The present study estimates the impact of climatic factors on various seasonal diseases of students at DIT University Dehradun. For this, the study used experimental data based on a daily survey of patients (students) who came for treatment for various diseases in the Hospital of DIT University during December 01, 2015, to November 30, 2016. Descriptive results of the study indicate that seven different types of seasonal diseases have been observed during the aforesaid period. Estimated values of the Chi2 test provide a piece of empirical evidence that there is significant variation in various diseases across months. Thereupon, it assesses the impact of climatic factors on different types of seven diseases using the linear and non-linear regression model. Empirical results based on both models imply that climatic factors have a significant impact on various diseases of students. It provides empirical evidence on the association of climatic factors with various seasonal diseases of students. Also, this study formulates an authentic and viable empirical model to predict various diseases using marginal impact analysis techniques. It is policy-oriented research that provides conclusive suggestions to mitigate the adverse impact of climatic factors on various diseases and research directions to generalize the empirical results of this study.

1. A Comparative Study of Data Mining Classification by Formulation of Empirical Models on the basis
of symtoms of an ailment.
By- Ankit Gururani
under
Prof. Ajay Kumar([Post-Doctorate (Science & Technology Entrepreneurship, DST (GoI) PRC,
Entrepreneurship Development Institute of India, Ahmedabad); PhD (Economics, IIT Indore); MPhil
(Economics, DAVV Indore)])
Abstract
The present study estimates the impact of climatic factors on various seasonal diseases of students in DIT
University Dehradun. For this, the study used experimental data based on daily survey of patients
(students) who came for treatment for various diseases in Hospital of DIT University during December
01, 2015 to November 30, 2016. Descriptive results of study indicate that seven different types of
seasonal diseases have been observed during aforesaid period. Estimated values of Chi2
test provide an
empirical evidence that there is significant variation in various diseases across months. Thereupon, it
assess the impact of climatic factors on different types of seven diseases using linear and non-linear
regression model. Empirical results based on the both the models imply that climatic factors have a
significant impact on various diseases of students. It provide an empirical evidence on the association of
climatic factors with various seasonal disease of students. Also, this study formulate an authentic and
viable empirical model to make prediction of various diseases using marginal impact analysis technique.
It is a policy oriented research which provide conclusive suggestions to mitigate the adverse impact of
climatic factors on various diseases and research direction to generalize the empirical results of this study.
Finally, it would also discover a software to make future projection of various diseases in near future.
Keywords: Climatic factors; Seasonal diseases; Diseases prediction; Empirical model; Dehradun;
Uttarakhand; India.
1. Introduction
Research Questions
• Whether climatic factors have any significant association with various seasonal diseases or not?
• How various seasonal diseases are climate sensitive?
• How researchers and health scientists can estimate the impact of climatic factors on various diseases?
• How it is possible to project future prediction of various diseases?
• What is association of climatic factors with various seasonal diseases of students of DIT University
Dehradun?
• How it is possible to mitigate the impact of climatic factors on various seasonal diseases of students
of DIT University Dehradun?
• What must be policy suggestions to reduce the negative consequences of climate change in different
months on various diseases of students of DIT University Dehradun?
Research Objectives
• To assess the various seasonal diseases of students of DIT University Dehradun using experimental
data.

2. • To estimate the association of various seasonal diseases with different climatic factors using
correlation coefficient technique.
• To examine the impact of climatic factors on various diseases using linear and non-linear regression
models.
• To estimate the projection of various diseases using Marginal Impact Analysis technique.
• To provide conclusive policy suggestions to mitigate the adverse impact of climate change on various
diseases based on existing studies.
• To deliver authentic research direction to researchers and health scientists to undertake extensive
research to predict the occurrence of various diseases due to climate change in near future.
2. Review of Literature
3. Research Methodology
Data Collection Technique: Day wise information on various diseases are collected through filed
survey.
Climatic Data: IMD (GoI)
4. Formulation of Empirical Model
Univariate and Multi-variable or mixed model ()
5. Discussion on Descriptive Results
Descriptive Results
Table: Occurrence of various diseases in 12 months
Diseases/Months
Ja
n
Fe
b
Marc
h
Apri
l
Ma
y
Jun
e
Jul
y
Au
g
Se
p
Oc
t
No
v
De
c
Tota
l
Abdomen
pain/Vomiting/Stoma
ch Pain/Acidity
18 15 21 33 5 2 0 37 20 6 5 7 169
Abdomen
pain/Vomiting/Stoma
ch Pain
55 107 50 10 4 1 4 18 22 7 20 1 299
Abdomen
pain/Vomiting/Stoma
ch Pain
0 13 15 9 0 0 0 0 2 3 7 3 52
Acidity 0 0 1 1 1 0 0 1 0 0 1 1 6
Allergy/Fungal
Infection/Itching
3 7 6 7 1 0 2 21 35 13 6 6 107
Itching 9 9 5 6 1 0 1 10 21 7 1 0 70
Fungal
infection/Itching
9 2 1 1 0 0 0 1 2 4 0 0 20
Body pain/ body
ache/Eye and ear
infection/Tooth pain
17 13 12 16 5 0 2 16 27 30 24 3 165
Eye and ear infection 9 7 5 8 2 0 0 2 6 6 4 0 49
Tooth pain/Infection 3 2 3 1 1 0 0 2 3 5 1 0 21
Cold / Fever/Loose
Motion/Vomiting
12
3
182 104 127 20 0 44 220
13
9
14
1
92 20 1212
Fever, Pain and
Vomiting
0 0 0 4 0 0 0 0 5 0 4 0 13
Vomiting/loose 17 14 8 38 7 3 3 15 19 6 7 3 140

