EXPERIMENT NO.

1
Statistical Analysis
I. BACKGROUND
Analytical chemistry involves identification, separation and quantitation of various
components in a sample and these processes are accompanied by various reliable
measurements. These measurements must provide useful data, where their accuracy and
precision are evaluated. To obtain this, a number of replicate measurements are carried out,
and various statistical parameters and treatments are applied on the data gathered.
In this experiment, statistical tools will be applied in determining weight variation in
coins and in calibration of pipet. Statistical parameters commonly used in data treatment
include Measures of Central Tendency, Measures of Precision and Measures of Accuracy.

Measures of Central Tendency

This provides measure of the uncertainty associated with the central result. Because
chemists use two to five replicates of measurements, the central (also called “best” or
“representative”) value for a set of replicated measurements is often determined. This is done
by getting the mean (or average) and median of the data gathered in an experiment.
Mean: the average of the data / results obtained. It is calculated by adding up the
data and dividing the sum to the number of measurements made.
Median: the middle result when the set of data is arranged in increasing order. This
is true when the number of measurements is odd, and if it is even, the two middle
values are averaged.

Measures of Precision
This provides a measure of the uncertainty associated with the central value obtained.
Precision is defined as the closeness of the results obtained which were measured in exactly
the same way. Thus, this statistical procedure will help us tell the reproducibility of the
procedure done, which is based on the number of measurement or repetitions.
The scatter of a set of measurements is described by the following: range, relative
range, average deviation, variance, standard deviation, relative standard deviation and
coefficient of variation.
Range: the difference between the highest and the lowest value in a set of
measurements. This is used for small number of measurements (n ≥ 3).
Relative Range: range expressed in relative terms. The range is divided to the
mean and multiplied to 1000.
Average Deviation: this is the average of the individual deviations from the mean,
divided by the mean.
Variance: used for obtaining scatter due to random error.

Standard Deviation: the square root of variance.

Coefficient of Variation: the relative value of standard deviation. This is done by
dividing the standard deviation to the sample mean and multiplying it by 100.
Relative Standard Deviation: another relative value of standard deviation multiplied
by 1000.
Measures of Accuracy
This provides the measure on the closeness to the true value, and is expressed as
error. It may be expressed as absolute or relative error.
Absolute Error: the difference between the measured value and the true value
Relative Error: the absolute error is divided to the true value and then multiplying it
to 100 or 1000.

Confidence Limit

The mean data obtained from a given set of measurements may or may not be a
representative data of the population (true) data. Statistics may provide an answer for us
whether or not the sample mean obtained from an experiment may represent the population
mean with a given degree of probability. The confidence interval provides us the range where
the true value lies.

Table 1. Values of t for Various Levels of Probability

n-1 1 2 3 4 5 6 7 8 9 10
T90% 6.31 2.92 2.35 2.13 2.02 1.94 1.90 1.86 1.83 1.81
T95% 12.7 4.30 3.18 2.78 2.57 2.45 2.36 2.31 2.26 2.23
T99% 63.7 9.92 5.84 4.60 4.03 3.71 3.50 3.36 3.25 3.17

Q-Test

This test is used when there is a questionable data. It determines whether

the data may or may not be rejected.

Table 2. Critical Values for the Rejection Quotient, Q

N 3 4 5 6 7 8 9 10
Q90% 0.941 0.765 0.642 0.560 0.507 0.468 0.437 0.412
Q95% 0.970 0.829 0.710 0.625 0.568 0.526 0.493 0.466
Q99% 0.994 0.926 0.821 0.740 0.680 0.634 0.598 0.568
Table 3. Summary of Statistical Analysis
Measures of Central Tendency
Mean Median middle value
Measures of Precision
Relative
Range R = Xhighest - Xlowest
Range
Average
Deviation
Standard
Variance
Deviation
Relative
Coefficient
Stand.
of Variation
Dev.
Measure of Accuracy
Absolute Relative
E = Xi - Xt
Error Error
Confidence Limit t = tabulated value for n-1
measurements
Q-Test

Xq = questionable value R = range Xn = value closest to the questionable

value
 Calibration is also an important tool in analytical chemistry. One way to minimize systematic
errors in an experiment, especially if the experiment requires high accuracy, is by calibration of
glass wares. Calibration is usually done by weighing the amount of liquid (such as water) delivered
by or contained inside the volumetric apparatus, and the mass obtained is then divided to the
density of water (Eq. 1). Since density is affected by temperature, it is necessary to measure the
temperature of water at the time of calibration. Table 4 shows the density of water at varying
temperature. The volume calculated at temperature, t, is corrected to standard volume 20oC, using
the described in Equation 2.

