Statistical Analysis of Health Data
Statistical Analysis of Health Data
x = 11, 12, 12, 12, 12, 13, 13, 14, 14, 15 and 15
x
a) ()
Mean x =
n
143
= = 13 cm
11
()
Mean x = 13 cm
𝑛+1 𝑡ℎ
b) Median = ( ) value
2
11 + 1 12
= =
2 2
= 6th value
Median = 13 cm
= 12 cm.
= 15 – 11
Range = 4 cm
(b) Mean Deviation
[Link]. x x 𝑥-xI I𝑥 - x I (𝑥 - x )2
1. 11 13 -2 2 4
2. 12 13 -1 1 1
3. 12 13 -1 1 1
4. 12 13 -1 1 1
5. 12 13 -1 1 1
6. 13 13 0 0 0
7. 13 13 0 0 0
8. 14 13 1 1 1
9. 14 13 1 1 1
10. 15 13 2 2 4
11. 15 13 2 2 4
TOTAL 12 18
Mean Deviation = ∑ I𝑥 - x I / n
= 12 / 11
( x − x)2
c) Standard deviation: =
n −1
18 18
= =
11 − 1 10
= 1.8 =1.34
2. The serum cholesterol levels (in mg/dl) of 10 persons are given below.
260, 200, 240, 260, 150, 220, 190, 210, 240, 240.
Calculate
i. Measures of Central tendency (mean, median, mode)
ii. Measures of Dispersion (range, mean deviation, standard deviation)
x= 150, 190, 200, 210, 220, 240, 240, 240, 260, 260.
x
a) Mean =
n
150 + 190 + 200 + 210 + 220 + 240 + 240 + 240 + 260 + 260
=
10
2210
= = 221
10
()
Mean x = 221 mg/dl
th th
n n
value + + 1 value
Median = 2
2
b)
2
10 10
+ + 1 5th + 6th
= =
2 2
2 2
220 + 240
=
2
= 230
Median = 230 mg/dl
= 260 – 150
S. No. x x 𝑥-x I𝑥 - x I (𝑥 - x )2
1. 150 221 -17 71 5041
2. 190 221 -31 31 961
3. 200 221 -21 21 441
4. 210 221 -11 11 121
5. 220 221 -1 1 1
6. 240 221 19 19 361
7. 240 221 19 19 361
8. 240 221 19 19 361
9. 260 221 39 39 1521
10. 260 221 39 39 1521
TOTAL 270 10690
Mean Deviation = ∑ I𝑥 - x I / n
= 270 / 10
( x − x)2
c) Standard deviation =
n −1
10690 10690
= =
10 − 1 9
= 1187.7 = 34.46
Answers:
Calculate
8 + 9 + 9 + 9 + 9 + 10 + 11 + 11 + 12 + 12
=
10
100
= = 10
10
Mean = 10 Kg.
th th
n n
value + + 1 value
Median = 2
2
b)
2
th
10
th
10
value + + 1
=
2 2
2
5th + 6th
=
2
9 + 10 19
= = = 9.5 Kg.
2 2
Mode = 9 Kg.
= 12 – 8
Range = 4 Kg
S. No. x x 𝑥-x I𝑥 - x I (𝑥 - x )2
1. 8 10 -2 2 4
2. 9 10 -1 1 1
3. 9 10 -1 1 1
4. 9 10 -1 1 1
5. 9 10 -1 1 1
6. 10 10 0 0 0
7. 11 10 1 1 1
8. 11 10 1 1 1
9. 12 10 2 2 4
10. 12 10 2 2 4
TOTAL 12 18
Mean Deviation = ∑ I𝑥 - x I / n
= 12 / 10
( x − x)2
c) Standard deviation =
n −1
18 18
= = = 2
10 − 1 9
Answers:
a) Mean = 10 Kg
b) Median = 9.5 Kg
c) Mode = 9 Kg
d) Range = 4 Kg
e) Mean Deviation = 1.2 Kg
f) Standard deviation = 1.414 kg
ANALYTICAL STATISTICS
4. A study was conducted to know the effects of forceps delivery on the development of
mental retardation. The obstetric records of 100 normal and 50 mentally retarded
children were and analyzed. It was found that outlet forceps was applied on 4 of
normal and 10 mentally retarded groups.
