Fundamental of Biostatics

1. DEPARTMENT OF PUBLIC
HEALTH DENTISTRY
NAVODAYA DENTAL COOLLEGE
DR.SOMANATH REDDY .K
INTRODUCTION TO
BIOSTATISTICS

2. WHEN YOU CAN MEASURE WHAT YOU ARE
SPEAKING AND EXPRESS IT IN NUMBERS, YOU
KNOW SOMETHING ABOUT IT;
BUT WHEN YOU
CANNOT EXPRESS IT IN NUMBERS, YOUR
KNOWLEDGE IS OF A MEAGRE AND
UNSATISFACTORY KIND.
- LORD KELVIN

3. WHAT DO
STATISTICS
MEAN ?

4. What do statistics mean..
To a stock broker?

5. What do statistics mean..
To a Twitter buff?

6. What do statistics mean..
To a Dieting buff?

7. What do statistics mean..
Size Zero?

8. Moral of the story..
Love them or hate them,
stats are here to stay!

9. STATISTICS
ITALIAN : STATISTA = STATESMAN
GERMAN : STATISTIK = POLITICAL STATE
‘STATISTIC’ OR ‘DATUM’ - MEASURED
OR COUNTED FACT OR PIECE OF
INFORMATION STATED AS FIGURE.
‘STATISTICS’ OR ‘DATA’ – PLURAL FORM

10. FATHER OF HEALTH STATISTICS
JOHN GRAUNT

11. Getting the Definitions Right!
STATISTICS: PRINCIPLES AND METHODS FOR
COLLECTION, PRESENTATION,ANALYSIS AND
INTERPRETATION OF DATA.
BIOSTATISTICS: TOOLS OF STATISTICS APPLIED
TO THE DATA THAT IS DERIVED FROM BIOLOGICAL
SCIENCES.

12. BIOSTATISTICS
SCIENCE OF
VARIATION
SCIENCE OF
FIGURES

13. EPIDEMIOLOGY BIOSTATISTICS
FACTS FIGURES FACTS

14. TO DEFINE NORMALCY.
TO TEST THE DIFFERENCE BETWEEN
MEANS AND PROPORTIONS BETWEEN
POPULATIONS.
TO STUDY THE CORRELATION OR
ASSOCIATION BETWEEN TWO OR MORE
ATTRIBUTES.
WHY DO WE NEED
STATISTICS ?

15. LOCATE ,DEFINE AND
MEASURE EXTENT OF
DISEASE
TO EVALUATE THE EFFICACY OF
DRUGS.
EVALUATE HEALTH PROGRAMS.
WHY DO WE NEED
STATISTICS ?

16. TO DETERMINE SUCCESS OR
FAILURE OF ORAL HEALTH
CARE PROGRAMS.
PLANNING AND
ADMINISTRATION OF ORAL
HEALTH CARE SERVICES.
PREDICTING TRENDS OF
DENTAL DISEASES.
TO ASSESS ORAL HEALTH
STATUS OF POPULATION.
APPLICATIONS OF
BIOSTATISTICS IN
DENTISTRY

17. TO UNDERSTAND THE ASSOCIATION BETWEEN
CAUSE AND EFFECT IN ORAL DISEASES.
SMOKING LEUKOPLAKIA
STRENGTH
DIRECTION

18. TO ASSESS THE EFFICACY OF VARIOUS
TREATMENTS FOR ORAL DISEASES.
PERIODONTITIS

19. HOW DOES BIOSTATISTICS
HELP A POSTGRADUATE
STUDENT ?

20. DATA

21. DATA
COLLECTIVE RECORDING OF OBSERVATIONS.
SOURCES OF DATA
•SURVEYS
• ANALYTICAL STUDIES
•EXPERIMENTS
•RECORDS

22. DEPENDING UPON
SOURCE OF DATA
COLLECTION
PRIMARY DATA
INTERVIEWS,
EXAMINATION,
QUESTIONNAIRES
SECONDARY DATA
RECORDS,
CENSUS DATA
TYPES OF DATA

23. DATA
QUALITATIVE DATA
(DISCRETE /FREQUENCY
DATA)
Subjects with same
characteristics are counted to
form specific groups.
Eg. Gingivitis, Malocclusion etc
QUANTITATIVE DATA
(CONTINOUS DATA)
They have magnitude .
Eg. Missing teeth, crown length

