
Probability and Statistics Basic Probability and Statistics Math Forum 
 LinkBack  Thread Tools  Display Modes 
November 16th, 2014, 12:23 PM  #1 
Senior Member Joined: Feb 2010 Posts: 135 Thanks: 0  Type 1 error  stats
what is a "twosided type I error" in a statistical test (e.g: research study)? thanks

November 16th, 2014, 11:27 PM  #2  
Senior Member Joined: Jan 2012 From: Erewhon Posts: 245 Thanks: 112  Quote:
Suppose our null hypothesis $H_0$ that the true value of the test statitic $t=t_0$ then a two sided test with a type 1 error probability $\varepsilon$ would be one for which we reject $H_0$ if $tt_0>v_{crit}$ where $v_{crit}$ is chosen so that: $$ p(tt_0>v_{crit}H_0)=\varepsilon$$ This is a two sided test because it is a test that $v_{crit}<tt_0<v_{crit}$. That is it is a test for the size of the deviation from the null in either direction. CB  

Tags 
error, stats, type 
Search tags for this page 
Click on a term to search for related topics.

Thread Tools  
Display Modes  

Similar Threads  
Thread  Thread Starter  Forum  Replies  Last Post 
possible error/relative error  jkh1919  Calculus  5  August 4th, 2012 06:30 PM 
TwoTailed Type II error (beta)  Erimess  Advanced Statistics  0  January 12th, 2012 06:10 PM 
Relative error Percenttage error  esther  Calculus  1  October 25th, 2011 03:57 AM 
Type 2 error  fc_groningen  Advanced Statistics  1  June 25th, 2011 07:54 AM 
Questions on Type 2 error  pinto90a  Advanced Statistics  0  March 11th, 2010 04:11 AM 