aXd
b) Odd’s Ratio =
bXc
ad 10 X 96
Odd’s ratio = =
bc 4 x 40
Odd’s ratio = 6
a
c) Exposure Rate among cases = a+c x 100
10
= x 100= 20 percent
50
5) 2000 smokers and 4000 non smokers were followed for 10 years. 65 smokers & 20 non-
smokers developed CHD. Find out casual association of smoking with CHD. Comment of results
obtained by you.
a) Cohort study
a) Incidence:
a
Smokers = a+b x 1000
65
= x 1000
2000
c
Incidence among non - smokers = c+d x 1000
20
= 4000 x 1000
= 5 per 1000
a
a+b
b) Relative Risk = c
C+d
32.5
= = 6.5
5
a c
−
a+b c+d
c) Attributable risk = a x 100
a+b
32.5−5
= x 100
32.5
= 0.8461 x 100
= 84.61%
INFERENTIAL STATISTICS
6. 300 surgeries were carried under local and general anesthesia. The number of success
and failures of surgeries are tabulated below. Test whether there is any statistically
significant difference between the two anesthesia in terms of success rates.
ANSWER:
Null Hypothesis: There is no difference in the success rates between local and general
anaesthesia
Expected Frequency (E): = (Column Total x Row Total) / Ground Total (N)
O E
Total [∑ (O – E) ² / E] 12.22
Find Table value: For df of 1, the table value for χ² is 3.841 at p<0.05
Comparing the calculated χ² value with table values, we find 12.22 > 3.841
Conclusion:
Since the calculated χ² value is > the table value, we REJECT the Null hypothesis
Hence there is a statistically significant difference in the success rates between surgeries done
under general anaesthesia and local anaesthesia
7. In a health survey of school children it is found that the mean haemoglobin level of 55
boys is 10.2g/dL with a SD is 2.1. Can we consider this group as taken from a
population with mean of 11.0g/dL?
Null Hypothesis: There is no difference between the sample mean and population mean
= 2.1 / √ 55
= 2.1 / 7.42
SE = 0.28
Z = |µ - x| / SE
= 11 - 10.2 / 0.28
= 0.8 / 0.28
Z = 2.86
Comparing the calculated Z value with table values, we find 2.83 > 1.96
Conclusion:
Since the calculated Z value is > the table value, we REJECT the Null Hypothesis
The observed difference between the sample mean and the population mean is statistically
significant with P< 0.05. Since the sample mean is significantly different from the population
mean, the sample is unlikely to have been drawn from the same universe
[Link] mean weight gain among 10 patients is 4 kg and SD is 3.33 kg. The mean weight
gain among the population is 8 kg. Find whether the difference in the weight gain is
statistically significant.
ANSWER:
There is no difference between the mean weight gain among population and patient group
(b) Given:
(c) Formula:
SE = 1.05
= |µ - x| / SE
= 4 - 8 / 1.05
t = 3.81
(e) Compare calculated t value with table value at the given d.f
For 9 d.f, table value of t is 2.262 (at p < 0.05) and the calculated t value is 3.81
3.81 > 2.262 →calculated value > table value → REJECT null hypothesis
EPIDEMIOLOGICAL EXERCISES
Population = 32165
Calculate annual blood smear examination rate, annual parasite incidence, annual
falciparum incidence, slide positivity rate, slide falciparum rate. Comment on the API and
enumerate the control measures.