24. SCALES OF DATA MEASUREMENT

25. SCALES OF DATA
MEASUREMENT
CATEGORICAL
NOMINAL SCALE
ORDINAL SCALE
NON
CATEGORICAL
INTERVAL SCALE
RATIO SCALE

26.  This scale uses names or tags to
distinguish one measurement from
another.
 It does not imply magnitude of
individual measurements.
Eg. Classification of sex
Classification of religion
NOMINAL SCALE

27. BINARY (DICHOTOMOUS) SCALE
EDENTULOUS :Yes/No
MALOCCLUSION: Present / Absent
SEX : Male/Female

28. It is like nominal scale but there exists an implicit graded
order relationship among the categories.
Eg. Pain measured as:
Mild – 1
Moderate – 2
Severe – 3
ORDINAL SCALE

29. A numerical unit of measurement is used in this scale.
The difference between any 2 measurements can be clearly
identified in terms of an interval between 2points of scale.
This scale has no true zero point.
Eg. Measurement of body temperature in Fahrenheit.
INTERVAL SCALE

30. RATIO SCALE
It is as same as interval scale
in every aspect except that
measurement begins at a true
or absolute zero.
Eg. Weight in Kgs,
Height in Mts.
There cannot be negative
measurements.

31. PRESENTATION OF DATA

32. METHODS OF DATA
PRESENTATION
TABULATION DIAGRAMS

33. ELEMENTS OF
CLASSIFICATION
VARIABLE
A CHARACTERISTIC THAT
TAKES DIFFERENT VALUES
IN DIFFERENT PERSON.
FREQUENCY
NUMBER OF UNITS
BELONGING TO EACH
VARIABLE.

34. TYPES OF
TABLES
SIMPLE TABLE MASTER TABLE
FREQUENCY
DISTRIBUTION
TABLE
TABULATION

35. SIMPLE TABLE
DMFT REGIONS AVERAGE DMFT
DAVANAGERE 3
BELGAUM 2
MYSORE 4
HUBLI 3
BANGALORE 4
CHITRADURGA 2
TABLE SHOWING AVERAGE CARIES EXPERIENCE (DMFT) IN
SIX DISTRICTS OF KARNATAKA.

36. SL.NO AGE
(YRS)
SEX EDUCATION DECAYED MISSING FILLED
1 22 MALE BA 2 0 1
2 23 FEMALE BBM 1 1 0
3 24 FEMALE BSC 6 2 0
4 25 MALE BE 3 1 2
MASTER TABLE
TABLE 1 : SHOWING DECAYED ,MISSING AND FILLED TEETH AMONG FOUR
DEGREE STUDENTS

37. INTERVAL (DMFT LEVEL) FREQUENCY
1-3 3
4-6 2
7-9 4
10-12 3
13-15 3
FREQUENCY DISTRIBUTION TABLE
TABLE SHOWING CARIES EXPERIENCE (DMFT LEVELS)
OF 15 STUDY SUBJECTS
CLASS INTERVAL – 2 DMFT

38. GRAPHS AND DIAGRAMS
• IMPACT ON IMAGINATION
• BETTER RETAINED IN MEMORY
• EASY COMPARISONS

39. SIMPLE BAR GRAPH
Graph showing the mean number of missing
teeth among 45 – 60 years old study subjects.

40. MULTIPLE BAR GRAPH
Bar graph showing the mean number of missing
teeth among 45 – 60 years old study subjects.
Mean
number of
Missing
teeth

41. COMPONENT BAR GRAPH
0
500
1000
1500
2000
2500
3000
3500
4000
4500
Endodontics
Pedodontics
Periodontics
January April September
Component bar graph showing the number of patients visiting three
departments in a dental college.
Number of
patients

42. 8 9 10 11 12 13 14 15 16 17
5
10
15
20
25
30
35
40
45
Number
Of
Students
Hemoglobin in gram %
Hemoglobin levels of Students in a class.
HISTOGRAM

43. FREQUENCY POLYGON
MARKS OBTAINED BY STUDENTS IN A TEST.

44. STEM AND LEAF DIAGRAM
15, 18, 26, 24, 54, 56, 59, 64, 66, 68,
69, 34, 36, 71, 73, 77, 78, 79, 45, 47,
48, 83, 87, 98, 92
MARKS SCORED BY 25 BDS FINAL YEAR STUDENTS
IN EXAM (TOTAL MARKS = 100 )

45. INTERVAL STEM LEAVES
10 - 19 1 5 8
20 - 39 2 4 6
30 - 39 3 4 6
40 - 49 4 5 7 8
50 - 59 5 4 6 9
60 - 69 6 4 6 8 9
70 - 79 7 1 3 7 8 9
80 - 89 8 3 7
90 - 99 9 2 8
STEM AND LEAF DIAGRAM

46. LINE DIAGRAM

47. LINE GRAPH

48. SCATTER PLOT
DEGREE OF
FLUOROSIS
FLUORIDE LEVEL IN WATER

49. PIE DIAGRAM
65%
15%
12%
8%
Angle's Class I
Angle's Class II
Angle's Class III
Angle's Class IV
Pie diagram showing the distribution of types of
malocclusion among 15 year old school children.

