# Ch4 - Quantitative Chemical Analysis Chapter 4 Statistics...

This preview shows pages 1–10. Sign up to view the full content.

Quantitative Chemical Analysis Quantitative Chemical Analysis Chapter 4: Statistics Statistics

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
1 All measurements have an associated uncertainty (error). Statistics gives us a way to quantitate error. The ensuing discussion assumes all errors are purely random, not systematic. A histogram of many measurements (say, n times) of a single quantity takes on a bell shape as n becomes very large. Lifetimes of 4,768 Light Bulbs (hours) The bell-shaped distribution is called a Gaussian distribution . x The curve superimposed on the histogram is the Gaussian distribution based on the average (mean) value, , and the standard deviation, s.
2 Arithmetic mean (aka mean or average) Median : In an ordered series of numbers, the middle value. Mode : the value that is observed the greatest number of times. Standard deviation : Where n is the number of data points and n -1 is the number of degrees of freedom (DOF)

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
3 Histogram for Serum Cholesterol in 953 American 17-Year Olds x The above curve superimposed on the histogram is the Gaussian distribution based on and s. ( = 176, s = 30) x x
Histogram of Cation Current Passing through Individual Channels of a Frog Muscle Cell (922 Measurements) 4

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
5 2s 2 ( x x ) 2 e y = c The Gaussian distributions superimposed on the above histograms have the form where c is a constant to fit the curve to the histogram. Now, as n →∞ , µ is the “True” value of what is being measured and σ is the standard deviation. and, mean = median = mode
6 The above curve is related to the normal distribution curve y = 1 σ 2 π e ( x µ ) 2 2 2 The pre-exponental factor is the normalization factor that insures that the integral from x = −∞ to + = 1. is the “True” value of what is being measured and is the standard deviation.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
7 Normal Distribution Curves as a Function of σ y = 1 2 π e ( x µ ) 2 2 2 = 0 at left Area = 1 in all cases The width of the curve (at its inflection points), 2 , depends on the amount of scatter in the data. The integral from to is always 0.3413 from + to – is 0.6826 These are the probability that then next measurement will fall in that range.
8 Normal distribution curve applies to all problems where error is random. Integral from + σ to – is always 0.6826 so, usually plotted with abscissa in units of rather than x .

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 26

Ch4 - Quantitative Chemical Analysis Chapter 4 Statistics...

This preview shows document pages 1 - 10. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online