MEAN, MEDIAN ,

MODE AND
STANDARD
DEVIATION
DR.TANU SHREYA
1ST YEAR MDS
1

DEPARTMENT OF PROSTHODONTICS AND CROWN &BRIDGE

CONTENTS
 Introduction
 Descriptive statistics
 Tests of significance
 Parametric test
 Non Parametric test
 Application of tests in dental research
 Conclusion

2
 INTRODUCTION
JOHN GRAUNT(1620-1674) is the father of health statistics.
Normal BP – 120/80 mm Hg
Europeans are taller than Asians
Average male adult weighs 70kgs
Drug A is better than drug B
- Endless
 Cannot be arrived by just Raw data .
 Numbers tell tales – Speak the language of STATISTICS – Adds meaning to
data – helps to interpret data.
Thus lending “significance” to the study. 3
DESCRIPTIVE STATISTICS
 STATISTICS – Is the science of compiling, classifying & tabulating numerical
data and expressing the results in a mathematical or graphical form.
OR
 Statistics is the study of methods & procedures for collecting, classifying,
summarizing & analysing data & for making scientific inferences from such
data.
- Prof P.V.Sukhatme

4
BIOSTATISTICS
 Is the branch of statistics applied to biological or medical sciences
(biometry).
OR
 Is that branch of statistics concerned with mathematical facts and data
relating to biological events.

5
USES OF BIOSTATISTICS
 To test whether the differences between two population is real or a chance
occurrence.
 To study correlation between attributes in the same population.
 To evaluate the efficacy of vaccines, sera.etc.
 To measure mortality and morbidity.
 To evaluate achievements of public health programs.
 To fix priorities in public health programs.
 To help promote health legislation and create administrative standards for oral
health.
6
BASIS OF STATISTICAL
ANALYSIS
1.The population(U)
2. The set of characteristics [variables] of the units of this population(V)
3. The probability distribution(P) of these characteristics in the population.

7
THE POPULATION (U)
 Is a collection of units of observations that are of interest .
 They are the target of investigation.
 The success of an investigation depends largely on identification of population
of interest.

8
VARIABLE

 “A variable is a state, condition, concept, or event whose value is free to vary

within the population.”
 A general term for any feature of the unit which is observed or measured.

 For eg- in case of a particular drug to determine its efficacy, one needs to
define the disease and what other characteristics of the U one intends to
study(-age, sex, educational qualifications, etc)

9
TYPES OF VARIABLES
 QUALITATIVE(CATEGORICAL)
 QUANTITATIVE(NUMERICAL)

CATEGORIAL NUMERICAL

NOMINAL ORDINAL DISCRETE CONTINUOUS

Eg-gender Eg-stage of disease Eg-teeth with caries Eg-weight(kgs)

10
FREQUENCY/ PROBABILITY
DISTRIBUTION(P)
The most crucial link between the population and its characteristics , which allow us to draw
inference on the population based on sample observation.
It is a way of showing the number of observations or frequencies at different values or how
frequently each value appears in a population.

P-value is defined as the probability under the assumption of null hypothesis, of obtaining a
result equal to or more extreme than what was actually observed.

HIGH P-VALUE LOW P-VALUE

0.8,0.6,0.1 indicates high 0.001,0.01,0.05 are low probability
probability to get observed result
11
due to chance. It favours null hypothesis.
MEASURES OF CENTRAL
TENDENCY/ STATISTICAL
AVERAGES
It is the central value around which the other values are distributed.

 Main objective- to condense the entire mass of data and facilitate
comparision

 MOST COMMON MEASURES OF CENTRAL TENDENCY

 1. Arithmetic mean- mathematical estimate
 2. Median- positional estimate
 3. Mode-based on frequency
12
ARITHMETIC MEAN
 It is the simplest measure of central tendency.
 Obtained by adding the individual observations and then dividing by the total
number of observations.

 Formula- ∑ Xi/ n
∑(sigma) is the sum of , Xi is the value of each observation in data, n
is the number of observations in the data.

13
 ADVANTAGES- Easy to calculate and understand
- It is the most useful of all averages.

 Disadvantages- May be unduly influenced by abnormal values.

- Sometimes it might look ridiculous.

14
VARISTIONS OF MEAN
 GEOMETRIC MEAN- nth root of the product
When the variation between the lowest and the highest value is
very high, geometric mean is advised & preferred .

 HARMONIC MEAN- is the reciprocal of the arithmetic mean of the

reciprocal of the observations.
15
MEDIAN
 is the middle value, which divides the observed values into two equal parts.
 when the values are arranged in ascending or descending order, one half of
the units in the distribution have values equal to or less than the median
while the other half has values higher than or equal to the median.
 Median is also the positional average.

 ADVANTAGE- it is not affected by abnormal values.

16
MODE
  is the value of the variable which occurs with the greatest frequency.
 The mode is located from frequency distribution table, taking the value of
the variable with the maximum frequency.

 MODE= 3MEDIAN – 2MEAN

17
MEASURES OF DISPERSION
 Dispersion is the degree of spread or variation of the variable about a central
value.
 They help to know how widely the observations are spread on either side of
the average.

 3 meaures are-
 1.RANGE
 2.MEAN DEVIATION
 3.STANDARD DEVIATION

18
RANGE
 Simplest method.
 Defined as the difference between the value of the largest item and the value of
the smallest item.
 It gives no information about the values that lie between the extreme values.

