Scribd
Upload
38 views16 pages

Statistical Data Treatment and Evaluation Lecture 1

Here are the steps to solve these problems: 1) Compute the mean and standard deviation of the replicate measurements: Mean = 116.4 Standard deviation = 2.5 Compute the 95% confidence interval: 116.4 ± 2.12 * (2.5/√5) = 116.4 ± 2.4 The known value of 111 is within this confidence interval, so we cannot say the results are significantly different. 2) Mean = 108.4 Standard deviation = 7.4 Range = 116.0 - 97.9 = 18.1 90% Confidence interval = 108.4 ± 1.57 * (7.4/√5) = 108.4

Uploaded by

Watchme Whip
Copyright
© © All Rights Reserved
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
38 views16 pages

Statistical Data Treatment and Evaluation Lecture 1

Here are the steps to solve these problems: 1) Compute the mean and standard deviation of the replicate measurements: Mean = 116.4 Standard deviation = 2.5 Compute the 95% confidence interval: 116.4 ± 2.12 * (2.5/√5) = 116.4 ± 2.4 The known value of 111 is within this confidence interval, so we cannot say the results are significantly different. 2) Mean = 108.4 Standard deviation = 7.4 Range = 116.0 - 97.9 = 18.1 90% Confidence interval = 108.4 ± 1.57 * (7.4/√5) = 108.4

Uploaded by

Watchme Whip
Copyright
© © All Rights Reserved
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/ 16

Gaussian Distribution

Confidence Interval
Student’s t-test
Q-test
Gaussian Distribution

Johann Carl Friedrich Gauss


(30 April 1777 – 23 February 1855)
was a German mathematician and physical
scientist who contributed significantly to
many fields, including number theory,
algebra, statistics, analysis, differential
geometry, geodesy, geophysics,
electrostatics, astronomy and optics.
A Gaussian or normal distribution curve is a curve that shows the
symmetrical distribution of data around the mean of an infinite set of data.
Student’s t - test
The Student t-test was introduced in 1908 by William Sealy
Gosset, a chemist working for the Guinness brewery in Dublin,
Ireland ("Student" was his pen name). Gosset devised the t-test
as a way to cheaply monitor the quality of stout. He published the
test in Biometrika in 1908

10-0 Guinness, Gossett,


Student, and t Tests
https://www.youtube.c
om/watch?v=U9Wr7VE
PGXA

William Sealy Gosset


(June 13, 1876–October 16, 1937)
Confidence Intervals
Confidence Interval or Confidence Limit is a type of interval
estimate of a population parameter and is used to indicate the
reliability of an estimate.
"we are 95% confident that the true value of the parameter is in
our confidence interval“
𝑡𝑠
𝐶𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑖𝑛𝑡𝑒𝑟𝑣𝑎𝑙 = 𝑥 ±
𝑛

x = mean value
t = student’s t-value
s = sample standard deviation
n = number of trials performed
Student’s “t” table
Confidence Intervals
Sample Exercise:
The carbohydrate content of a glycoprotein (a protein with sugars
attached to it) is determined to be 12.6, 11.9, 13.0, 12.7, and 12.5
grams of carbohydrate per 100 grams of protein in replicate
analysis. Find the 95% confidence intervals for the carbohydrate
content.

Answer:
95% Confidence Interval: 12.5 ± 0.5

t-table
Student’s t - test
Among the most frequently used t tests are:
Case 1: We measure a quantity several times, obtaining an
average value and a standard deviation. We need to compare our
answer with an acceptable answer. The average is not exactly the
same as the accepted answer. Does our measured answer
agree with the accepted answer “within experimental error”?
The measured value
is not significantly
different from the
T
r true value
u
e

v
a
l
u
e
Null hypothesis
Null hypothesis refers to a general statement or default position
that there is no relationship between two measured phenomena,
or no difference among groups.

