Names of places in Croatia

[The Grand Nudger]

I find it unconscionable that a serious subject can use a p value of more than .005 as a guide. To do so leads to too many unnecessary errors.

But my paper with math showing that the p-value is somewhere between 1/300 and 1/17 is still better than the vast majority of papers about Croatian names of places, which do not even attempt to calculate the p-value, right?

Nope.  You can't see it, but you actually do have an amusing and novel thing to discuss.  Your "research" is a data point on false discovery rates at a given p value.

[FlatAssembler]

But my paper with math showing that the p-value is somewhere between 1/300 and 1/17 is still better than the vast majority of papers about Croatian names of places, which do not even attempt to calculate the p-value, right?

I don’t think you truly grasp what p-values mean. You seem to be mistaking statistical significance for scientific significance. It looks as though you’re trying to apply p-values to your hypothesis about Croatian place names. That’s not what p-values are intended to test.

Boru

I don't understand what you mean. By p-value, I mean the probability of that k-r pattern in Croatian river names occurring by chance. By measuring collision entropy of the Croatian language and using the Monte Carlo birthday calculations, I have shown that the probability of that pattern occurring by chance is somewhere between 1/300 and 1/17.

[FlatAssembler]

But my paper with math showing that the p-value is somewhere between 1/300 and 1/17 is still better than the vast majority of papers about Croatian names of places, which do not even attempt to calculate the p-value, right?

Nope.  You can't see it, but you actually do have an amusing and novel thing to discuss.  Your "research" is a data point on false discovery rates at a given p value.

And how do you know that my discovery is false? And even if it is wrong, isn't it still less wrong than the vast majority of papers in the field of Croatian names of places, since the vast majority of papers in that field do not even attempt to calculate the p-value?

[The Grand Nudger]

Just to be clear, you're asking me... if...had you done The Wrong Thing™, wouldn't it still be less wrong than other papers that didn't even attempt to do The Wrong Thing™?

[FlatAssembler]

Just to be clear, you're asking me... if...had you done The Wrong Thing™, wouldn't it still be less wrong than other papers that didn't even attempt to do The Wrong Thing™?

I mean, sure, a weak p-value can be alarming that the conclusion is wrong. But isn't a paper that doesn't even attempt to calculate a p-value way more alarming in that regard than a paper that has a weak p-value?

[The Grand Nudger]

Right, so that is what you're asking, just in the context of a continued assertion or argument. The short answer is no, and obviously no.

[Angrboda]

Fu Less Wong. Love U Long Time.

[FlatAssembler]

Right, so that is what you're asking, just in the context of a continued assertion or argument.  The short answer is no, and obviously no.

How is it "obvious"? I don't see it. If that were true, p-values would not be valued in social sciences (or natural sciences, for that matter), right?

[BrianSoddingBoru4]

I don’t think you truly grasp what p-values mean. You seem to be mistaking statistical significance for scientific significance. It looks as though you’re trying to apply p-values to your hypothesis about Croatian place names. That’s not what p-values are intended to test.

Boru

I don't understand what you mean. By p-value, I mean the probability of that k-r pattern in Croatian river names occurring by chance. By measuring collision entropy of the Croatian language and using the Monte Carlo birthday calculations, I have shown that the probability of that pattern occurring by chance is somewhere between 1/300 and 1/17.

But you’re continually touting (or at least implying) that p-values support your study hypothesis. P-values are only meant to test the statistical likelihood of a null hypothesis. But even if that was your null, it’s pretty pointless, since phonic patterns never arise by chance. If it did, the English word for ‘fish’ could be something like ‘grzblk’.

Boru

[FlatAssembler]

Fu Less Wong.  Love U Long Time.

What does that mean?