19
MEAN DEVIATION
 It is the average of the deviations from arithmetic mean.
 It is given by,
M.D.= ∑(X-Xi)
n

20
STANDARD DEVIATION(ROOT
MEAN SQUARE DEVIATION)
 Is the most important and widely used measure of studying
dispersion.
 It is the square root of the mean of the squared deviations from
arithmetic mean.
 Greater the S.D. greater will be the magnitude of dispersion from
mean.
 A small S.D. means higher degree of uniformity of the
observations.

21
22
USES OF SD
 1. Summarizes the deviations of a large distribution from mean in one figure
used as unit of freedom .
 2. Indicates whether the variation from the mean is by chance or real .
 3. Helps finding standard error- which determines whether the difference
between means of two samples is by chance or real .
 4. Helps finding the suitable size of the sample for valid conclusions.

23
THE NORMAL CURVE
 Also known as Normal distribution or Gaussian distribution.
 When data is collected from a very large number of people and a
frequency distribution is made with narrow class intervals, the
resulting is smooth and symmetrical called the normal curve.

24
25
CHARACTERISTICS OF
NORMAL CURVE
 Bell shaped
 Symmetrical
 Mean, Mode & Median – coincide
 Has two inflections – the central part is convex, while at the point of
inflection the curve changes from convexity to concavity.
 Total area of curve -1, mean-0, standard deviation-1.
 IF MEAN > 2S.D., VALUES ARE NORMALLY DISTRIBUTED.

26
VARIATION FROM NORMAL
CURVE
 Skewness – as the static to measure the asymmetry
 coefficient of skewness is 0.
 CURVE CAN BE-
Negatively (left) skewed
Positively (right) skewed

27
28
KURTOSIS
  Kurtosis – is a measure of height of the distribution curve
 Coefficient of kurtosis is 3
 1.Mesokurtic (normal) 2.Platykurtic (flat) 3.Leptokurtic(high)

29
30
TESTS OF SIGNIFICANCE
 A statistical procedure by which one can conclude if the results from the
sample is due to chance or not.
 2 types of tests-

PARAMETRIC TESTS NON PARAMETRIC TESTS

These are applied when sample Applied when data is not
is normally distributed. normally distributed.

31
PROCEDURE OF TESTING
 1.Hypothesis testing
 Hypothesis is an assumption about the status of a phenomenon or is a
statement about the parameters or form of population.
 Null hypothesis or hypothesis of no difference .
 States no difference between statistic of a sample & parameter of population
or between statistics of two samples .
 This nullifies the claim that the experiment result is different from or better
than the one observed already,

32
 2. State Alternate hypothesis –
 Any hypothesis alternate to null hypothesis, which is to be tested
 Note : the alternate hypothesis is accepted when null hypothesis is rejected.

 3. Selection of the appropriate test to be utilized & calculation of test

criterion based on type of test.
 4. Fixation of level of significance
 5. Select the table & compare the calculated value with the critical value of
the table
 6. If calculated value is > table value, is rejected
 7. If calculated value is < table value, is accepted
 8. Draw conclusions

33
34
FOR QUALITATIVE
DATA

35
COMPARISIONS HYPOTHESIS PARAMETRIC HYPOTHESIS NONPARAMETRIC
TESTED TEST TESTED TEST
1.SINGLE GROUP SAMPLE MEAN ONE SAMPLE T- SAMPLE MEDIAN SIGN TEST
NOT DIFFERENT TEST(<30) NOT DIFFERENT
FROM POPULATION Z TEST (>30) FROM POPULATION
MEAN MEDIAN
2.TWO TWO POPULATION UNPAIRED T-TEST/ TWO POPULATION MANN WHITNEY
INDEPENDENT MEANS ARE EQUAL INDEPENDENT MEDIANS ARE TEST
GROUP SAMPLE T-TEST EQUAL
3.TWO RELATED OR MEAN DIFFERENCE PAIRED T-TEST MEDIAN WILCOXON RANK
PAIRED SAMPLES IS ZERO DIFFERENCE IS TEST
ZERO
4. THREE OR MORE ALL POPULATION ANOVA ALL POPULATION KRUSKAL WALLIS
INDEPENDENT MEANS ARE EQUAL MEDIANS ARE TEST
SAMPLES EQUAL

5. THREE OR MORE DIFFERENCE REPEATED DIFFERENCE MANN WHITNEY

DEPENDENT BETWEEN MEANS MEASURES ANOVA BETWEEN MEDIAN TEST
SAMPLES OF EACH OF EACH
POPULATION POPULATION
GROUP IS EQUAL GROUP IS EQUAL

36
FOR QUALITATIVE
DATA

37
TESTS CHARACTERISTICS

CHI SQUARE TEST TEST ASSOCIATION BETWEEN CATEGORIAL

VARAIBLES(EG- GENDER, BLOOD GRP,
STAGES OF DISEASE)

MC NEMAR TEST ALTERNATIVE TO PAIRED T-TEST FOR

CATEGORIAL VARIABLES.

FISHER EXTRACT TEST USED WHEN EXPECTED VALUES IS <5 IN ANY

COLUMN IN A CHI SQUARE CONTINGENCY
TABLE.

38
APPLICATION IN RESEARCH
METHODOLOGY

39
40
CONCLUSION
 Research is a quest for knowledge through deligent search or
investigation aimed at discovery and interpretation of new
knowledge. Scientific method is a systemic body of procedures and
techniques applied in carrying out experimentation targeted at
obtaining new knowledge hence its understanding is necessary in
human health science and medicine fields.

41
THANK YOU.

42