Research Methodology And Biostatistics
Question 1. Define sampling. Classify and explain the methods of sampling.
Or
Define sample. Describe different sampling methods.
Answer. Sampling is defined as a process by which some units of a population or universe are selected for the study and by subjecting the sampling computation; conclusions are drawn about the population from which there units are drawn as it is difficult to study each and every individual of the population.
Sample is a part of population called the ‘universal’, ‘reference’ or ‘parent’ population.
Classification Of Sampling Methods
- Nonprobability sampling
- Quota sampling
- Purposive sampling
- Convenience sampling.
- Probability sampling
- Simple random sampling
- Systemic sampling
- Stratified sampling
- Cluster sampling.
- Other sampling methods
- Multiphase sampling
- Multistage sampling.
Read And Learn More: Public Health Dentistry Question And Answers
Quota Sampling
- If population has got various categories of units, investigators may decide to fix specified quota for representation of each category of sample.
- The quota from each category is filled by judgment.
- Importance: If investigator is interested in getting predetermined units from the population. General composition of the sample in terms of sex, education, per capita income is decoded in advance and investigator is interested in filling quotas assigned to various groups in population.
Purposive Sampling
- Purposive sampling is a nonrepresentative subset of larger population and is framed to serve the purpose.
- It is not possible to specify population and access is difficult.
- Researcher will attempt to zero on target group and interviewing who is available.
- Subset of purposive sample is snowball sampling.
- Snowball samples are useful in hard to track populations.
- Importance: This method of sampling provides the investigator the typical or representative of population under his study.
Convenience Sampling
- The criterion adopted in this sampling is that of convenience to the investigator.
- Sampling is done by examining the people who get access to the examiner, even though they are not representative of the population.
- It is said to have been used when selection is made from an available sources like that of telephone directory, automobile registers, etc.
- Importance: When there is no need of random samples this technique is applied. The sample is chosen with ease of access being sole concern.
Simple Random Sampling
- Sampling procedure in which units are selected in a way that all units in population have equal chances of being selected.
- Selection is based on the occurrence of events.
- In this type of sampling each and every item in the population has an equal chance of inclusion in the sample. This is done by assigning a number of each unit in the sampling frame.
- The easiest way for random sample is to use random number table or lottery methods.
- Importance: This method endows each sampling unit with the same probability of being selected. It can be with or without replacement. In this, sample is the representative of population.
Systemic Random Sampling
- It is obtained by selecting one unit at random and then selecting additional units at evenly spaced interval till sample of required size is obtained.
- By this method, each unit in the sampling frame would have the same chance of being selected, but the number of possible samples are greatly reduced.
- Importance: In this method only first unit is selected at random, rest being selected automatically as per a predetermined pattern. Pattern followed involve regular spacing of units.
Stratified Random Sampling
- This method of sampling adopted when population can besplit in group with regard to same characteristic.
- From each group, appropriate number of units is randomly selected to form a sample.
- This method is particularly useful where one is interested in analyzing the data by certain characteristics of population example—Hindus, Muslims, Christians, age groups, sex groups, etc.
- Depending on the characteristics, they are divided into subgroups and random sample drawn independently from each group.
- Importance: In this method, every unit in stratum has equal chances of being selected. By this technique, the adequate representation of minority subgroups of interest can be achieved.
Cluster Sampling
- This method is adopted when the unit forms a small group or clusters when the population is made-up of cluster of unit. Some of clusters are selected randomly and they are selected to form a sample.
- It is a systemic sampling where different groups are taken, e.g. cluster sampling in the vaccination group.
- In cluster sampling, we usually select 30 clusters by random sampling method. After selecting the cluster, entire population in the cluster was studied.
- Importance: In this technique, sampling frame of population is not needed. As the selected cluster is studied there is increase in total number of subjects in sample without increase in cost. Results should be obtained in very less time.
Multistage Sampling
- Under the multistage sampling, the first stage may be to select large primary sampling units such as districts towns-families.
- For total healthcare program the question is which village, which house and which person is answerer in this type of sampling.
