Thread: Modern Economics

Originally Posted by Reiver

Wrong. I employ econometricians to do it for me. One needs a passing knowledge of the procedures used.


You've not actually said anything here. You certainly haven't shown the hypothesis testing methods used aren't robust. The "significance levels used" comments was particularly cretinous. We also never accept, only fail to reject (making your other comment just a post filler)

You don't employ anyone. No one here believes that you do. It's highly doubtful that you even work for a living. And you certainly have no knowledge of the theory & application of hypothesis testing other than vague acquaintance with the terminology you Googled.

Your ignorance about the relation of significance levels and information speaks volumes. The probability of a Type I error is a function of the level of significance - this conditions the power of the test and the probability of a Tye II error. Most tests in econ research papers test at the 0.05 level - which makes little to no sense in most cases given the data at a researcher's disposal. One of the first things you learn when estimating a linear regression model by least squares, is that a large sample where the explanatory variable is insensitive to changes in the information of the sample implies a large variance in the estimator. The need for quality information that can be extracted from the sample will inevitably lead one to powerful tests. As has been explained to you, these are absent from most tests of hypothesis in economics research. Instead, they rely solely on p-values. This is one the [many] reasons why I (and the majority of people who are educated on the subject) scoff at economists who speak about "results" or "conclusions" in their field.

Originally Posted by Random_Variable

You don't employ anyone.

I don't care what you believe

The probability of a Type I error is a function of the level of significance - this conditions the power of the test and the probability of a Tye II error.

This is Stats 101 (which amuses me as you're trying to use it despite saying you're well educated).

Most tests in econ research papers test at the 0.05 level - which makes little to no sense in most cases given the data at a researcher's disposal.

Wrong. 5% can be used but that depends on the journal. Some will prefer 1% etc. Ultimately it doesn't matter as, unless you're just reliant on podcasts, you'll be referring to multiple studies with different testing methodologies.

As has been explained to you, these are absent from most tests of hypothesis in economics research.

They test hypothesis. You cannot dismiss those tests. Everything you have said has been vacuous low level stuff. Put it this way: I wouldn't employ you

Originally Posted by Reiver

I don't care what you believe


This is Stats 101 (which amuses me as you're trying to use it despite saying you're well educated).


Wrong. 5% can be used but that depends on the journal. Some will prefer 1% etc. Ultimately it doesn't matter as, unless you're just reliant on podcasts, you'll be referring to multiple studies with different testing methodologies.


They test hypothesis. You cannot dismiss those tests. Everything you have said has been vacuous low level stuff. Put it this way: I wouldn't employ you

Where is the content, kiddo?

Powerful/most powerful tests are topics covered in Mathematical Statistics which is an upper level course. You focused on terms introduced in stats101 (Type I & II error) because that's all you understood. Everything I've said is accurate, and you haven't comprehended a single word because you don't have 1/100 of the prerequisite knowledge necessary. Stop crying and stomping your foot, you girl.

I dismiss their methodology.

You couldn't employ me because you are not, have not, and never will be an employer of any kind.

Originally Posted by Random_Variable

Where is the content, kiddo?

You haven't provided any, which has been predicted.

Powerful/most powerful tests are topics covered in Mathematical Statistics which is an upper level course.

You are indeed a student. I'm not sure if you're undergrad mind you as you've been too reliant on copy and paste

You focused on terms introduced in stats101 (Type I & II error) because that's all you understood.

The interesting aspect was how you got it wrong, like the cretinous comment about a null being true

You couldn't employ me

Indeed!

Originally Posted by Reiver

You haven't provided any, which has been predicted.


You are indeed a student. I'm not sure if you're undergrad mind you as you've been too reliant on copy and paste


The interesting aspect was how you got it wrong, like the cretinous comment about a null being true


Indeed!

What have I copied and pasted and from where?

The comment about the null being true? I'm assuming you're referring to the comment about the acceptance of the null? Why is this such a foreign concept to you? In powerful tests, the null can be accepted. The fact that you've oblivious to this underscores that you are only familiar with basic p-value tests where the null cannot (should not) be accepted and you can only "fail to reject it."

This deficiency in knowledge will not do. Rectify it at once.

Originally Posted by Random_Variable

What have I copied and pasted and from where?

You mean you haven't copied and pasted the bland stuff? You're making it worse

The comment about the null being true?

The null is never accepted. You might want to talk comic strip power, but you're only showing yourself up when it comes to the hypothesis tests used

Originally Posted by Reiver

You mean you haven't copied and pasted the bland stuff? You're making it worse


The null is never accepted. You might want to talk comic strip power, but you're only showing yourself up when it comes to the hypothesis tests used

You don't know what power means as it relates to hypothesis testing.

You can continue to display your ignorance, but the fact remains: in a test with a large enough power, the null can indeed be accepted. Your lack of education will not change this fact.

Originally Posted by Random_Variable

You don't know what power means as it relates to hypothesis testing.

This is just repetition of your previous vacuous remark. We have hypothesis test rejected or we have hypothesis failed to reject. You just have a sub-graduate maths whine about it. It is on a par with your opening post

Originally Posted by Reiver

We have hypothesis test rejected or we have hypothesis failed to reject.

In economics, yes. This is a consequence of utilizing p-value tests as opposed to powerful tests of hypothesis. Why is this a complicated concept for you to grasp?

Originally Posted by Random_Variable

In economics, yes.

Given the inconsistency with your previous 'copy and paste' foot stamp, I'm upset you haven't blagged better