analytical selectivity and sensitivity, assay quality control and statistical computations

plan sampling sample prep analytical measurement data analysis

Qualitative, quantitative or both? What kind of information do we have? What technique is suitable?

Accuracy depends on proper sampling, characteristic of sample is important, required good representative sample (from top, middle and bottom and mix up and take average sample)

Depends on analytical techniques

Which techniques are best?

Whether data acquires make sense or not

Accuracy and precision required Available sample amount Concentration range of the analyte Interference in sample Physical and chemical properties of the sample matrix Number of samples to be analysed Speed, ease, skill and cost of analysis

Precision Bias Sensitivity Detection limit Concentration range Selectivity

How close the same measurements made on the same material are to one another. The degree of mutual agreement amongst data that have been obtained in the same manner. Precision provides a measure of the random or indeterminate error of an analysis.

How close the measurement approached the real value?

Bias provides a measure of the systematic, or determine error of an analytical method bias: x’ = x + δ +  where is x’ is the population mean, δ is the bias (perhaps caused by an interfering component),  is a random component (experimental error), and x is the true value.

terms on calculation precision

normal distribution

standard deviation

If various different concentrations of a sample are subjected to UV/Vis radiation the different absorbance readings obtained can be plotted on a graph against concentration.

absorbance - concentration relationships graph

Is there a relationship between x and y? What is the strength of this relationship? - Pearson’s r Can we describe this relationship and use it to predict y from x? • Regression • Fitting a line using the Least Squares solution Is the relationship we have described statistically significant? - Significance tests

how well our data fit a LINEAR relationship

person’s correlation coefficient

Aim of linear regression is to fit a straight line, ŷ = ax + b to data that gives best prediction of y for any value of x This will be the line that minimises distance between data and fitted line, i.e. the residuals

best fit line equation graph

now we find the value of a that gives the least sum of squares trying out different values of a is equivalent to changing the slope of the line, while b stays constant

First we find the value of b that gives the least sum of squares Trying different values of b is equivalent to shifting the line up and down the scatter plot

outliners more than 1 different population or contrast