State the null hypothesis: Ho : μ = μo


Where is μo a specific value and μ is the accepted value, a
theoretical value or a threshold value

If the null hypothesis is rejected then a systematic error or bias is


detected in the analytical method.
Bias = μ - μo
Case 1: Comparing a measured result with a “known” value

Sample Exercise:
You purchased a Standard Reference Material coal sample
certified by the National Institute of Standards and Technology
to contain 3.10 wt% sulfur. You are testing a new analytical
method to see whether it can produce the known value. The
measured values are 3.29, 3.22, 3.30 and 3.23 wt% sulfur. Does
your answer agree with the known answer?

To find out, compute the 95% confidence level for your answer
and see if that range includes the known answer. If the known
answer is not within your 95% confidence level, then the results
do not agree.
Answer:
3.26 ± 0.06 [The test method is biased.]
Student’s t – test (unpaired t-test)
Case 2: We measure a quantity multiple times by two different
methods that give two different answers, each with its own
standard deviation. Do the two results agree with each other
“within experimental error”?

Method A is not significantly Method A is significantly different


different from Method B from Method B
Student’s t – test (paired t-test)
Case 3: Sample 1 is measured once by Method 1 and once by
Method 2, which do not give exactly the same results. Then a
different sample, designated 2, is measured once by Method 1
and once by Method 2; and, again, the results are not exactly
equal to each other. The procedure is repeated for n different
samples. Do the two methods agree with each other “within
experimental error”?
Q-test
Dixon's Q test, or simply the Q test, is used for identification and
rejection of outliers. This test should be used sparingly and never
more than once in a data set.
Q-test is based on the statistical distribution of "sub-range ratios"
of ordered data samples, drawn from the same normal
population. Hence, a normal (Gaussian) distribution of data is
assumed whenever this test is applied. In case of the detection
and rejection of an outlier, Q-test cannot be reapplied on the set
of the remaining observations.

𝑞𝑢𝑒𝑠𝑡𝑖𝑜𝑛𝑎𝑏𝑙𝑒 𝑣𝑎𝑙𝑢𝑒 − 𝑛𝑒𝑎𝑟𝑒𝑠𝑡 𝑣𝑎𝑙𝑢𝑒


𝑄𝑒𝑥𝑝 =
𝑙𝑎𝑟𝑔𝑒𝑠𝑡 𝑣𝑎𝑙𝑢𝑒 − 𝑠𝑚𝑎𝑙𝑙𝑒𝑠𝑡 𝑣𝑎𝑙𝑢𝑒
Q-test table
Q-test
Sample Exercise:
The following values were obtained for the determination of
cadmium in a sample of dust: 4.3, 4.1, 4.0, 3.2, 3.9, 4.2, and 4.0
μg g-1. Should the last value be rejected?

(1) The N values comprising the set of observations under


examination are arranged in ascending order:
3.2 < 3.9 < 4.0 = 4.0 < 4.1 < 4.2 < 4.3
(2) The statistic experimental Q-value (Qexp) is calculated. This is
a ratio defined as the difference of the suspect value from its
nearest one divided by the range of the values (Q: rejection
quotient).
3.2 − 3.9
𝑄𝑒𝑥𝑝 = = 0.636
4.3 − 3.2
Q-test
(3) The obtained Qexp value is compared to a critical Q-value
(Qcrit) found in tables. This critical value should correspond to the
confidence level (CL) we have decided to run the test (usually:
CL=95%).
At 95% confidence level and 7 observations, Qcrit is 0.568.

(4) If Qexp > Qcrit, then the suspect value can be characterized as
an outlier and it can be rejected, if not, the suspect value must be
retained and used in all subsequent calculations.
Qexp (0.636) > Qcrit (0.568)

The null hypothesis associated to Q-test is as follows: "There is


significant difference between the suspect value and the rest
of them, any differences must be exclusively attributed to
random errors".
Assignment:
1.) A reliable assay shows that the ATP (adenosine triphosphate)
content of a certain cell type is 111 μmol / 100 mL. You developed
a new assay, which gave the following values for replicate
analyses: 117, 119, 111, 115, 120 μmol / 100 mL. Can you be
95% confident that your results is not significantly different from
the “known” value?

2.) For the numbers 116.0, 97.9, 114.2, 106.8 and 108.3, find the
mean, standard deviation, range, and 90% confidence interval for
the mean. Using the Q-test, decide whether the number 97.9
should be discarded.

You might also like