- Importance: In this, sample is spreaded in entire population and every unit in each stage has equal chances of being selected. This technique saves time and cost.
Multiphase Sampling
- In this method, part of the information is collected from the whole sample and part from the subsample.
- A desired sample is examined and a subsample is drawn from this sample for future information.
- Used for studying a specific disease.
- Importance: This technique is used when various items on selected units in the sample and cost of collection of data on few items is very high. Information is collected in phases and is precise.
Question 2. Define sampling and various sampling designs. Write in detail about pathfinder survey methodology.
Or
Define sampling and describe sample designs.
Answer. Sampling is defined as a process by which some units of a population or universe are selected for the study and by subjecting the sampling computation; conclusions are drawn about the population from which there units are drawn as it is difficult to study each and every individual of the population.
Various Sampling Designs
- Simple random sampling.
- Systemic random sampling.
- Stratified random sampling.
- Cluster sampling.
- Multiphase sampling.
- Pathfinder sampling.
Simple Random Sampling
Evenly spaced inter additional units. It is defined as sampling technique in which each and every unit in the population has an equal chance of being included in sample.
Systemic Random Sampling
It is defined as sampling technique which is formed by selecting one unit at random and then selecting additional units at evenly spaced interval till the sample of required size has been formed.
Stratified Random Sampling
As susceptibility to disease generally varies in relation to age, sex, family history, exposure to risk, many other genetic or environmental factors, it is advisable to examine samples when drawn to see whether they are on average, comparable in these respect.
Cluster Sampling
This method is used when the population form natural groups or clusters such as village, ward blocks or children of school.
Multiphase Sampling
In this method a part of the information is collected from the whole sample and a part from sub sample.
Pathfinder Sampling
This method used is stratified cluster sampling technique which aims to include the most important population sub groups likely to have different disease level.
Pathfinder Survey Methodology
This method used is stratified cluster sampling technique which aims to include the most important population subgroups likely to have different disease level.
- Pathfinder survey is suitable for obtaining the following information:
- The overall prevalence of the common oral diseases and conditions affecting the population.
- Variations in disease in the population enable care needs for different age groups to be determined, to provide information about severity and progression of disease and to give an application as to whether the levels are increasing or decreasing.
- Pathfinder surveys can be either pilot or national depending on the number and type of sampling size and the age groups included or another age groups.
- A pilot survey: It includes only the most important subgroups in the population and only one or two index ages usually 12 years, such a survey provides the minimum amount of data needed to commence planning.
- A national pathfinder survey: Incorporates sufficient examination sets to cover all important subgroups of the population that may have different disease levels or treatment needs and at least three of the age groups or index ages. This type of survey design is suitable for the collection of data for the planning and monitoring of the services.
Question 3. What is sample in epidemiological investigation. Classify them. State with reasons which is ideal sample and describe method of selection of the same.
Answer. Sample is a part of population called the ‘universal’ reference or ‘parent’ population.
Ideal Sample
An ideal sample is the one who fulfill all the following requirements, i.e.
- Efficiency: Efficiency is the ability of sample to yield desired information.
- Representativeness: An ideal sample should represent parent population so that inferences drawn from sample are generalized to the following population with precision.
- Measurability: An ideal sample validates estimate of its variability, i.e. an investigator should be able to estimate the extent in which findings from sample differ from parent population.
- Size: Sample should be large enough for minimizing variability of the sample and for allowing an estimate of population characteristic which is to be made with measurable precision.
- Coverage: Proper coverage should be essential for representing sample.
- Goal Orientation: Selection of the sample should be oriented for study objectives and research designs.
- Feasibility: Sample design should be simple to carry in practice.
- Economy and Cost-Efficiency: Sample should yield desired information along with saving the time and cost with minimal sampling error.
Methods of Selection of Sample
Sample selection is done by two methods, i.e.,
- Purposive selection: Selection of sample should be such that it represents the population as a whole. For example in a study in oral hygiene in an urban school 30 students are undertaken for examining and assessing for poor oral hygiene. This selection method is easily done and does not require sample frame. This method under represents the rate of population under study.
