Scribd
Upload
90 views19 pages

Treatment of Analytical Data I. Accuracy vs. Precision A. Accuracy

This document discusses methods for analyzing analytical data, including accuracy versus precision, types of errors, expressing uncertainty in results, and rejection of outlier data points. Key points covered include: 1) Precision refers to the reproducibility of measurements and can provide information about accuracy. Accuracy describes how close a measurement is to the true value. 2) There are two main types of errors - determinate (systematic) errors which are consistent, and indeterminate (random) errors which occur due to imprecise measurements. 3) Results should express the uncertainty using significant figures, absolute or relative uncertainties, or standard deviations. Propagation of uncertainties must be considered in calculations. 4) Statistical tests like the 2

Uploaded by

theUnearthly
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
90 views19 pages

Treatment of Analytical Data I. Accuracy vs. Precision A. Accuracy

This document discusses methods for analyzing analytical data, including accuracy versus precision, types of errors, expressing uncertainty in results, and rejection of outlier data points. Key points covered include: 1) Precision refers to the reproducibility of measurements and can provide information about accuracy. Accuracy describes how close a measurement is to the true value. 2) There are two main types of errors - determinate (systematic) errors which are consistent, and indeterminate (random) errors which occur due to imprecise measurements. 3) Results should express the uncertainty using significant figures, absolute or relative uncertainties, or standard deviations. Propagation of uncertainties must be considered in calculations. 4) Statistical tests like the 2

Uploaded by

theUnearthly
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 19

Treatment of Analytical Data I. Accuracy vs. Precision A.

Accuracy

B. Precision

C. Use of Precision to Infer Accuracy

II. Precision A. Range B. Average Deviation C. Standard Deviation D. Standard Error of the Mean

E. Confidence Limits

III. Error - Measure of Accuracy A. Let X = Ave of Triplicate Determinations = True Value

B. Absolute Error = X - *X& * x 100 (% E rror)

C. Relative Error = 1. Expressed as

X& pph x 100' ------ pph % error ------ % X& ppt = x 1000' ------ ppt 2. Eg pph = ppt =

IV. Types of Error A. Determinate Error (Systematic Error)

B. Two Types of Determinate Error 1. Constant Error (Additive Error) a. Magnitude of error is constant regardless of sample size. Absolute error is constant. Relative error 9 as sample size 8

b.

2. Proportional Error a. Absolute error 8 with 8 sample size Relative Error remains constant Interfering substances in sample

b.

C. Indeterminate Error - Random Error 1. Random fluctuations occur when one pushes a method to its limits of accuracy

2. Data with Random Error vs. Less Precise Data with No Random Error

V. Methods of Expressing Uncertainty in Results A. Three methods 1. Record Uncertainty (Absolute)

2. Record Relative Uncertainty in %

3. Use of Significant Digits a. Record all accurately known digits + a digit that is uncertain

b.

Method assumes that the last digit recorded is uncertain by 1 unless stated differently

B. Rules for Significant Digits 1. Digits 1 6 9 2. Zeros between Significant Digits

3. Terminal Zeros to Right of Decimal

4. Terminal Zeros to Left of Decimal (two thoughts)

5. Place holding zeros

Except log x = 0.025

C. Mathematical Manipulation of Numbers and Significant Figures 1. Addition & Subtraction (rules of rounding numbers off)

2. Multiplication and Division of Measurements

3. Multiplication and Division of a Measurement by a Constant

4. Logs - Same number of significant figures to the right of the decimal as the total number of significant figures in the non-exponential number used to calculate the log a. [H+] = 6.6 x 10-11 8 8 Exponential non exponential

b. pH = -log [H+] = - log (6.6 x 10-11)

D. Use of Absolute and Relative Uncertainties in Mathematical Manipulations 1. Addition and Subtraction a. Rule: Add Absolute Uncertainties b. Final Buret Initial Buret Reading 48.26 ml .02 ml 0.15 ml .02 ml

Volume Delivered = 2. Multiplication & Division a. Rule: Calculate % uncertainty for each number and add the % uncertainties b. 325.0 ml .02% x 5.200 N 0.1% 3.100 N 0.1%

E. Use of Standard Deviations in Mathematical Manipulations - Propagation of Uncertainties 1. Reminder that standard deviation of <20 *0 & xi*2) j (N&1)

s '

2. Addition and Subtraction a ( sa) + b ( sb) - c ( sc) ______ y = sy sy ' sa % sb % sc '


2 2 2

j Variances

Example - Perform the following operations and compute an uncertainty for the resulting number 0.50 ( 0.02) + 4.10 ( 0.03) 1.97 ( 0.05) ______________ 2.63 ?

3.

Multiplication and Division y = a ( sa) x b ( sb) _______________ c ( sc) Relative Standard Deviations sa a sb b sc c

sy/y ' (sa /a)2 % (sb /b)2 % (s c /c)2 Example 4.10 (0.02) x 0.0050 (0.0001) 1.97 ( 0.04)

VI. Rejection of Data A. Things You May Do 1. 2. 3.

B. Statistical Rejection Tests 1. 2.5 d Rule a. Approach

b. Problem

2.

4 d Rule a. Approach

b. Problem

3.

Q Test a. Approach

Q = ________________________

b. Values of Q # Observations 3 4 5 Q0.90 0.94 0.76 0.64 # Observations 6 7 8 Q0.90 0.56 0.51 0.47

c. Example .10525 .10651 .10663

Q = _________________________

d. What Can We do if a Result Must Be Retained? 1. Estimate Precision

2.

Check Calculations

3.

Repeat Analysis

4.

Try Q Test With Additional Data Point

You might also like