Data Analysis and Forecasting of Humidity in Ruse, Bulgaria

This report presents an analysis of humidity data collected from Ruse, Bulgaria. The analysis begins with setting the data in a table format and plotting the data using column and line graphs. Descriptive statistics, including mean, median, mode, range, and standard deviation, are computed and interpreted to understand the central tendency and dispersion of the humidity data. Furthermore, the report employs a linear forecasting model to predict humidity levels for the 15th and 20th days, providing insights into future humidity trends. The report concludes with a list of cited references, providing a comprehensive overview of the methodologies and findings. This report provides a detailed analysis of the dataset, including descriptive statistics and forecasting, offering valuable insights into the humidity patterns.

Numeracy and Data Analysis

Table of Contents
1. setting the data in table form ...................................................................................................3
2. plotting data in the graphs .......................................................................................................3
3. Computing descriptive statistics by employing statistical techniques ....................................5
4. forecasting humidity for 15th and 20th day through linear forecasting model ......................9
REFERENCES..............................................................................................................................11

The present report is based on Ruse, Bulgaria which is one of the largest city in North-
Eastern part of a country. Furthermore, the report highlights descriptive statistics evaluation and
present forecasting of the humidity for future periods.
1. setting the data in table form
S. No. Date Data related to humidity
1 31st December 2019 72.00%
2 1st January 2020 74.00%
3 2nd January 2020 90.00%
4 3rd January 2020 87.00%
5 4th January 2020 77.00%
6 5th January 2020 82.00%
7 6th January 2020 93.00%
8 7th January 2020 79.00%
9 8th January 2020 91.00%
10 9th January 2020 81.00%
2. plotting data in the graphs
Column graph

Line chart
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
72.00%74.00%
90.00%
87.00%
77.00%
82.00%
93.00%
79.00%
91.00%
81.00%
Data related to humidity

3. Computing descriptive statistics by employing statistical techniques
a. value of Mean
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
Data related to humidity

S. No. Date Data related to humidity
1 31st December 2019 72.00%
2 1st January 2020 74.00%
3 2nd January 2020 90.00%
4 3rd January 2020 87.00%
5 4th January 2020 77.00%
6 5th January 2020 82.00%
7 6th January 2020 93.00%
8 7th January 2020 79.00%
9 8th January 2020 91.00%
10 9th January 2020 81.00%
Total of humidity data 826.00%
total number of days 10
Mean 82.60%
Interpretation- From the above table the mean value represented as 82.60% or .826.
Mean value is computed by dividing the total value of the humidity data to total number of the
days (George and Mallery, 2016). This value reflects the average of the dataset as the standard
measure of a centre of the distribution data.
b. Median value
Step 1- presenting the data in an ascending order
S. No. Date Data related to humidity
1 31st December 2019 72.00%
2 1st January 2020 74.00%
3 4th January 2020 77.00%
4 7th January 2020 79.00%

5 9th January 2020 81.00%
6 5th January 2020 82.00%
7 3rd January 2020 87.00%
8 2nd January 2020 90.00%
9 8th January 2020 91.00%
10 6th January 2020 93.00%
Step 2- calculating median observation
Median observation (n+1)/2
(10+1)/2
5.5
Median value 5th observation+6th observation/2
(.81 + .82)/2
81.50%
Interpretation- Median value of the humidity dataset of Ruse, Bulgaria accounted to
81.50% which indicates a mid value. It is determined by way of ranking an observation and
assessing the observation that present at number (n+1)/2 within the ranked order.
c. Modal value
S. No. Date Data related to humidity
1 31st December 2019 72.00%
2 1st January 2020 74.00%
3 2nd January 2020 90.00%
4 3rd January 2020 87.00%
5 4th January 2020 77.00%
6 5th January 2020 82.00%
7 6th January 2020 93.00%
8 7th January 2020 79.00%

