Module 3 Flashcards

1
Q

Characterization of systematic, Random and gross errors

A

Systematic: determinate, affects accuracy, 1-sided
Random: indeterminate, affects precision, 2-sided
Gross: affects accuracy and precision

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Errors affecting accuracy (systematic errors example)

A

Sampling, method, measurement, personal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are sampling errors and how to mitigate

A

If improper or non representative sample is collected and analyzed
Non homogenous sample leads to inaccurate results
Mitigate by collecting true representative sample

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is a method error and examples how to mitigate

A

Result of non ideal behaviour of reagents and reaction
Incompleteness of reactions, instability of some species
Mitigate by parallel analysis of samples by an independent method

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What are measurement errors and how to mitigate

A

Instruments not calibrated properly
Mitigated by calibrating instruments

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What are personal errors how to mitigate

A

Lack of judgement. Ex. Level of liquid, Color of solution at endpoint
Mitigate with more care and paying greater attention to detail

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What are random errors caused by and how to treat

A

Caused by uncontrollable variables that exist in every physical or chemical measurement
Treated by statistical analysis of dataset

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What 2 components must any measurement have

A

1) a numerical value
2)a degree of uncertainty

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is uncertainty

A

The range of values within which the value of the analyte can be said to lie within a specified level of confidence

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is range of measure of

A

The scatter of the data rather than precision

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is Standard deviation and what is it not

A

How closely the data is clustered around the mean
It is not the random error of the mean
A measure of uncertainty of the mean due to random error

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

When does a Gaussian distribution occur

A

When an experiment is repeated and the results approach a smooth curve

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is the coefficient of variation and the formula

A

Relative standard deviation
RSS= sd/meanx100

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is a confidence interval and equation

A

A range of values within which is there’s a specified probability of finding the true value
CI=mean +/- txSD/(n)^1/2

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What does range depend on

A

Precision of individual measure,ents
Number of measurements made

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What are outliers and how to identify

A

A measurement in dataset that’s distinct from all other measurements
Identify with Grubb’s test or Dixon q test

17
Q

What is significance testing

A

Significance testing determines if the difference between two values is too large to be explained by indeterminate error

18
Q

Steps to significance testing

A
  1. State experimental problem as yes or no question
  2. A null hypothesis and an alternative hypothesis provides answers to question
  3. T test is preformed to see if there’s a statistically significant difference
  4. A confidence level is chosen to decide if null hypothesis is accepted or rejected
19
Q

What is a null hypothesis

A

States the mean values from two sets of measurements are different

20
Q

What is an alternative hypotheses

A

States the mean values from two sets of measurements are different