𝑁𝑜. 𝑜𝑓 𝑠𝑙𝑖𝑑𝑒 𝑒𝑥𝑎𝑚𝑖𝑛𝑒𝑑
a) Annual blood smear = x 100
𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛
Examination Rate
2500
= x 100 = 7.77
32165
ABER = 7.77%
Answers:
a) Annual blood smear examination = 7.77%
b) Annual Parasite incidence = 2.30 / 1000 population per year
c) Annual falciparum Incidence = 0.466/1000 population per year
d) Slide positivity rate = 2.96%
e) Slide falciparum rate = 0.6%
API of the PHC is 2.3/1000 per year, which can be stratified as Category 3 and hence
needs Intensified control measures as per National Framework for Malaria Elimination in
India (2016-30) which includes:
• Massive scaling up of existing disease management and preventive approaches
and tools
• Screening of all fever cases suspected of malaria
• Classify areas as per risk of transmission and implement tailored interventions
• Strengthening intersectoral collaboration
• Timely referral and treatment of severe malaria cases to reduce mortality
• One stop centres or Mobile clinics on fixed days in tribal areas
• Establishment of robust supply chain management system
• Maintenance of optimum level of surveillance
10. See the results of a filarial survey done in a PHC in the population of 45,000.
❖ Population examined = 3700
❖ Positive for M.F alone (without symptoms) = 300
❖ Patients with clinical symptoms only without mf = 400
❖ Patients with both clinical symptoms and mf positive = 100
Calculate MFR, FDR, FER and comment on the size of population surveyed.
MFR = 10.81%
400+100
= x 100
3700
500
=
37
FDR = 13.5%
400+100+300
= x 100
3700
800
=
37
FER = 21.6%
d) ABER = population examined x 100
total population
3700
= x 100
45000
ABER = 8.22 %
Sample size:
Answers:
a) Microfilaria rate = 10.81%
b) Filarial disease rate = 13.5%
c) Filarial endemicity rate = 21.6%
d) Size of the population surveyed is adequate and acceptable.
11. In a population of 20,000 there was 200 cases of TB on Jan 1st 2019. There were 100
new cases of TB during that year. 10 died due to TB, 15 were cured and 5 of them
migrated to other community. The crude death rate for this community was 8 per
1000 population. Calculate.
a) Period prevalence for 2019
b) Point prevalence on dec 31st 2019
c) Incidence in 2019
d) Case fatality rate.
e) Proportional mortality rate.
270
= x 1000
20,000
= 13.5 per 1000 population.
= 5/ 1000 population.
d) Case fatality rate = Total No. of deaths
due to disease
No. of cases in x 100
same disease
10
= x 100
300
= 3.33%
𝒳
8 = x 1000
20,000
𝒳 = 8x 20 = 160
10
Proportional mortality rate = x 100
160
= 6.25%
Answer:
a) Period prevalence = 15 / 1000 Population
b) Point prevalence = 13.5/ 1000 Population
c) Incidence = 5/ 1000 population
d) Case fatality rate = 3.33%
e) Proportional mortality rate = 6.25%
12. A morbidity survey was conducted in subcentre of PHC to know the extent of TB in
this centre in the year 2019.
Total population = 8000
Total TB cases on Jan 2019 = 70
No. of new TB cases during 2019 - 60
No. of TB cases cured in 2019 = 90
Calculate Incidence, point prevalence of TB on January 2019, cure rate of TB.
60
= x 1000
8000
= 7.5 / 1000 population
c) Cure rate of TB
(survival rate) = Total No. of patients
alive after 5 years
Total No. of patients x 100
disease / treated
90
= x 100
70+60
90
= x 100
130
=69.23%
Answers:
13. A city has recorded 20,000 live births in the year 2019. 200 die within 28 days of
birth. 90 died before 1 year of age. 12 Mother died due to pregnancy causes.
Calculate all possible vital indices from the above data.
12
= x 100000
20,000
90+200
= X 1000
20,000
IMR = 14.5 / 1000 live births
200
= X 1000
20,000
90
= X 1000
20,000
PNMR = 4.5 / 1000 live births.
