Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
49 views

Random Errors in Chemical Analysis

RANDOM ERRORS ON CHEMICAL ANALYSIS *Fundamentals of Analytical Chemistry (8th Edition) REFERENCE *Analytical Chemistry Lecture topic, CHAPTER 6 (c) Ma'am Erlyn Jessie Dy

Uploaded by

Dave Marimon
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
49 views

Random Errors in Chemical Analysis

RANDOM ERRORS ON CHEMICAL ANALYSIS *Fundamentals of Analytical Chemistry (8th Edition) REFERENCE *Analytical Chemistry Lecture topic, CHAPTER 6 (c) Ma'am Erlyn Jessie Dy

Uploaded by

Dave Marimon
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 24

Random Errors in Chemical

Analysis
A. Nature of Random Errors

Uncontrollable variables are the source of


random errors
Contributors to random errors are not all
identifiable
individually detectable
quantifiable
The combined effect of random errors produce
the fluctuation of replicate measurements
around the mean
Random errors are the major source of uncertainty
Distribution of Random Errors
Assume four contributors to the random error of equal magnitude.
qual probability of occurrence of negative and positive deviation.
ach can cause the final result to be high or lo! by "U
1:4:6:4:
1
Frequency of Occurrence and Probability
The frequency of
a deviation of a
given
magnitude is a
measure of the
probability of
occurrence of that
deviation
!."#
$".%# $".%#
6.$"#
6.$"#

#or ten equal si$e


uncertainty
&aussian 'ur(e or Normal Error 'ur(e

#or a very
large
number of
individual
errors
Re)licate Data on t*e 'alibration of a 1%m+ Pi)et
&eneratin, a *isto,ram
Frequency -it*in ran,es
Distribution of t*e E.)erimental Errors A))roac*es
a &aussian 'ur(e
A % &ar 'raph or (istogram & 'aussian Curve
/ources of Random 0ncertainties
). *isual +udgments
,. *ariations in the drainage time and in
the angle of the pipet as it drains
-. Temperature fluctuations
.. *ibration and drafts that cause small
variations in the balance readings.
/tatistical 1reatment of Random
Errors

/istribution of the majority of analytical data


displays characteristics of the normal
distribution
Therefore0 'aussian distribution is used to
appro1imate distribution of analytical data

Available standard statistical methods are


used
to evaluate analytical data assuming random
distribution of errors
1erminolo,y

2opulation3 all possible observations4


measurements4a universe of data
Types of population
#inite and real 5lot of steel0 a lot of Advil Tablets6
(ypothetical or conceptual 5Calcium in blood0 lead in
la7e 8ntario6.
A sample of the population is analy$ed
9ample3 subset of the population
Results from the analysis are used to infer the
characteristics of the population
Pro)erties of &aussian 'ur(es

The gaussian curve


is
fully characteri$ed by
t!o parameters
the mean3:
the standard
deviation3;

2opulation mean
5:6 and
9tandard
/eviation5;6
0ni(ersal &aussian 'ur(e

Abscissa3
deviation from
the mean in
units of standard
deviation
Pro)erties of a normal error cur(e

<ean occurs a the central point of


ma1imum
frequency
9ymmetrical distribution of positive and
negative
deviations
1ponential decrease in frequency as the
magnitude of the deviations increases
1*e /am)le /tandard De(iation

=umber of degrees of
freedom3 number of
independent results
needed to compute the
standard deviation

As = approaches
infinity0
s approaches ; and
approaches :
E.am)le
The follo!ing results !ere obtained in the
replicate analysis of a blood sample for its lead
content3 >.?@,0 >.?@A0 >.?@,0 >.?@)0 and >.?A>
ppm 2b. Calculate the mean and the standard
deviation of this set of data.
9ample Bi B,
>.?@, >.@A@@>.
>.?@A >.@?)@-A
>.?@, >.@A@@>.
>.?@) >.@A.>>)
>.?A> >.@??A
sumBi C -.??) ,.D..).@
mean C >.?@.,ppm 2b
9 C >.>>-?AD
Assi,nment
). Consider the sets of replicate.
Calculate3 a. mean b. median c.
spread d. standard deviation
a. ,..0 ,.)0 ,.)0 ,.-0 ).@
b. AE.E.0 AE.E,0 AE.D>
c. >.>E>,0 >.>DD.0 >.>DDA0 >.)>>>
/tandard Error of t*e 2ean
The standard
deviation of the
mean
C standard error
of
the mean
Pooled /tandard De(iation
Relati(e /tandard De(iation
/i,nificant Fi,ures
All certain digits plus one uncertain digit
Rules
All initial $eros are not significant
All final $eros are not significant0 unless they
follo! a decimal point
Feros bet!een non$ero digits are significant
All remaining digits are significant
Use scientific notation to e1clude $eros
that are not significant
/i,nificant fi,ures in Numerical
'om)utations

You might also like