- Random selection: In this method, sample should be selected in such a manner that characteristics of population are reflected in the sample. This is done by selecting the units of sample at random. Sample in which each individual in population has equal chance of appearing is a random sample.
Question 4. Write notes on sampling methods and types of samples in biostatistics.
Answer.
Types of Samples in Biostatistics
Samples are of two types, i.e.
- Random sample or probability sample: In statistical terms a random sample is a set of items that have been drawn from a population in such a way that each time an item was selected, every item in the population had an equal opportunity to appear in the sample. In practical terms, it is not so easy to draw a random sample.
- Nonrandom sample or nonprobability sample: These samples are not true representatives and are, therefore, less desirable than probability samples. It is used in cases where researcher is unable to obtain a random sample.
Question 5. Define biostatistics.
Answer. “Biostatistics is the application of statistical methods to medical and biological phenomenon”. Murad & Shi, 2010
“Biostatistics is a tool that is used to analyze, understand, and explain the variance in medical and epidemiological data”.—Jekel et al., 2007.
Question 6. Describe in detail the various types of sampling methods and their application in dental research.
Answer.
Application of Sampling Methods in Dental Research
- Sampling methods allow thorough investigation of units of observation in dental research.
- Sampling methods provide adequate and in-depth coverage of sampling units in dental research.
- They reduce cost of investigation, time required as well as number of personnel involved in dental research.
Question 7. Write short note on multiphase sampling.
Answer. In this method, part of the information is collected from the whole sample and part from the subsample.
- Example is, for instance in a school health survey, all children in school are examined. From these only the children who have health problems are selected in second phase. A section needing treatment is selected in third phase. Number of children in sub- samples in third and fourth phase becomes smaller.
- A desired sample is examined and a subsample is drawn from this sample for future information.
- It is useful for studying a specific disease.
- Survey by multiphase sampling is less costly, less laborious and more purposeful.
- Information on all the items is collected
Question 8. Write short note on general principle of biostatistics.
Or
Write in brief general principle of biostatistics.
Or
Write in brief on principle of biostatistics.
Or
Define biostatistics. Describe in detail the principles of biostatistics.
Answer. “Biostatistics is the application of statistical methods to medical and biological phenomenon”. Murad & Shi, 2010
“Biostatistics is a tool that is used to analyze, understand, and explain the variance in medical and epidemiological data”. Jekel et al., 2007.
Biostatistical principles are based on applied mathematics and include tools and techniques for collecting information or data and then summarizing and analyzing and interpreting those results.
These principles extend to make inferences anddrawing conclusions that appropriately take uncertainty into account.
Results
Various demographic information are collected and are reported in a simple way in results without attempting to explain the results. State the type of statistical test performed and reports the statistics and conclusions followed by appropriate table.
Question 9. Define data. Enumerate the methods of collection of data. Describe in detail about presentation of data.
Or
Define biostatistics. Describe the methods of collecting the data and ways of presentation of the same.
Or
Describe various methods of collection and presentation of data.
Answer.
Definition of Data
A collective recording of observations either numerical or otherwise is called data.
Definition of Biostatistics
“Biostatistics is the application of statistical methods to medical and biological phenomenon”. —Murad & Shi, 2010
“Biostatistics is a tool that is used to analyze, understand, and explain the variance in medical and epidemiological data”. —Jekel et al., 2007.
Methods of Collection of Data
Primary data can be obtained by using following methods:
- Direct personal (face to face) interview.
- Oral health examination.
- Questionnaire method.
Direct Personal Interview
- In this method, there is a face to face contact with the information which is to be obtained.
- This method enables to measure subjective phenomenon such as oral health status, the opinion, beliefs and attitudes and some behavioral characteristics.
- An advantage of this method is that all the information can be collected accurately but it is time consuming and requires more personnel.
Oral Health Examination
- This method provides more valid information than health interviews.
- It is conducted by dentists, technicians and the investigators.
Questionnaire Method
- In this method a list of the questions pertaining to the survey known as questionnaire is prepared and the variable informants are requested to supply the information either personal or through post.