Answers:
a) MMR = 60/100000 live births
b) IMR = 14.5/1000 live births
c) NMR = 10/1000 live births
d) PNMR = 4.5/1000 live births
[Link] population of Chennai as per 1st march 2001 was 62,20,000 and as per 1st march
2011 was 94,21,000. Calculate the midyear population for 2016.
𝑃2 − 𝑃1 4
PIC (MYP) = P2 + ( ) x (𝑑 + 12 )
𝑛
= 94,21,000+ (9421000−6220000
4
) X (5 + )
10 12
32,01,000
= 94,21,000+ ( ) (5+10.3)
10
= 94,21,000+ 1707200
= 11,128,200
15) In a town with a mid year population of 1,00,000 there were 2000 births and 38 infant
deaths in year 2016. Of these 26 infants died in first 28 days of life and of them 15 died in
1st week of life. There were 30 still births in same year calculate all possible vital indices
for the data given and Write 2 causes for each of the following.
38
= X 1000
2000
IMR = 19/1000 live births.
26
= x 1000
2000
NMR = 13/1000 live births.
= 15/2000X1000
ENMR= 7.5/1000 live births
30 30
= x 1000 = x 1000
2000+30 2030
SBR = 14.77 / 1000 births
Causes:
Infant mortality Rate - Anemia, low birth weight
Perinatal mortality Rate - Preterm birth & Respiratory distress syndrome
Neonatal Mortality - Birth defects, preterm birth
Answers:
a) IMR - 19/ 1000 Live births
b) PMR – 22.17 / 1000 births
c) PNMR - 6/ 1000 Live births
d) NMR -13/ 1000 Live births
e) ENMR- 7.5/1000 live births
f) CBR =20 /1000 Population
g) SBR = 14.77 / 1000 births
16) A town has midyear population of 40,000 in 2011. During the year, 550 live births
and 340 Deaths. Calculate the possible vital indices.
No. of live births during a year
a) Crude birth Rate = x 1000
Midyear population
550
= x 1000
40,000
= 13.5/1000 Population.
No. of deaths
during a year
b) Crude death Rate = x 1000
Midyear population
340
= x 1000
40,000
= 8.5/1000 Population.
13.5−8.5 20
= x 100 =
1000 10
= 0.525%.
Answers:
a) CBR = 13.5 / 1000 Population
b) CDR = 8.5 / 1000 Population
c) Growth Rate – 0.525%
17) In a town with midyear population of 3 lakhs there were 6050 live births, 110 still
births, 121 deaths in 1st year of life,; of these 80 deaths occurred in 1st month of life and
52 deaths within 1 week after birth .Calculate possible vital indices for the given data and
Write 2 causes for each of the following
110 110
= x 1000 = x 1000
6050+110 6160
SBR = 17.85 / 1000 births
110+52
= x 1000
6050+110
162
= x 1000 = 26.3
6160
PMR = 26.3 / 1000 Births
80
= x 1000
6050
NMR = 13.22/1000 live births.
= 52/6050X1000
ENMR= 8.6/1000 live births
Answers:
a) Still birth Rate = 17.85 / 1000 Births
b) PMR = 26.3 / 1000 Births
c) IMR = 20 / 1000 live births
d) PNMR = 6.78/1000 live births.
e) NMR = 13.22/1000 live births.
f) ENMR= 8.6/1000 live births
g) CBR =20.17 /1000 Population.
Causes:
Infant mortality Rate - Anemia, low birth weight
Perinatal mortality Rate - Preterm birth & Respiratory distress syndrome
Neonatal Mortality - Birth defects, preterm birth
18) India’s 2001 census population was 846 million. 2011 census population was 1020
million calculate the population and midyear population of India for 2007.
