votes

I think there might be some other issues related to the interpretation of these sequential test results, but one small suggestion is that you could use the Bonferroni correction to reduce the number ...

View answer
1 answers
2 votes
39 views
Check if real data follows the memoryless property
1 votes

The only continuous distribution that is memoryless is the exponential distribution. Similarly, the only discrete distribution that is memoryless is the geometric distribution. If you plot your data ...

View answer
2 answers
1 votes
154 views
In the experiment of drawing balls from bag. Does 3 in $X_i \sim \mathit{Binomial}(3, \theta)$ mean there are 3 balls in the bag?
0 votes

The parameters of the binomial distribution are n, the number of independent trials and p, the probability of success on each trial. So here, the three in the second experiment means that three balls ...

View answer
2 answers
3 votes
141 views
Does the t-test require randomization?
0 votes

Here are a couple of papers that suggest that hypothesis tests and p-values are not entirely appropriate without randomization. I've included excerpts from the abstracts of each one as well. Can p-...

View answer
6 answers
37 votes
122k views
Assumptions of linear models and what to do if the residuals are not normally distributed
3 votes

The most accessible exploration of the impact of non-normal errors that I have found is this paper by Schmidt and Finan. Here is the summary of the results in the abstract: Although outcome ...

View answer
1 answers
1 votes
34 views
p value for monthly trend
Accepted answer
2 votes

You could use time series regression, and test whether the slope/trend has a significant coefficient after accounting for months. This page might be a good place for more details.

View answer
1 answers
1 votes
40 views
Survival Analysis to Forecast Attrition
0 votes

I think this chapter could be quite helpful to you: http://peopleanalytics-regression-book.org/survival.html. It focuses specifically on HR-related analyses, which should translate to what you are ...

View answer
1 answers
1 votes
23 views
divide txt data into two sets according to text vocab distribution
0 votes

Let X be the original list. If I understand correctly, you want to split X into X1 and X2, which have the same word frequency distributions. You can first get the word frequency distribution of X. ...

View answer
2 answers
2 votes
18 views
meaningful difference at a particular point of two cumulative distribution functions
1 votes

It sounds like you're looking for a quantile test. A quick search led to this: https://www.jstor.org/stable/2673594?seq=1 I'm sure there are other tests in this category. In your case, the null ...

View answer
1 answers
1 votes
125 views
Normality assumption for t/z tests
0 votes

This post may be helpful: https://www.johndcook.com/blog/2018/05/11/two-sample-t-test/ It shows that when you sample from populations that are non-normal, but symmetric and with tails that aren't too ...

View answer
2 answers
2 votes
18k views
Sample Size proportion per control vs. experiment group
1 votes

This post gives the results of simulations for several combinations of sample size, effect size and proportion of the sample that is assigned to the control group: https://www.markhw.com/blog/control-...

View answer
2 answers
20 votes
46k views
Plotting confidence intervals for the predicted probabilities from a logistic regression
3 votes

Here's a modification of @smillig's solution. I use tidyverse tools here, and also use the linkinv function that is a part of the GLM model object mod1. That way, you don't have to manually invert the ...

View answer