- This method is easy to adopt when a wide geographic area is to be covered.
- It is relatively cheap.
- The questions should be short, easy to understand. There should be no unambiguity while answering the questions.
- The disadvantage of this method is that the informants must be literate so that they can understand the question.
- Adoption of this method should be done for knowing general awareness and attitude of people in community regarding their oral health practices.
Question 10. What is Data? Give its types and describing the various ways of presentation of data.
Or
What is data? Describe various methods of presentation of data for the statistical analysis.
Or
Define biostatistics. Describe the various methods of presentation of data.
Or
Write short note on methods of data presentation.
Or
Write in detail on presentation of data in biostatistics.
Or
Write in brief on data presentation.
Or
Write short note on data presentation.
Or
Describe briefly various methods of depicting statistical data.
Or
Define biostatistics. Describe the various method of presentation of data with suitable examples.
Or
Write in brief on different forms of diagrammatic presentation of data.
Or
Write note on geographical or diagrammatic representation of data.
Answer.
Definition of Biostatistics.
“Biostatistics is the application of statistical methods to medical and biological phenomenon”. Murad & Shi, 2010
“Biostatistics is a tool that is used to analyze, understand, and explain the variance in medical and epidemiological data”. Jekel et al., 2007.
Definition of Data
Data: A collective recording of observations either numerical or otherwise is known as data.
Types of Data
- Depending upon the source:
- Primary data: Data obtained directly from an individual.
- Secondary data: Data, which is, obtained from outside source, e.g. Hospital records.
- Depending upon the nature of the variable, data is classified into two broad categories:
- Quantitative data: When the data is collected on the basis of attributes or qualities like sex, malocclusions, cavity, etc. It is called qualitative data.
- Quantitative data: When the data is collected through measuring using calipers like arch length, arch width, fluoride concentration in water supply, etc. is called qualitative data.
Quantitative data can be classified into two kinds:- Discrete data: When the variable under observation takes only fixed value like whole numbers, e.g.
The DMF teeth. - Continuous data: If the variable can take any value in a given rough, decimal or fractional, it is called as continuous data, e.g. arch length.
- Discrete data: When the variable under observation takes only fixed value like whole numbers, e.g.
- Grouped Data and ungrouped Data
- Grouped data: These are presented in groups.
- Ungrouped data: These are presented individually
- Nominal data and Ordinal data
- Nominal data: In this the information fits into one of the categories but the categories are not ordered one above the other.
- Ordinal data: It describes the limited number of categories which are ordered one above the another but space between each category is not same.
Presentation of Data
- A good presentation of data is very important.
- A good presentation makes the data simple, concise, meaningful, interesting and helpful in further analysis.
- There are two main method of data presentation:
- Tabulation
- Diagrams and charts
Tabulation
Tables are the devices for presenting data.
Types of Tables
- Simple table: They provide answer to questions about a characteristic of data only. Example of simple table is:
- Frequency distribution table: It is a two column frequency table. First column consists of classes in which data is grouped. Second column consists of frequencies of each classification.?
While forming a frequency distribution table, the following basic rules are to be followed:- Every table should contain a title.
- The number of class intervals should not be too many or too less.
- The class limit should be clearly designed with the headings.
- Units of measurement should be specified.
- If the data is not original, the source of the data should be mentioned at the bottom of the table.
- Example of frequency distribution table is:
- Master table: They are the tables which contain all the data obtained from a survey. Example of master table is:
Diagrams and Charts
Diagrams and graphs are one of the most convincing and appealing ways of depicting statistical results.
Types of diagrams: Depending upon the nature of data, whether it is qualitative or quantitative.
- Simple bar chart:
- It presents the set of numbers by length of a bar.
- It is used to represent qualitative data.
- It represents only one variable.
- Width of the bar remains the same and only length varies according to frequency in every category.
- Multiple bar chart: It is used to compare qualitative data which represent to a single variable. This diagram is similar to the bar diagram except that for each category of the variable we have a set of bars of the same width.
- Proportional or components bar chart: It is used to represent qualitative data, when it is desired to compare only the proportion of subgroups between different major groups of observations. Bars are drawn for each group with same length.