174
= 846 + ( )x6
10
= 846 + 17.4 x6
= 846 + 104.4
= 950.4
Population of India in 2007 is 950.4 million
𝑃2 − 𝑃1
PIC = P1 + ( ) x (𝑑 + 124 )
𝑛
1020−846 4
PIC = 846 + ( ) x 6+
10 12
174
= 846 + ( ) x 6+ 0.3
10
= 846 + 17.4 x 6.33
= 956. 142.
in a year
x 1000
Mid year population
600
= x 1000
30,000
Birth Rate = 20 / 1000 Population
b) Death Rate = No. of deaths during
a year
x 1000
Mid year population
300
= x 1000
30,000
Death Rate = 10 / 1000 Population
No. of infant deaths
c) Infant Mortality Rate = x 1000
Total [Link] live births
13
= x 1000
600
IMR = 21.6 / 1000 Live births
Answers:
a) Birth Rate = 20 / 1000 Population
b) Death Rate = 10 / 1000 Population
c) IMR = 21.6 / 1000 Live births
d) MMR = 35 / 1000 Live births
ENVIRONMENT
20. The diameter of a circular well = 1m
Depth of water column in well = 5m
While doing the Horrock’s test the blue colour appeared from 2 nd cup onwards.
Estimate.
a) The volume of water in the well
b) The quantity of bleaching powder required for chlorinating the
above well.
c) Write the steps of Chlorination.
Solution:
Diameter = 1m
Radius, r = 0.5m
Depth of water column, h = 5m
Volume = 𝜋𝑟 2 ℎ
= 3.14 x 0.5 x 0.5 x5
= 3.925m3
1𝑐𝑢. 𝑚 = 1000 L
= 3.925 x 1000
Volume = 3925 L
Blue colour appears on the 2nd cup in Horrock’s test.
1 cup = 2gms.
4 gms = 455 ℓ
3925
For 3925 ℓ = x4
455
= 34.5 gms.
Answer:
a) Volume of water in well = 3925 ℓ
b) Amount of bleaching powder required for chlorinating = 34.5gms.
c) Steps of chlorination
21) Calculate the amount of bleaching powder required to chlorinate a square well of
sides 2m and depth 3m. The horrocks test showed blue color from 2nd cup
onwards. Write the steps of Chlorination of well.
Volume of square well = 𝑎2 ℎ
=2x2x3
= 12cu.m
1 cu.m = 1000 ℓ
= 12 x 1000
= 12000 ℓ
Blue colour appears on the 2nd cup onwards in horrock’s test.
1 cup = 2gms
4gms = 455 ℓ
12000
For 12,000 ℓ = x4
455
= 105.4gms.
Answer:
a) Volume of square well = 12000 ℓ
b) Quantity of bleaching powder required for chlorinating = 105.4gms.
c) Steps of chlorination
i)Dissolve the Calculated Amount of Bleaching Powder in Water
The calculated amount is drawn and placed in a bucket .Make it into a thin paste. Add more
water till the bucket is nearly ¾ full. The contents are stirred well. Allow to sediment for 5 –
10 min. Lime settles down. The supernatant solution is the chlorine solution. This
supernatant chlorine solution is transferred to another bucket. The chalk or lime which
settles at the bottom is discarded DO NOT POUR the SEDIMENT into the well, this is lime
which will increase the hardness of water.
ii) Delivery of the Chlorine Solution into the Well
The bucket containing the chlorine solution is lowered some distance below the water
surface. Then the well water is agitated by moving the bucket violently vertically and
laterally. This is repeated several times to ensure thorough mixing of the chlorine solution
into all of the well water
iii) Allow a Contact Period between the Chlorine and Water
Contact period of one hour is allowed before anyone is permitted to draw water from the
well
iV) Perform Orthotolidine Arsenite (OTA)Test
Orthotolidine Arsenite Test is then performed at the end of one hour contact period. This is
done to check the level of free residual chlorine
If the free residual chlorine is < 0.5 mg/L, the entire procedure is repeated before any water
is drawn
22) Calculate the amount of bleaching powder required for disinfecting a well with a
diameter 3m and depth 15m. Horrock’s test shows blue colour on 3rd cup. Write
the steps of Chlorination of well.