(Eq. 1)

V20 = VT [1 + 0.00025 (20 – T)] (Eq. 2)

where:

ρT = the density of water at temperature T

VT = the calculated volume at temperature T

V20 = the volume at 20oC temperature

T= the calibration temperature of water

Table 4. Density of Water at Varying Temperature

Temperature Density (g/mL) Temperature Density (g/mL)
(oC) (oC)
10 0.9997026 21 0.9979955
11 0.9996084 22 0.9977735
12 0.9995004 23 0.9975415
13 0.9993801 24 0.9972995
14 0.9992474 25 0.9970479
15 0.9991026 26 0.9967867
16 0.9989460 27 0.9965162
17 0.9987779 28 0.9962365
18 0.9985986 29 0.9959478
19 0.9984082 30 0.9956502
20 0.9982071
II. OBJECTIVES
At the end of this activity, the students should be able to:
1. use statistical concepts in data treatment and analysis
2. understand and differentiate accuracy and precision
3. calibrate pipet using analytical balance
4. practice proper use of analytical balance and volumetric wares

III. MATERIALS
A. The students need to bring the following:
same type of 1-peso coin ➔ ten (10) pieces

B. The instructor/technician/custodian need to / should prepare the

following:

Instrument: Analytical balance

C. The students need the following:

Item Qty. Item Qty.
wash bottle 1 thermometer 1
10-mL pipet (serological or Mohr) 1 watch glass or weighing paper 3
beaker (any size) 2 graduated cylinder (50-mL) 1

IV. REMINDERS
• Wear complete PPE.
• Wash hands thoroughly with soap and water before leaving the laboratory.
• Wear gloves specially when handling glass wares to be calibrated.

V. PROCEDURE

NOTE:

• Data processing will be done during session 2. Only data gathering will be
done in lab session 1. Manage your time wisely.

• Odd-numbered groups perform procedure A first while even-numbered

groups perform procedure B first. Use the designated analytical balance for
your group in the balance room.

• Log before using the balance in the balance room.

• Divide the tasks specially during data processing.

 A. Calibration of Pipet
1. Place approximately 100 mL distilled water using graduated cylinder in any clean beaker
and label this beaker “A”.
2. Allow the water to stand at room temperature for five (5) minutes.
3. Measure the temperature of the water to the nearest 0.01oC. Make sure the temperature is
not changing anymore before recording it.
4. Weigh another clean and dry available beaker using analytical balance. Label it beaker “B”.
This will serve as a receiving beaker. (NOTE: Use gloves or tongs in handing beaker “B”)
5. Fill a clean, dry 10-mL pipette to the fill line with distilled water from beaker “A”. Wipe
excess water on the outside of the pipette.
6. Dispense the liquid properly into beaker “B”. Take note of the pipet given to you if it is a
blowout-type.
7. Weigh beaker “B” with the dispensed water using the same analytical balance you used in
step 4. Record in your data sheet.
8. Return the water to beaker “A” and dry beaker “B”.
9. Repeat steps 2 to 6 until you have made five measurements.
10. Record all data in your data sheet.
11. Calculate the volume delivered by pipette at the given temperature for each trial and correct
the volume to 20oC.
12. Calculate the mean volume, standard deviation and 95% confidence interval for your
calibrated result.

B. Determination of Mass Variations in Coins

1. Label three (3) watch glass with “A”, “B”, and “C”. Alternatively, use sturdy weighing paper
if no available watch glass.
2. Clean ten (10) pieces of one-peso coin of same type by wiping using a clean rag or tissue.
Make sure not to touch the coins after wiping. Wear gloves in handling the coins and transfer
the coins on watch glass or weighing paper “A”.
3. Place watch glass or weighing paper “B” on the balance and press “tare”.
4. Obtain a one-peso coin and weigh the coin. Record the mass to the nearest 0.0001 g using
analytical balance.
5. Place the weighed one-peso coin on watch glass or weighing paper “C”. Obtain another
one-peso coin and weigh again. Repeat the procedure on the remaining coins.
6. Record all the mass of the samples in your data sheet.

CALCULATIONS:
Divide the samples into two data sets with the following conditions:
Samples 1 to 6 Data Set 1 This will serve as “sample”
Samples 1 to 10 Data Set 2 this will serve as “population”
1. Perform Q-test at the 95% confidence level for the highest and lowest values of
data sets 1 and 2.
2. Calculate the following for data sets 1 and 2:
a. Mean d. Relative range g. confidence limit at 95% CI
b. Median e. Coefficient of variation
c. Range f. Standard deviation
3. For the calculations, write only sample computations. No repeated calculations.