Professional Documents
Culture Documents
Covid-19 Case Study Using MS-Excel (Report) : Submitted By: Rasika Deshpande (020) PGDM-RBA, Welingkar, Bangalore
Covid-19 Case Study Using MS-Excel (Report) : Submitted By: Rasika Deshpande (020) PGDM-RBA, Welingkar, Bangalore
Covid-19 Case Study Using MS-Excel (Report) : Submitted By: Rasika Deshpande (020) PGDM-RBA, Welingkar, Bangalore
Using MS-Excel
(Report)
Uttarakhand
Tripura
Tamil Nadu
Rajasthan
Puducherry
Nagaland
Meghalaya
Maharashtra
Lakshadweep
Kerala
Jharkhand
Himachal Pradesh
Gujarat
Delhi
Chhattisgarh
Bihar
Arunachal Pradesh
Andaman and Nicobar Islands
0 2000000 4000000 6000000 8000000
From the given bar graph, we can infer that Maharashtra registered
highest number of cases and highest number of deaths.
Some of the following reasons of failure of Maharashtra to handle
covid-19 outbreak is given below:
• Incoming international travellers:
Mumbai being financial capital of the India and Pune being one of
the largest IT service exporters in India, more and more
international travellers travel through these two cities in
Maharashtra. Also, many people from Maharashtra who worked
or studied abroad returned home a month ago and after the
Corona news.
So, this might be the reason behind covid out-break in Mumbai and
in Maharashtra.
Max of Death
Uttarakhand
Tripura
Tamil Nadu
Rajasthan
Puducherry
Nagaland
Meghalaya
Maharashtra
Lakshadweep
Kerala
Jharkhand
Himachal Pradesh
Gujarat
Delhi
Chhattisgarh
Bihar
Arunachal Pradesh
Andaman and Nicobar Islands
0 20000 40000 60000 80000 100000 120000 140000 160000
• Poor Governance:
So, this might be the reason of maximum covid cases and deaths in
Maharashtra.
Outliers for maximum covid cases are: Tamil Nādu (2716421), Karnataka
(2992276), Kerala (5071135) and Maharashtra (6625872)
After looking into given data, Andaman and Niko bar Island is having
highest recovery rate of 88.13%. But as, this island falls under union
territories of India we can interpret from given statistic chart that
Tripura has the best recovery rate (83.50) in India.
Following might be the reasons for the best recovery rate in Tripura:
1) Geographic location: Tripura is a state in northeastern India. It is
third smallest state in the country and is bordered by Bangladesh,
assam and Mizoram.
As the state is geographically isolated it might be the one of the
reasons for comparatively less covid cases resulted in highest
recovery rate.
Recovery rate = cured cases/ confirmed cases
Uttar Pradesh
Tamil Nadu
Punjab
Nagaland
Manipur
Lakshadweep
Karnataka
Himachal Pradesh
Goa
Chhattisgarh
Assam
Andaman and Nicobar Islands
0.00% 10.00% 20.00% 30.00% 40.00% 50.00% 60.00% 70.00% 80.00% 90.00%100.00%
3) Which states have done better in terms of having lower deaths despite
higher cases as compared to other states?
State Data
7000000 160000
6000000 140000
120000
5000000
100000
4000000
80000
3000000
60000
2000000
40000
1000000 20000
0 0
When we look into above statistical chart, it is very easy to understand that,
Kerala has done great job in keeping death rate lower despite of spike in the
cases.
1) Better Management: The covid-19 outbreak hit Kerala one month late
as compared to other states that means Kerala got around one month
to learn about the spread and also to design the policies.
Also, the government of Kerala started the lockdown one week before
the national lockdown was announced.
They were better prepared and large social media campaigns which
helped almost every citizen knowing what exactly was coming and how
to deal with it, CM of Kerala came live every day to update people about
the current situation and the measures government is taking and
making sure none of the citizens will go hungry by making adequate
arrangements like community kitchens, free rations to homes etc made
sure people have no reason to leave their homes.
So, because of these reasons, Kerala might manage to control its death rate
as compared to the other states in the country.
No. As India’s average recovery rate is 79.12 % and world’s average recovery
rate is 79.18%, we cannot say that India’s recovery rate is significantly greater
than worlds average rate
Explanation:
SUMMARY OUTPUT
Regression Statistics
Multiple R 0.999107
R Square 0.998216
Adjusted R Square 0.996584
Standard Error 802127.8
Observations 616
ANOVA
Significance
df SS MS F F
Regression 2 2.21E+17 1.11E+17 171749.7 0
Residual 614 3.95E+14 6.43E+11
Total 616 2.21E+17
Confirm= 0.9224*cured+8.6944*Death
Cured = (confirm-8.6944*death)/0.9224
Using these equations, we got the value for cured. After this, we put
the value of cured in given equation, to get the value of active
cases.
Confirmed cases = Active Cases + Cured Cases + Deaths.
Yes. We can predict the number of deaths from the confirmed cases
of data. With the help of equation which we derived using regression
plot between confirmed cases and deaths. Wherein to prove our
derivation to be accurate, we used this equation and put the value of
confirmed cases and got approximately equal data of the death as
that of actual data.