1 cup = 2gms
6gms = 455 ℓ
105 975
For 105 975 ℓ = x6
455
= 1397.4gms.
Answer:
23. Calculate the amount of bleaching powder required to disinfect a circular well of
diameter 6m and depth 12m. Horrock’s test shows blue colour on 4 th cup onwards.
Write the steps of Chlorination of well.
Diameter of well = 6m
Radius (r) = 3m
Depth, h = 12m
Volume = 𝜋𝑟 2 h
= 3.14 x 3 x 3 x 6
= 3.14 x 9 x 6
= 339.12 cum.
1 cum = 1000 ℓ
= 339.12 x 1000
= 339120 ℓ
1 cup = 2gms
8gms = 455 ℓ
339120
For 339120 ℓ = x8
455
= 5962.54gm
= 5.9 Kg.
Answer:
SCREENING TESTS
24) The screening (widal test) conducted and the results are follows.
Out of 200 diseased typhoid patient test was positive in 180 and negative in 20. In
contrast out of 200 non diseased test was +ve in 60 and negative in 140. To the given data
set up a 2 x 2 contingency table. Calculate the screening parameters.
a
a) Sensitivity = a+c x 100
180
= 200 x 100
= 90%
d
b)Specificity = b+d x 100
= 140 / 200 x 100
= 70%
a
c) +ve predictive value = (a+b) x 100
180
= 240 x 100
= 75%
d
d) -ve predictive value = (c+d) x 100
140
= 160 x 100
= 87.5%
Answers:
a) Sensitivity = 90%
b) Specificity - 70%
c) Positive predictive value - 75%
d) Negative predictive value - 87.5%
25) 1000 people were screened for TB in PHC. Sputum +ve for AFB in 140 persons.
Mass miniature radiography shows 60 as positive. Both MMR and sputum for AFB
showed negative in 848 persons. Calculate various screening parameters.
48
= 140 x 100
= 34.2%
d
b) Specificity = b+d x 100
848
= x 100 = 98.6%
860
a
c) Positive predictive value = a+b x100
848
= 940 x 100
= 90.2%
Answers:
a) Sensitivity - 34.2%
b) Specificity - 98.6%
c) Positive predictive value - 80%
d) Negative predictive value - 90.2%
26) A new screening test for disease with a prevalence of 16% and was positive in 20%
of 600 population. There were 12 False negative. Calculate the screening parameters.
16
For 600 population = x 600
100
= 96.
20
Screening test +ve in 20% = 100 x 600
= 120
a
a) Sensitivity = a+c x 100
84
= 96 x 100
= 87.5%
d
b) Specificity = b+d x 100
468
= 504 x 100
= 92.8 %
a
c) Positive predictive value = a +b x 100
84
= 120 x 100
= 70%
d
d) Negative predictive value = c+d x 100
468
= 480 x 100
= 97.5%
Answers:
a) Sensitivity = 87.5%
b) Specificity = 92.8%
c) Positive predictive value = 70%
d) Negative predictive value = 97.5%
NUTRITION
27. Sita is a house wife and her weight is 50Kg and does moderate work. Calculate her
daily nutritional requirement for energy & protein.
= 2400 x 0.9
= 2160 kcal
= 2510 k cal.
= 2760 Kcal.
28) Calculate the energy & protein requirement of a child 7 years old weighing 20Kg.
Suggest a diet to meet the requirements. Mention some sources of carbohydrates
and protein to improve the diet.
Protein requirement = 1 g/ kg
1680 x 10
=
100
In a balanced diet
Protein = 10 - 15%
Fat = 20%
Carbohydrate = 65 - 70%
1680 x 70
= = 1176 kcal = 1176/4 = 294 g
100
1680 x 20
= = 336 kcal = 336/9 = 37.3 g
100
294 g Carbohydrates
37.3 g fats
Prescribed diet:
Chutney 2 stspn. = 20
Banana (1) = 90