<div>
you can't without some way of estimating the sd<br />
is 5000 the number of samples? &nbsp; how can the test sample have more than the gerneral population?
</div>


you can't without some way of estimating the sd
is 5000 the number of samples?   how can the test sample have more than the gerneral population?

<div>
The context is:<br />
&quot;Suppose the incident rate of MI (myocardial infraction) per year was 5<br />
per 1000 men in 1990. &nbsp;To look at the changes in incidence over time,<br />
5000 men were followed for 1 year starting in 2000. &nbsp;15 new cases of MI<br />
were found.&quot;, and we know &amp;#945; =0.05 for the critical-value method.<br />
and I am trying to test if the incident rate of MI has changed from<br />
1990 to 2000. 
</div>


The context is:
"Suppose the incident rate of MI (myocardial infraction) per year was 5
per 1000 men in 1990.  To look at the changes in incidence over time,
5000 men were followed for 1 year starting in 2000.  15 new cases of MI
were found.", and we know &#945; =0.05 for the critical-value method.
and I am trying to test if the incident rate of MI has changed from
1990 to 2000.

<div>
more precisely the probaility that there will be &lt;= 15 incidents will be<br />
sum(n=0..15:5000!(5/1000)^<wbr />n(1-5/1000<wbr />)^(5000-n)<wbr />/(n!(5000-<wbr />n)!) = 0.022
</div>


more precisely the probaility that there will be <= 15 incidents will be
sum(n=0..15:5000!(5/1000)^n(1-5/1000)^(5000-n)/(n!(5000-n)!) = 0.022

<div>
<div class="content wysiwyg-content">
The general population has the mean (5/1000); and the test sample has<br />
(15/5000).<br />
However, we don't know the sd. &nbsp;In this case, how to calculate t value?<br />
<br />
If I use the critical-value method with &amp;#945; =0.05, then I come up with<br />
the critical value, -1.645158<br />
<br />
My question is how to calculate t value without knowing the sd at all?<br />
<br />
The formula is t = (x bar - mu 0) / (sd/sqrt(n)).<br />
so, it could be:<br />
<br />
(5/1000 - 15/5000)<br />
--------------------------<wbr /><br />
sd /sqrt(5000)<br />
<br />
thx<br />
<br />
ej 
</div>
</div>


The general population has the mean (5/1000); and the test sample has
(15/5000).
However, we don't know the sd.  In this case, how to calculate t value?

If I use the critical-value method with &#945; =0.05, then I come up with
the critical value, -1.645158

My question is how to calculate t value without knowing the sd at all?

The formula is t = (x bar - mu 0) / (sd/sqrt(n)).
so, it could be:

(5/1000 - 15/5000)
--------------------------
sd /sqrt(5000)

thx

ej 

Critical value and test statistic

Programming theory deals with the design, implementation, analysis, characterization, and classification of programming languages and their individual features, along with introductory programming concepts like program structure, variable declaration and conditional and looping constructs. Sub-disciplines include the formal semantics of programming languages, type theory, program analysis and transformation, comparative programming language analysis, metaprogramming, domain-specific languages, compiler construction and run-time systems.

Programming Theory

The Math / Science topic primarily includes discussions of mathematics, physics, statistics and economic analysis, but also biology, chemistry and other sciences.