- Pie diagram: These are used to show percentage breakdown for qualitative data. It is so called because the entire graph look like a pie and component represent the slice cut from a pie. Angle at the center of circle is equal to 360 degree and presents total frequency.
- Line diagram: This diagram is useful to study change of values in the variable overtime and is the simplest type of diagram. On the X-axis the time represented and the value of any quality pertaining to this is represented along Y-axis.
- Histogram: This diagram is used to depict qualitative data of continuous type. A histogram is a bar diagram without gap between bars. It represents a frequency distribution. In histogram class intervals are present on X-axis and frequencies on Y-axis.
- Frequency polygon: This is used to represent frequency distribution of quantitative data and is useful to compare two or more frequency distribution.
- Cartogram or spot map or shaded map: These maps are used to show geographical distribution of frequency of a characteristic. Coverage of cases of fluorosis by geographical area may be depicted by this diagram and dot or point may be used to indicate one such case for that area.
- Pictogram: Small pictures and symbols are used for presenting data. They are specially used for common man.
Scatter or dot Diagram: It is the diagram which shows the relationship between two variables. If dots cluster around a straight line it shows a linear relationship.
Question 11. Describe the role of biostatistics in community dentistry. Describe briefly various methods of presentation of statistical data.
Answer. Role of biostatistics in community dentistry
- To assess the state of oral health in the community and to determine the availability and utilization of dental care facilities.
- To indicate the basic factors underlying the state of oral health by diagnosing the community and solutions to such problems.
- To comparing the health status on a community to the other community or for comparing the present status with past.
- Use for planning and administration of health survey.
- To determine success and failure of specific oral health care program or to evaluate the program action.
- To promote health legislation and in creating administration standards for oral health.
- Use to stimulate the future needs of community.
Question 12. Write short note on pie diagram.
Answer. It is so called because whole of the graph looks like a pie and the components represent slices cut from a pie.
- Total angle at center is 360° and it shows total frequency.
- Pie diagram is divided in different parts which correspond to the frequencies of variables in distribution.
- Different parts are shaded with different colors.
- An index is provided for the shaded colors.
- Pie diagram cannot represent two or more data sets.
- The male:female distribution, chewing habits of a group of individuals, type of cases attending an OPD are depicted in a pie diagram.
Question 13. Write short note on scatter diagram.
Answer. Scatter diagram or Dot diagram:
- It is a graphic presentation, made to show the nature ofcorrelation between two variable characters X and Y in the same person or group, such as height and weight in men of age 20 years, hence, it is called correlation diagram.
- The characters are read on base (X) and vertical (Y) and the perpendicular drawn up to meet, to get scatter point.
- Varying frequencies of the characters give a number of such point or dots.
- A line is drawn to show the nature of correlation at a glance.
Question 14. Write short note on importance of data in biostatistics.
Answer. Data: A collective recording of observations either numerical or otherwise is called data.
Importance of Data
- It is used to design the healthcare program.
- It is important to evaluate the effectiveness of ongoing program.
- It is important to determine the need of a specific population.
- It is important to evaluate the scientific accuracy of a journal article.
Question 15. Discuss the role of statistics in oral health.
Answer. Following is the role of statistics in oral health:
- It provided assessment of the state of oral health in the community and to determine met and unmet oral health needs.
- To indicate the basic factors underlying the state of oral health by diagnosing community ills and to discover solutions to such oral health problems.
- To determine the success or failure of specific oral health programs or in evaluating the total program of action.
- To promote oral health legislation and in creating administrative standards of oral health activities so that the community’s health may be promoted.
- To define what is normal or healthy in a population and to end limits of normality in variables.
- To test usefulness of sera and vaccines in the dentistry, the percentage of attacks or deaths among the vaccinated subjects is compared with that among the unvaccinated ones to find whether the difference observed is statistically significant.
- In public health dentistry, the measures adopted are evaluated.
- In epidemiological studies—the role of causative factors is statistically tested.
- To end out an association between two attributes such as oral cancer and tobacco chewing.