50. MAP
CHART

51. PICTOGRAM
Pictogram showing the percentage( % ) of mobile network
users in Belgaum city.
VODAFONE USERS
AIRTEL USERS
DOCOMO USERS
OTHERS
= 10 %

52. BOX AND WHISKER PLOT

53. BOX WHISKER PLOT
Q1
MEDIAN
Q2 Q3 QUARTILES
CENTILES

54. BOX WHISKER
PLOT
(5-NUMBER SUMMARY)
Highest value
Upper quartile (Q1)
Median(Q2)
Lower Quartile (Q3)
Lowest value

55. CONSTRUCTING A BOX WHISKER PLOT
Example: The following set of numbers are the amount of
marbles fifteen different boys own.
18, 27, 34, 52, 54, 59, 61, 68, 78, 82, 85, 87, 91, 93, 100 .
• First find the median. *68 is the median
• Find the lower quartile *52 is lower quartile
• Find the upper quartile * 87 is upper quartile
• Inter quartile range is * 87-52= 35

56. FOREST PLOT ( BLOBBOGRAM)
It is a graphical display designed to illustrate
the relative strength of treatment effects in
multiple quantitative scientific studies which
are used to address the same question.
Used mainly to represent meta
analysis of the results of randomized
controlled trails.

57. FOREST PLOT
weights used in
meta-analysis),
summary
measure (centre
line of diamond)
and associated
confidence
intervals (lateral
tips of diamond),

58. FUNNEL PLOT
• It is a useful adjunct to meta analysis.
• Funnel plot is a scatter plot of treatment
effect against a measure of study size.
• Used to detect bias or systematic
heterogeneity.

59. FUNNEL PLOT
SYMMETRIC
PUBLICATION BIAS
UNLIKELY.
ASYMMETRIC
PUBLICATION BIAS
SMALL STUDY EFFECTS
INAPPROPRIATE EFFECT MEASURE

60. TYPES OF STATISTICS

61. DESCRIPTIVE STATISTICS:
METHODS OF PRODUCING
QUANTITATIVE SUMMARIES OF
INFORMATION.
INFERENTIAL STATISTICS:
METHODS OF MAKING
GENERALIZATIONS ABOUT A LARGER
GROUP BASED ON INFORMATION
ABOUT A SUBSET (SAMPLE) OF THAT
GROUP.

62. MEASURES OF CENTRAL TENDENCY

63. CENTRAL TENDENCY
GENERAL TENDENCY FOR THE OBSERVATIONS
FROM A SAMPLE TO CLUSTER AROUND A
CENTRAL VALUE.
OBJECTIVES:
TO CONDENSE THE ENTIRE MASS OF DATA.
TO FACILITATE COMPARISION.

64. MEAN : ARITHMETIC AVERAGE
MEAN=
SUM OF ALL OBSERVATIONS
TOTAL NUMBER OF OBSERVATIONS
e.g. DMFT OF 5 CHILDREN IS 2, 3, 4, 1, 5
MEAN DMFT (x) =
2+3+4+1+5
5
= 3

65. Example
If the number of decayed teeth in 5 children
are as follows 2,3,1,2,9.
Mean is 3.2
One value 9 has increased the mean number
considerably.

66. MEDIAN
ARRANGE ALL THE OBSERVATIONS IN
ASCENDING OR DESCENDING ORDER.
THE MIDDLE OBSERVATION IS THE MEDIAN
e.g. DMFT OF 5 CHILDREN ARE 2, 3, 4, 1, 5
ARRANGE IN ORDER : 1,2,3,4,5
MEDIAN IS 3
e.g. DMFT OF 6 CHILDREN ARE 2,3,1,4,6,5
ARRANGE IN ORDER : 1,2,3,4,5,6
MEDIAN IS 3+4
2
= 3.5

67. MODE
THE MOST FREQUENTLY OCCURING
OBSERVATION IN A SERIES.
e.g. DMFT OF 6 CHILDREN ARE 2, 3, 4, 2,1,2
MODE IS 2

68. EXAMPLE
GROUP 1 : 8, 9, 10,11, 12
GROUP 2 : 10, 10, 10, 10, 10
GROUP 3 : 1, 5, 10,15,19
Mean is 10, Median is 10
What other characteristic besides
central tendency would it seem
necessary to describe it ?

