Exam 1 Flashcards
What’s the difference between implicit and explicit uncertainty?
Explicit uncertainty is explicitly stated
ex) 0.03+/- implies an uncertainty of 0.03
implicit uncertainty is implied by the number of significant figures reported
ex) 399.32 implies an uncertainty of 0.01
what is absolute uncertainty
it expresses the margin of uncertainty associated with a specific measurement
what is relative uncertainty
it compares the absolute uncertainty with the measurement itself.
This allows us to have a perspective on how much the uncertainty might have on a sample
usually smaller samples are impacted more by uncertainties than larger samples
what is determinate error
it is caused by the way you make a measurement, it always occurs in one direction and is constant
what is an indeterminate error
it is harder to detect but it can occur in either direction. It is not constant and is always present + random
What type of error is a precision error
indeterminate
what are the errors that affect precision
repeatability and reproducibility
what is repeatability
the precision accomplished in one session (weighing something over and over)
what is reproducibility
day-to-day laboratory precision, the precision of another person or under a different set of conditions
Can reproducibility be less than repeatability?
No, reproducibility includes repeatability
what is error
error is the difference between a single measurement and its expected value
what is uncertainty
it expresses the range of possible values for a measurement or result, it includes determinate and indeterminate errors
what is absolute error
experimental-actual value
what is the relative error
absolute error divided by the actual
Q
what is the uncertainty in this? 10.00 ± 0.02
0.02
Q
A 25 mL pipette consistently delivers 25.031 ± 0.009 mL. Is the error determinate, indeterminate or both?
Determinate: 0.031
indeterminate ± 0.009mL
what does the uncertainty express
it accompasses a range of what the values could be
Q
In a normal distrubution graph, what does the area under the curve tell us?
the probability of finding a member of a population in a range of values
what is z
it is a standard score that tells us how many standard deviations we are away from the mean
when do we use normal distribution curves?
When we think our sample set is normal and we want to see the probability of a certain event occuring/not occurring
The formula weight of CaCO3 is 100.087 +/- 0.004 g/mol,
what is the the +/- 0.004 g/mol representative of?
explicit uncertainty
Precision and Accuracy can both be measured in the laboratory, however, precision is almost always easier to measure why?
One can almost always make repreated measurements but sometimes we can’t evaluate the accuracy of something due to the lack of knowledge of the true value
A student is measuring 500.00 mL using a volumetric flask with a specified tolerance of 0.08 mL. The studuent fills the flask below the line. What type of error is this
the student ALWAYS fails to fill up the flask, it is always a constant underestimation so it is a determinate (systematic error)
When do we use a paired t-test?
When we have pairs of data and want to see the change in variances. We do not want to analyze the means. We assume that the variance is not equal
when do we use an unpaired t-test
when we want to know if the means are statistically different and we assume that the standard deviations are equal.
what is a false positive
it is when the null hypothesis is true but we say that it is false
what is a false negative
it is when the null hypothesis is not true but we say that it is
when do we use a comparing x to u test
if you have a mean value and are trying to determine if it is different from a known value (also called the reference value)
you are comparing the mean of your sample set to a known value (u)
When do we use an F test
to check if the standard deviations from sample set one and sample set two are different
always arrange s1 and s2 so that F>1
if F calculated > F table, then the difference in the standard deviations is signifiant
when do we use a grubbs test
when we want to know if we have an outlier
you can calculate it with with |(questionable value - mean)/standard deviation|
if Gcalculated is > Gtable, then we have an outlier
Errors that affect accuracy are
determinate
errors that affect precision are
indeteminate
what is ppm equivalent to
ug/g, mg/L, ug/mL
what is ppb equivalent to
ng/g,ug/L,ng/mL