Question 16. Write short note on Variables.
Answer. “A variable is a state, condition, concept or event whose value is free to vary within the population”.
Classification of Variables
- Independent variable: They are manipulated or treated in a study to see what is the effect, difference in the variables will have on those variables proposed as dependent on them. Synonyms used for these variables are cause, input, predisposing factor, risk factor, attribute, determinant.
- Dependent variables: In them changes are due to the result of level or amount of independent variable. Synonyms used are effect, outcome, result, condition, disease.
- Cofounding or intervening variables: They should be studied so that they can influence or cofound the effect of independent variables on dependent variable.
- Background variables: They provide relevance in investigations of groups or population which should be considered for inclusion in study. Synonyms used are sex, age, ethnic origin, marital status and social status.
Functions of Variables
- They provide the yardstick on which the effects of treatment or experience are measured.
- They are used to identify the subpopulation to which an individual belongs.
- They are used to measure or classify treatment or experience.
Question 17. Write short note on measures of central tendency.
Or
Write short answer on measures of central tendency.
Or
Write short answer on measures of central tendency in biostatistics.
Answer. Generally, it is found that values of variable tend to concentrate around some central value of observations of an investigation, which can be taken as a representative for whole data. This tendency of distribution is known as central tendency and the measures devised to consider this tendency are known as measures of central tendency.
- Main objective of measure of central tendency is to condense complete mass of data and facilitate comparison.
- A measure of central tendency should satisfy following properties:
- Easy to understand and compute
- Based on each and every item in series
- Should not get affected by extreme observations.
- Should have sampling stability.
- Most common measures of central tendency used in dentistry are:
- Arithmetic mean
- Median
- Mode.
Question 18. What is the role of biostatistics in dental epidemiology? Describe with the example the common measures of statistical average and dispersion.
Or
Write short note on mean, median and mode.
Answer.
Measures of Statistical Average
There are several kinds of average of which the commonly used are:
- Arithmetic mean
- Median
- Mode.
Arithmetic Mean
- It is the simplest measure of central tendency.
- When we have ungrouped data mean is calculated as follows:
Mean = \(\frac{\text { Sum of all the observations in data }}{\text { Number of observations in data }}\)
Or Symbolically as: \(\mathrm{X}=\frac{\sum \mathrm{X}_{\mathrm{i}}}{\mathrm{n}}\)
∑ means the sum of
Xi is value of each observation in data
N is number of observations in data
X is symbol for mean
It is obtained by summarizing up all the observations and dividing the total by number of observations, e.g. the fasting blood glucose level of a sample of 10 children.
\(\begin{array}{lccccccccc}1 & 2 & 3 & 4 & 5 & 6 & 7 & 8 & 9 & 10 \\
56 & 62 & 63 & 65 & 68 & 65 & 69 & 68 & 70 & 65
\end{array}\)
Total = 650
Mean = 650/10 = 65.
Mean is denoted by the sign of X.
Median
- Median by definition is the middle value in the distribution such that one-half of the units in the distribution have a value smaller than or equal to median and one-half has a value higher than or equal to the median.
- In median the data are arranged in an ascending or descending order of magnitude and the value of middle is located.
- For example, diastolic blood pressure of 10 individuals
1 & 2 & 3 & 4 & 5 & 6 & 7 & 8 & 9 & 10 \\
83 & 75 & 81 & 79 & 71 & 95 & 75 & 77 & 84 & 80
\end{array}\)
Arrange them in ascending order or descending order
71 75 75 77 79 81 83 84 90 95
Median = \(\frac{79+81}{2}=80\)
Mode
- The mode or the modal value is that value in a series of observations that occurs with the greatest frequency.
- Mode is the value, which occurs with the greatest frequency. A distribution may have more then one mode, e.g. Diastolic pressure of 10 individual
80 85 70 75 81 83 75 90 72 73
Here the mode is 75 and it is unimodal
85 75 81 79 80 71 80 78 75 73
Here the mode is bimodal 75 and 80 - There can be more than one mode for the series.
