Beruflich Dokumente
Kultur Dokumente
Joraen Talamor
Kyle Denev Villaflor
I. Introduction
2 2.2300
Date Set 2
3 5.3739
4 5.4232
5 5.3745
6 5.4122
7 5.2870
8 5.4138
9 5.3379
10 5.3441
B. Q-test
C. Reported Values
III. Discussion
The statistical parameters calculated from data set 1 have minimal variations obtained from data set 2.
This could be due perhaps because most of the date from the second data set comes from the first data set.
The confidence limits tell us that we are confident that the samples we have gathered are ranging
between its endpoints. We can say that we have 100(1-α)% confidence that the parameter we are estimating
will lie between the two endpoints from our confidence interval. Naturally, we choose values that is close
to 0 for our α (0.1, 0.05, and 0.01) so that so that we can be more confident. The more it is closer to 0, the
lesser is its margin of error.
The Q-test is a simple statistical test to determine if a data point that is very different from the other
data points in a set can be rejected. In this experiment, the result of our Q-test is accepted due to the true
value of the test is greater than the calculated value of the test.
Standard deviation is the measure of the dispersion of a set of data from its mean. The more spread
apart the data, the higher the deviation. Standard deviation is calculated as the square root of
variance. The standard deviation provides us with a measure of just how spread out the scores are: a high
standard deviation means the scores are widely spread; a low standard deviation means they're bunched
up closely on either side of the mean.
When several small sets have the same sources of indeterminate error (i.e. the same type of
measurement but different samples) the standard deviations of the individual data sets may be pooled to
more accurately determine the standard deviation of the analysis method.The pooled standard deviation is
most useful when used in the two sample t-test, when conducting hypothesis tests for the means of two
samples.
IV. Conclusion
There were 2 groups of coins used, the data set 1 and the data set 2. No significant difference can be
observed from both data sets. Both set of coins were from the year 2010 and have no significant difference
from the coins can be observed. The group learned from this experiment the proper handling, calibration
and reading of the analytical balance.
The statistical parameters of the sample data were measured which was later then used for statistical
tests which were Grubbs’ test and Q-tests. Furthermore, the group also discovered that the weighing
methods have no significant difference between their means and variances.
V. References
Grubbs, Frank E. (1950) “Sample criteria for testing outlying observations.” Annals of Mathematical
Statistics. 21 (1): 27 – 58. doi: 10/1214/aoms/1177729885.
Skoog, D.A., West, D.M., et al. Fundamentals of Analytical Chemistry, 9th ed.; Cengage Learning Asia Pte
Ltd., 2014
APPENDIX
Sample calculations using different statistical concepts
Table 1.1 Reported Values
Data Set 𝑋̅ s RSD R RR CL
1 5.3410 0.0875 16.3827 0.1932 36.1730 5.3410+0.091805
2 5.3429 0.0743 13.9063 0.1932 36.1601
a.) Mean
5.2319+5.2300+5.3739+5.4232+5.3745+5.4122
n= 6
n = 5.3410
Using the same process, the mean of Data Set 2 is 5.3429.
b.) Standard Deviation
Required values in order to solve the standard deviation (Data Set 1)
xi 𝑥̅ i (xi - 𝑋̅) (xi - 𝑋̅)2
= √0.00765625
= 0.0875
Using the same process, the standard deviation of Data Set 2 is 0.0743.
= 0.0875/5.3410
= 16.3827
Using the same process, the relative standard deviation of Data Set 2 is 13.9063.
d.) Range
W = Max – Min
= 5.4232 – 5.2300
= 0.1932
Data Set 1 and Data Set 2 have the same range of 0.1932.
= 36.1730
Using the same process, the relative range of Data Set 2 is 36.1601.
(0.0875)
= 5.3410 + (2.57)
√6
= 5.3410 + 0.091805
Using the same process, the confidence limit (95% confidence level) with t = 2.262 of Data Set 2
is 5.3429 + 0.053147.
2 2
∑(𝑥𝑖−𝑋𝑖) + ∑(𝑥2−𝑥2)
Spooled = √ 𝑁1+𝑁2−2
0.08793277
=√ 14
= √0.006280912
= 0.07925
Table 2 Q-Test
Data Set Suspect Values Qtrue Qcalc Conclusion
1 H: 5.2319 0.625 0.00983 Qcalc < Qtrue
L: 5.2300
2 H: 5.2319 0.466 0.00983 Qcalc < Qtrue
L: 5.2300
a.) Q-test
|5.2319−5.2300|
Qexp = 0.1932
= 0.00983
|5.2319−5.2300|
Qexp = 0.1932
= 0.00983
Table 3 Grubbs Test
Data Set Suspect Values Gtabα=0.05 Gexp Conclusion
1 H: 5.2319 1.8871 0.021714 Gcalc < Gtrue
L: 5.2300
2 H: 5.2319 2.290 0.025572
L: 5.2300
= 0.021714
|5.2319−5.2300|
Gexp = 0.0743
= 0.025572