3. motion/stomach pain
Lose motion/vomiting 23 37 23 52 4 0 2 24 26 5 6 4 206
Cold /Throat Pain/
headache/Nausea,
weakness/Sore
throat/sore cough
57 0 12 10 0 0 2 0 0 0 2 0 83
Headache 30 85 55 32 5 0 6 44 35 32 26 13 363
Nausea, weakness,
head ache
3 1 4 9 1 0 0 1 0 2 2 1 24
Cough / Throat
Infection/Throat
pain/Tonsillitis
43 33 29 35 1 4 10 92 49 29 17 2 344
Throat infection/
Throat Pain
16 29 10 18 1 0 3 50 48 19 14 3 211
Tonsillitis/Throat Pain 3 14 2 0 0 0 0 5 3 4 2 0 33
Dehydration,
Dysentery Asthmatic
53 58 48 21 12 0 6 64 44 16 6 2 330
Dehydration 0 1 0 3 0 0 0 1 0 8 0 0 13
Dysentry 3 10 20 6 0 0 0 0 0 0 0 0 39
Injury 36 42 48 27 5 13 22 59 51 68 39 24 434
Total
53
0 681 482 474 76 23 107 683
55
7
41
1 286 93
Empirical Results
Table 1: Association of Abdomen pain/Vomiting/Stomach Pain/Acidity diseases with climatic
factors
Model Linear Model Non-linear Model
Number of obs. 161 161
F (3, 157) 4.61 2.38
Prob > F 0.004 0.0315
R-squared 0.081 0.0849
Adj R-squared 0.0634 0.0492
Root MSE 2.7585 2.7792
No of topati Coef. Std. Coef. Std.
dwmaxt -0.2317* 0.0906 0.0241* 0.4951
dwmaxt2 -0.0060* 0.0098
dwmint 0.0876* 0.0825 0.1233* 0.2898
dwmint2 -0.0009* 0.0086
dwpcp -0.0120* 0.0339 -0.0252* 0.0958
dwpcp2 0.0003* 0.0020
Con Coef. 7.7120* 1.3369 4.9080* 4.8709
Source: Authors’ estimation; Note: *, **, and *** indicate the parameter is statistically significant at the 1%, 5%
and 10% significance level respectively.
Table 2: Association of Allergy/Fungal Infection/Itching disease with climatic factors
Model Linear Model Non-linear Model
Number of obs. 100 100
F( 3, 157) 5.62 2.89
Prob > F 0.0014 0.0127
R-squared 0.1494 0.1569
Adj R-squared 0.1228 0.1026