Andhra Pradesh
16000
14000 y = 0.0071x
12000 R² = 0.9944
10000
8000
6000
4000
2000
0
0 500000 1000000 1500000 2000000 2500000
Correlation
between
actual death
and
predicted
Row Labels Equation deaths
Andhra Pradesh y= 0.0071x 0.994394
Arunachal
Pradesh y=0.0047x 0.990052916
Assam y= 0.0086x 0.977197367
Bihar y= 0.0113x 0.945143512
Chhattisgarh y= 0.0132x 0.998253425
Delhi y= 0.017x 0.994835741
Goa y= 0.0178x 0.994696634
Gujarat y= 0.0127x 0.989426795
Haryana y= 0.012x 0.991620354
Himachal
Pradesh y= 0.0167x 0.998810051
Jharkhand y= 0.014x 0.988939515
Karnataka y= 0.0124x 0.995443774
Kerala y= 0.0052x 0.979970539
Madhya Pradesh y= 0.0125x 0.983933909
Maharashtra y= 0.0203x 0.982764403
Manipur y= 0.0154x 0.99751533
Meghalaya y= 0.0168x 0.997056471
Mizoram y= 0.0035x 0.997193675
Nagaland y= 0.0179x 0.961529952
Odisha y= 0.0064x 0.947008249
Punjab y= 0.0272x 0.997018745
Rajasthan y= 0.0091x 0.995291639
Sikkim y= 0.0133x 0.979799434
Tamil Nadu y= 0.0133x 0.996118617
Telangana y= 0.0058x 0.997445935
Tripura y=0.0101x 0.993659278
Uttar Pradesh y= 0.013x 0.993478285
Uttarakhand y= 0.0206x 0.99400484
West Bengal y= 0.0126x 0.981855365
For first wave in India, we considered data from 10th July 2020 to 12th
November.
India
first wave
121
109
97
85
73
61
49
37
25
13
1
0 1000000 2000000 3000000 4000000 5000000 6000000 7000000 8000000 9000000 10000000
confirmed Death
For the second wave in India, we considered 11th march to 17th July 2021
121
113
105
97
89
81
73
Deaths
65
57
49
41
33
25
17
9
1
0 5000000 10000000 15000000 20000000 25000000 30000000 35000000
Active cases
For the first wave we get the correlation of 99.99% and for second wave we get
the correlation of 97.63%
Here, we can see that in second wave, correlation of confirmed cases and
deaths are less than first wave. From this we can predict that, there might be
variation in the give data of second wave as compared to first wave. Like
increase in deaths as well as increased in the active cases.
6) Records for a few dates are missing. Predict them for India-level data.
Missing data are values that are not recorded in a dataset. They can be a
single value missing in a single cell or missing of an entire observation
(row). Missing data can occur both in a continuous variable or a
categorical variable.
1) For example, there is a available data for 1st and 3rd and the data for 2nd
is missing.
So here take the average of 1st and 3rd to get the data for 2nd. Here we
used this method as we observed that the provided data is progressive
in nature.
2) Confirmed cases on 2nd = (confirmed cases on 1st + confirmed cases on
3rd) /2
3) In the same way we can calculate the data for cured cases and deaths.
4) To calculate the active cases, we use the given formula:
Active cases = Confirmed cases – Cured cases – Deaths
Confirmed Active
Date Region Cases Cases Cured/Discharged Death
15-12-2020 India 9906165 339820 9422636 143709
16-12-2020 India 9931361 331093 9456188 144080
17-12-2020 India 9956557 322366 9489740 144451
01-01-2021 India 10295320 252438 9893795 149087
02-01-2021 India 10309642 249829 9910553 149261
03-01-2021 India 10323965 247220 9927310 149435
04-01-2021 India 10340469 243953 9946867 149649
25-01-2021 India 10667736 184182 10330084 153470
26-01-2021 India 10678632 180340 10344695 153597
27-01-2021 India 10689527 176498 10359305 153724
27-02-2021 India 11079979 159590 10763451 156938
28-02-2021 India 11096110 164109 10774954 157047.5
01-03-2021 India 11112241 168627 10786457 157157
04-03-2021 India 11156923 173413 10826075 157435
05-03-2021 India 11174506 176859 10840102 157546
06-03-2021 India 11192088 180304 10854128 157656
11-03-2021 India 11285561 189226 10938146 158189
12-03-2021 India 11309645 195624 10955703 158318
13-03-2021 India 11333728 202022 10973260 158446
25-03-2021 India 11787534 395192 11231650 160692
26-03-2021 India 11848222 423920 11263336.5 160966
27-03-2021 India 11908910 452647 11295023 161240
19-07-2021 India 31144229 421665 30308456 414108
20-07-2021 India 31180283 414418 30349571.5 416294
21-07-2021 India 31216337 407170 30390687 418480
22-07-2021 India 31257720 409394 30429339 418987
23-07-2021 India 31334491 410292 30504223 419977
24-07-2021 India 31372877 410740 30541664 420472
25-07-2021 India 31392069 410965 30560385 420720
26-07-2021 India 31411262 411189 30579106 420967
16-09-2021 India 33172237 342223 32389375 440639
17-09-2021 India 33294814 341431 32510799 442584
18-09-2021 India 33417390 340639 32632222 444529
02-11-2021 India 34296237 153776 33683581 458880
03-11-2021 India 34308631 151178 33698187.5 459266
04-11-2021 India 34321025 148579 33712794 459652
12-11-2021 India 34414186 137416 33814080 462690
13-11-2021 India 34425747 136667 33825970 463110
14-11-2021 India 34437307 135918 33837859 463530
7) Forecast the number of cases, deaths and cures for India for next week.
As we have the all the data for India level, we can forecast the values
for next week using moving average method.
So here, using moving average method, we predicted the data for
confirmed cases, cured cases, the active cases and deaths.