- When mode is ill defined it can be calculated using the relation
Mode = 3 Median-2 Mean - Depending on the nature of data and objective of study, the appropriate measure of central tendency may be used. Most commonly used measure is arithmetic mean; if there are extremes of value in series of data, median may be used. If it is required to know that value that has high influence in the series, mode may be computed.
Question 19. Write short note on measures of dispersion in biostatistics.
Answer. Measures of dispersion provides the knowledge how widely is the observation spreaded on either side of an average.
The most common measures of dispersion used in dentistry are:
- Range
- Mean deviation
- Standard deviation.
Range
- It is the simplest method which is defined as the difference between the value of the smallest and the value of the largest item.
- Advantages: This method is simple to calculate, it is not based on all the values, e.g. diastolic pressure of 10 individuals.
86 83 75 81 73 75 85 95 71 90
Range = 95 – 71 = 24.
Mean Deviation
Mean deviation of observation is find by the formula.
M.D. = \(\frac{\Sigma(X-X i)}{\mathrm{n}}=80\)
∑ is sum of
X is arithmetic mean
Xi is value of each observation in data
n is total number of observation.
Question 20. Write short note on standard deviation.
Answer. Standard deviation is the most important and widely used measures of dispersion.
- It is also called as root mean square deviation.
- It is denoted by Greek letter sigma or SD.
- The standard deviation is calculated from the basic formula.
SD = \(\sqrt{\frac{\sum(x-\bar{x})^2}{n}}\)
- When the sample is more than 30 above basic formula is used.
- For smaller sample, the above formula tends to underestimate the standard deviation and therefore needs correction.
Steps in Calculating Standard Deviation
It is completed by following five steps:
- Calculate mean of series, i.e. x.
- Take deviations of the items from mean, i.e. x– x
- Squared the deviations and add them ∑(x– x)2
- Divide this sum by total number of observation, i.e. n or n-1 if sample size is less than 30.
- Obtain square root to the main formula which provides standard deviation.
Question 21. Write short note on normal curve.
Or
Write short answer on normal distribution curve.
Answer. It is also known as normal distribution or Gaussian distribution.
When data get collected from very huge population and frequency distribution is made from with narrow class intervals, the formed curved is smooth and is symmetrical so it is known as normal curve.
Features of Standard Normal Curve
- It is bell-shaped curve and is bilaterally symmetrical.
- It is continuous curve and its both tails extends to infinity.
- Smoothness present is due to equal and small classintervals. Symmetry indicates that curve has only one peak and its skewness is zero.
- Frequency of measurement increases from one side arrives towards the peak, plateau and goes on declining as they have mounted.
- Highest point at frequency distribution represents mean, median and mode.
Presentations of Normal Curve
- Area between the one standard deviation at either side of mean include 68.3% of values.
- Area between the two standard deviations at either side of mean include 95.4% of values.
- Area between the three standard deviations at either side of mean include 99.7% of values.
- Limits on either side of mean are known as confidence limits.
Uses
- To make decision about the common/uncommon measurements.
- To provide an estimate of number of units in given range of measurement.
Merits
- It is rigidly defined.
- It is based on all observations
- It does not ignore the algebraic signs of deviations
- It is capable of further mathematic treatment.
- It is not much affected by sampling fluctuations.
Demerits
- It is difficult to understand and calculate.
- It cannot be calculated for qualitative data and distribution with open end classes.
- It is unduly affected due to extreme deviations.
Question 22. Write short note on uses of standard error.
Answer. The standard error is the standard deviation of the sampling distribution of a statistic, most commonly of the mean. The term may also be used to refer to an estimate of that standard deviation, derived from a particular sample used to compute the estimate.
Uses of Standard Error
Following are the uses of standard error based on its types:
- Standard error of mean: It is used to provide the standard deviation of means of various samples from same population.
- Standard error of proportion: It is used to focus on proportions.
- Standard error of difference between two means: It is used in finding out whether the difference between means of two groups is significant to indicate that samples represent two different universe.
- Standard error of difference between proportions: It is used in finding out whether the difference between means of two groups is significant or occurs by chance.
Question 23. Write notes on Test of significance.