4. Root MSE 2.0336 2.057
No of topati Coef. Std. Coef. Std.
dwmaxt -0.0869* 0.0859* 0.0895* 0.5297
dwmaxt2 -0.0038* 0.0107
dwmint 0.1038 0.0723 0.1386* 0.2954
dwmint2 -0.0020* 0.0085
dwpcp 0.0555* 0.0249* 0.1097* 0.0832
dwpcp2 -0.0011* 0.0016
Con Coef. 2.4522* 1.2963 0.4114* 5.0795
Source: Authors’ estimation; Note: *, **, and *** indicate the parameter is statistically significant at the 1%, 5%
and 10% significance level respectively.
Table 3: Association of Body pain/ body ache/Eye and ear infection/Tooth pain with climatic factors
Model Linear Model Non-linear Model
Number of obs. 113 113
F( 3, 157) 0.37 0.53
Prob > F 0.7712 0.7839
R-squared 0.0102 0.0292
Adj R-squared 0.017 0.0258
Root MSE 1.611 1.6179
No of topati Coef. Std. Coef. Std.
dwmaxt -0.03023* 0.0592 0.069516* 0.33312
dwmaxt2 -0.00363 0.00665
dwmint 0.049107 0.05558 0.197068* 0.20896
dwmint2 -0.0034 0.00618
dwpcp -0.00704* 0.01937 -0.07739* 0.07193
dwpcp2 0.001501 0.00141
Con Coef. 2.264286* 0.89587 0.916163* 3.29904
Source: Authors’ estimation; Note: *, **, and *** indicate the parameter is statistically significant at the 1%, 5%
and 10% significance level respectively.
Table 4: Association of Cold/Fever/Loose Motion/Vomitting
Model Linear Model Non-linear Model
Number of obs. 192 192
F( 3, 157) 5.17 2.87
Prob > F 0.0019 0.0108
R-squared 0.0762 0.0851
Adj R-squared 0.0614 0.0554
Root MSE 6.2591 6.2792
No of topati Coef. Std. Coef. Std.
dwmaxt -0.3737* 0.1854 0.8717* 1.0372
dwmaxt2 -0.0262 0.0206
dwmint 0.4592* 0.1702 0.2491* 0.6040
dwmint2 0.0062 0.0180
dwpcp 0.0192* 0.0750 0.0250* 0.1937
dwpcp2 -0.0004 0.0045
Con Coef. 10.9103* 2.7641 -1.7333* 10.2121
Source: Authors’ estimation; Note: *, **, and *** indicate the parameter is statistically significant at the 1%, 5%
and 10% significance level respectively.

5. Table 5: Association of Cold /Throat Pain/ headache/Nausea, weakness/Sore throat/sore cough
with climatic factors
Model Linear Model Non-linear Model
Number of obs 159 159
F( 3, 157) 6.81 3.43
Prob > F 0.0002 0.0034
R-squared 0.1165 0.1191
Adj R-squared 0.0994 0.0844
Root MSE 2.9562 2.9808
No of topati Coef. Std. Coef. Std.
dwmaxt -0.2499* 0.0928 0.0521* 0.5337
dwmaxt2 -0.0055 0.0107
dwmint 0.0644* 0.0848 -0.0985* 0.3052
dwmint2 0.0046 0.0092
dwpcp -0.0264* 0.0333 -0.0059* 0.1037
dwpcp2 -0.0005 0.0021
Con Coef. 8.7711* 1.3976 5.9953 5.3083
Source: Authors’ estimation; Note: *, **, and *** indicate the parameter is statistically significant at the 1%, 5%
and 10% significance level respectively.
Table 6: Association of Cough /Throat Infection/Throat pain/Tonsillitis with climatic factors
Model Linear Model Non-linear Model
Number of obs 145 145
F( 3, 157) 9.64 5.55
Prob > F 0 0
R-squared 0.1703 0.1943
Adj R-squared 0.1526 0.1593
Root MSE 2.9644 2.9526
No of topati Coef. Std. Coef. Std.
dwmaxt -0.1257* 0.1030* 0.1119* 0.5368
dwmaxt2 -0.0076* 0.0107
dwmint 0.1768* 0.0903 0.2310* 0.3256
dwmint2 0.0025* 0.0097
dwpcp 0.0937* 0.0390 -0.1068* 0.1112
dwpcp2 0.0044* 0.0023
Con Coef. 4.2469 1.5202 2.1493* 5.2549
Source: Authors’ estimation; Note: *, **, and *** indicate the parameter is statistically significant at the 1%, 5%
and 10% significance level respectively.
Table 7: Association of Dehydration, Dysentery, and Asthmatic with climatic factors
Model Linear Model Non-linear Model
Number of obs 138 138
F( 3, 157) 0.5 0.39
Prob > F 0.6798 0.8814
R-squared 0.0112 0.0178
Adj R-squared 0.011 0.0272
Root MSE 2.3084 2.3269
No of topati Coef. Std. Coef. Std.
dwmaxt -0.0903* 0.0802 0.0755* 0.4620

6. dwmaxt2 -0.0024* 0.0095
dwmint 0.0614* 0.0694 -0.1597* 0.2542
dwmint2 0.0070* 0.0076
dwpcp -0.0187* 0.0270 -0.0324* 0.0841
dwpcp2 0.0002* 0.0017
Con Coef. 4.3178* 1.2172 3.2190 4.5847
Source: Authors’ estimation; Note: *, **, and *** indicate the parameter is statistically significant at the 1%, 5%
and 10% significance level respectively.