9 8th January 2020 91.00%
10 9th January 2020 81.00%
Mode 0
Interpretation- The above table reflects that mode refers to the value that has been
occurred frequently in dataset (McCarthy and et.al., 2019). Observing the humidity data of
Bulgaria for the last 10 days it has been identified that value of mode is Zero because no value is
seen as repeated within the humidity data. It is computed by counting number of time every
value had occurred in the data.
d. Range
Largest value 93.00%
Smallest value 72.00%
Range
Largest value –
smallest value 21.00%
Interpretation- The table above depicts the range value which is been calculated by
subtracting the smallest value from the largest or maximum value (Bonner, 2018). This way the
range value attained as 21% that means 93% - 72%. It reflects that there is a less percentage of
the dispersion in a data.
e. Standard deviation
S. No. Date
Data related to
humidity (X) X^2
1 31st December 2019 0.72 0.5184
2 1st January 2020 0.74 0.5476
3 2nd January 2020 0.9 0.81
4 3rd January 2020 0.87 0.7569
5 4th January 2020 0.77 0.5929
6 5th January 2020 0.82 0.6724
7 6th January 2020 0.93 0.8649

8 7th January 2020 0.79 0.6241
9 8th January 2020 0.91 0.8281
10 9th January 2020 0.81 0.6561
Total 8.26 6.8714
Standard deviation= Square root of ∑x^2 / N – (∑x / n) ^ 2
= SQRT of (6.87 / 10) – (8.26 / 10) ^ 2
= SQRT of 0.68 – 0.682
= SQRT of 0.0022
= 0.047
Interpretation- The calculation above states that standard deviation of the humidity data
of Ruse, Bulgaria evaluated as 0.047. This value shows that the value in the statistical data are
seen as close to mean or average. It is accounted by making the square root of the value that
resulted from applying an equation.
4. forecasting humidity for 15th and 20th day through linear forecasting model
Date Days (X)
Data related to
humidity (Y) X*Y X^2
31st December
2019 1 0.72 0.72 1
1st January 2020 2 0.74 1.48 4
2nd January 2020 3 0.9 2.7 9
3rd January 2020 4 0.87 3.48 16
4th January 2020 5 0.77 3.85 25
5th January 2020 6 0.82 4.92 36
6th January 2020 7 0.93 6.51 49
7th January 2020 8 0.79 6.32 64
8th January 2020 9 0.91 8.19 81
9th January 2020 10 0.81 8.1 100
Total 55 8.26 46.27 385

m = NΣxy – Σx Σy / NΣ x^2 – (Σx)^2
Y = mX + c
M = 10 (46.27) - (55 * 8.26) / (10 * 385) – (55)^2
m = (462.7 – 454.3) / (3850 – 3025)
m = 8.4 / 825
m = 0.010 or 1.01%
c = Σy – m Σx / N
c = 8.26 – (0.010 * 55) / 10
c = (8.86 - 0.55) / 10
c = 8.31 / 10
c = .83
computing value of Y by making use of m and c value
For 15 days-
Y = mX + c
= 0.010(15)+0.83
= 0.15 + 0.83
= 0.98
For 20 days -
Y = mX + c
= 0.010(20)+0.83
= 0.2 + 0.83
= 1.03
Interpretation- The above computation depicts that the humidity for 15th and 20th day is
been seen as 0.98 & 1.03 (Ruse humidity data, 2018). It is determined or evaluated through the
equation that is Y= mX + c where value of m and c attained as 0.010 & 0.83.

REFERENCES
Books and journals
Bonner, M. D., 2018. Descriptive statistics. Police Abuse in Contemporary Democracies. p.257.
George, D. and Mallery, P., 2016. Descriptive statistics. In IBM SPSS Statistics 23 Step by
Step (pp. 126-134). Routledge.
McCarthy, R. V. and et.al., 2019. What Do Descriptive Statistics Tell Us. In Applying Predictive
Analytics (pp. 57-87). Springer, Cham.
Online
Ruse humidity data, 2020. [Online]. Available through:
<https://www.timeanddate.com/weather/bulgaria/ruse/historic>