69. MEASURES OF DISPERSION

70. RANGE
• THE DIFFERENCE BETWEEN THE LARGEST AND
SMALLEST VALUES IN A DISTRIBUTION.
• EXAMPLE: 1, 2, 2, 2, 3, 4, 5, 6, 7, 8
• RANGE = 8-1 = 7

71. STANDARD DEVIATION
MEASURE OF DISPERSION (OR SCATTER) OF
THE VALUES ABOUT THE MEAN.
IF THE NUMBERS ARE NEAR THE MEAN,VARIANCE IS SMALL.
IF NUMBERS ARE FAR FROM THE MEAN,THE VARIANCE IS
LARGE.
Standard deviation of a sample, S = standard deviation of population

72. DISTRIBUTION
OF
OBSERVATIONS

73. NORMAL CURVE
[GAUSSIAN CURVE]

74. BELL SHAPED CURVE
(NORMAL CURVE)

75. 140 145 150 155 160 165 170
HEIGHT OF STUDENTS IN CLASS (CMS)

76. PROPERTIES OF NORMAL CURVE
 BELL SHAPED AND SYMMETRICAL ABOUT THE MID POINT.
 MEAN, MEDIAN AND MODE COINCIDE.
 MAXIMUM NUMBER OF OBSERVATIONS ARE AT VALUE
CORRESPONDING TO THE MEAN AND OBSERVATIONS
GRADUALLY DECREASE ON EITHER SIDES.

77. MEAN ± 1 SD COVERS
68.3% OF
OBSERVATIONS
MEAN ± 2 SD COVERS
95.4% OF
OBSERVATIONS
MEAN ± 3 SD COVERS
99.7% OF
OBSERVATIONS

78. STANDARD NORMAL CURVE
In statistics , the standard deviation is used
as an unit. A statement like "the root length
of two people differ by few centimeters" is
of little value to a statistician. A statistician
would like to know how many standard
deviation apart are the root lengths of these
people.

79. EXAMPLE
A TEST WAS CONDUCTED AMONG POSTGRADUATE
STUDENTS OF 2 DENTAL COLLEGES IN THE
SUBJECT OF BIOSTATISTICS
TEST SCORE MEAN SCORE STANDARD
DEVIATION
STUDENT A
(COLLEGE 1 )
35 20 10
STUDENT B
(COLLEGE 2 )
33 25 8

80. NORMAL CURVE
STANDARD NORMAL
CURVE

81. STANDARD NORMAL CURVE
THEOREM
• If X is a variable with mean μ and standard deviation
σ, then Z = (X-μ)/σ is also a normal random variable
with mean ZERO and standard deviation ONE. This Z
is called the standard normal variable. The process of
converting X to Z is called the standardization of X.
CURVE OF X – NORMAL CURVE
CURVE OF Z – STANDARD NORMAL CURVE

82. STANDARD NORMAL
CURVE
TOTAL AREA IS 1
MEAN IS 0, STANDARD DEVIATION IS 1
MEAN,MEDIAN AND MODE COINCIDE
 NEVER TOUCHES THE BASELINE

83. EXAMPLE
A TEST WAS CONDUCTED AMONG POSTGRADUATE
STUDENTS OF 2 DENTAL COLLEGES IN THE
SUBJECT OF BIOSTATISTICS
TEST SCORE MEAN SCORE STANDARD
DEVIATION
STUDENT A
(COLLEGE 1 )
35 20 10
STUDENT B
(COLLEGE 2 )
33 25 8

84. CALCULATION OF Z SCORE
35 - 20
Z SCORE OF STUDENT A = = 1.5
10
33 – 25
Z SCORE OF STUDENT B = = 1
8
Score(X) – Mean
Z =
Standard Deviation

85. SKEWNESS

86. STATISTICS IS
THE FUNDAMENTAL
SCIENCE TO RESEARCH.

87. “HE WHO ACCEPTS STATISTICS
INDISCRIMINATELY, WILL OFTEN BE
DUPED UNNECESSARILY.
BUT HE WHO DISTRUSTS
STATISTICS, INDISCRIMINATELY WILL
OFTEN BE IGNORANT, UNNECESSARILY”.
- WA WALLIS AND HV ROBERTS

88. The Road To Success
is always under
construction..
So keep striving but
don’t forget the
stats!

89. THANK YOU