Hypothesis Tests in Stata

How to implement a hypothesis test on the mean of a variable manually and using the test command.

[rgportocarero]

Dear Sebastian,

Thank you once again for the informative video. I am studying the evolution of firms scores from 2009 until 2020. For the purpose of this study, I will be using oneway and the post-hoc Tukey test to test for significant score increases from one year to another. E.g from 2009 to 2010, 2011 to 2012 etc. However, if I would like to use the Tukey test, I first need to use the Levene's test to make sure the variance of the scores over the years are equal to each other.

My dataset:
Company Year Score
X 2009 70
...
X 2020 80
Y 2009 60
...
X 2020 65

I am looking at the statistical significance in score increases over the years of the aggregate sample (e.g mean of 2009 scores to 2010 over all companies).

My question: I need to perform a Levene's test of equal means (sdt test (mean) 2009 == sdtest (mean) 2010) over the covered years to test for equal variance difference. Therefore, I will probably need to perform a test of each year against one another.
I was wondering how to tackle this problem so that when I perform the test is still takes the mean of each year. (I cannot first collapse towards mean value because it removes the variance of the individual observations)

Much appreciated Sebastian!!

[amratz]

Hi, I'm trying to perform a t-test where the null hypothesis is that one coefficient equals to 2 times the other one. I regressed and generated two new variables where z1 =_b[x1] and z2 = 2*_b[x2]. I then tried to perform a ttest with ttest z1==z2, the code did work but somehow the null hypothesis shows that mean(diff)=0 and no t values were shown. SE and SD are also shown to be 0. I'm not sure what went wrong and would appreciate some help.
Thanks!!

[mohammadhasibemran]

Dear Sebastian.

Does STATA report a two-tailed Prob>F value in the "Goodness of Fit" table after a multiple linear regression? Or is it one-tailed? And, should all F-tests (especially for model validity test) be right-tailed?

With regards,
Hasib

[afzinno.]

What significance level was this done at by any chance ?

[cartilo]

Where can I get the dataset used in the video?

[Dr_Shiny]

@2: 39, How did you get that null hypothesis value? as the mean is 30552.11, but you use 35000 as the null hypothesis value, why? please explain.