Statistical functions with E-Basic?

[Katz, Lena B.]

Would it be possible to use C++, and just hook in the dll (if any language has statistical libraries, C++ is sure to have them)?  I haven't done much work with dlls and Eprime, so I'm not sure if this is a good option or not.  
 
Lena

	-----Original Message----- 
	From: eprime at mail.talkbank.org on behalf of Alex Francis 
	Sent: Tue 3/15/2005 3:50 PM 
	To: Ignacio Valdes; eprime at mail.talkbank.org 
	Cc: 
	Subject: Re: Statistical functions with E-Basic?
	
	


	I just had a similar problem. I ended up implementing the approximation of
	the z transform given in Macmillan & Creelman (1991) "Signal Detection
	Theory: A User's Guide" [a newer version of this book is now available and
	I recommend it to everyone].  It seems to work pretty well:
	
	I also implemented it in Excel and compared it with the Normsinv function -
	the two give very similar results for values of p < .99 (within a z value
	of 0.01 or so).
	
	Here is the function pasted in from Excel (the eprime code is on a
	different machine - let me know if you'd rather see that).
	
	= - 1 * D5 + ((((0.0000453642210148 * D5 + 0.0204231210245) * D5 +
	0.342242088547) * D5 + 1) * D5 + 0.322232431088) / ((((0.0038560700634 * D5
	+ 0.10353775285) * D5 + 0.531103462366) * D5 + 0.588581570495) * D5 +
	0.099348462606)
	
	Hope this helps,
	
	-alex
	
	At 03:21 PM 3/15/2005, Ignacio Valdes wrote:
	>Hello all, I've created a E-prime task that I would like to report summary
	>statistics after running such as Discrminability. A key function to
	>accomplish this would be a lookup for the z and ordinal statistics value
	>for a given p. The table for me to implement this myself would consist of
	>me keying in 300 normal distribution entries. This is something that I
	>would rather not do because most importantly, the possibility of
	>inaccuracy. I have talked to E-prime's technical support people and they
	>are unable to help me with this. They are saying that the underlying Basic
	>that they have licensed from a different company doesn't have these
	>functions which I find odd. E-prime mysteriously includes a number of
	>financial calculation functions such as mortgage calculations, but no
	>basic statistic functions? Possible solutions I have are ugly:
	>
	>1) Implement it myself -- possible inaccuracies, tedious, maintenance is
	>an issue.
	>2) Use DDE functions to try to hook Excel into calculating it -- Not sure
	>this is possible with the limited command set available.
	>
	>Does anyone have ideas on how to solve this?
	>
	>Thanks,
	>
	>-- IV
	>
	
	   Alexander L. Francis        http://web.ics.purdue.edu/~francisa
	   Assistant Professor                          francisA at purdue.edu
	   Speech, Language & Hearing Sciences       ofc. +1 (765) 494-3815
	   Purdue University                         lab. +1 (765) 494-7553
	   500 Oval Drive                            fax. +1 (765) 494-0771
	   West Lafayette IN 47907-2038
	   USA
	------------my employer requires the following addendum------------
	CONFIDENTIALITY NOTICE: This email and the documents accompanying
	this email may contain legally privileged confidential information.
	The information is intended only for the use of the individual or
	entity named as recipient. If you are not the intended recipient,
	you are hereby notified that any disclosure, reproduction or
	distribution of this email or its attachments, or the taking of any
	action in reliance on the contents of this email or its attachments,
	is strictly prohibited. If you have received this email in error,
	please notify the sender by return email.