Answer. Whatever is the sampling procedure or the care taken while selecting sample, the sample statistics will differ from the population parameters. Also variations between two samples drawn from the same population may also occur, i.e. differences in the results between two research workers for the same investigation may be observed. Thus, it becomes important to find out the significance of this observed variation, i.e. whether it is due to chance or biological variation (statistically not significant) or due to influence of some external factors (statistically significant). To test whether the variation observed is of significance, the various tests of significance are parametric tests and nonparametric tests.
Parametric Tests
- Parametric tests are those tests in which certain assumptions are made about the population.
- Population from which sample is drawn has normal distribution
- The variances of sample do not differ significantly
- The observations found are truly numerical thus arithmetic procedure such as addition, division, and multiplication can be used.
- Since these test make assumptions about the population parameters hence they are called as parametric tests.
- These are usually used to test the difference.
- They are:
- Student T test (paired or unpaired)
- ANOVA (Analysis of variance)
- Test of significance between two means.
Nonparametric Tests
- In many biological investigations, the research worker may not know the nature of distribution or other required values of the population.
- Also some biological measurements may not be true numerical values hence, arithmetic procedures are not possible in such cases.
- In such cases distribution free or nonparametric tests are used in which no assumption are made about the population parameters, e. g.
- Mann-Whitney test
- Chi-square test
- Phi coefficient test
- Fischer’s exact test
- Sign test
- Friedman’s test.
Question 24. Write short note on chi-square test.
Answer. Chi-square test is developed by Karl Pearson.
- Chi-square test plays important role in problem where information is obtained by counting or enumerating instead of measuring.
- Chi-square test is used in dental statistics for:
- Test of proportion
- Test of association
- Test of goodness of fit.
- This test is used to test the significance of differencebetween two proportions and is used where more than two groups are present.
- Chi-square test is a nonparametric test.
- Chi-square is denoted by X2
- Test of proportion is used as an alternate test to find the significance of difference in two or more than two proportions.
- Test of association measure the probability of association between two discrete attributes.
- Test of goodness of fit assess whether the observed values of a character differ from the expected value by chance or due to play of some external factor.
- Chi-square test uses the following formula:
X2 = ∑ (O – E) 2/E
Here, X2 denotes Chi-square
O denotes observed value
E denotes expected value.
Question 25. Discuss the role of biostatistics on the study of epidemiology of community health.
Answer. Statistics plays an important role in study of epidemiology of community health.
- In epidemiological studies the role of causative factors is statistically tested. Excess of fluoride as an important cause of fluorosis in a community is confirmed only after comparing the incidence of fluorosis cases in the affected area as compared to the cases in other areas.
- It plays an important role in formulating community diagnosis quantifies the health problems in community in terms of mortality and morbidity and the ratios. Quantification of morbidity and mortality can serve as benchmark for evaluation of health services at later stages. As quantification of health problems is done by statistics it can act as a new knowledge about disease distribution, causation and prevention.
- Biostatistics helps in analyzing the epidemiological studies which find out cause effect relationships and intervention.
- Researches should be carried out in the community health, these researches were analysed by the biostatistics.
Question 26. Write short note on uses and sources of vital and health statistics.
Answer.
Vital Statistics
Vital statistics is defined as data which gives quantitative information on vital events occurring in life, i.e. migration, births, marriages and deaths in a given population.
Uses of Vital and Health Statistics
- In population estimation and forecasting.
- In analysis of health trends.
- In program planning, monitoring and evaluation.
- In operational and administrative decision making.
- In providing indices for measuring health and disease in a community.
- To provide tools and methods for measuring and comparing morbidity, mortality, fertility, etc. of a country, city, state and region with other country, city, state and region.
Sources of Vital and Health Statistics
Following are the sources of vital and health statistics:
- Records of health departments: Notification of epidemic diseases such as cholera, smallpox and plague is compulsory in rural India by the village officers such as secretary of village Panchayat to the Taluka office, who conveys the same by telegrams to Collector, District Health Officer and Director of Health Services, for immediate action. In municipalities and corporations, notification is compulsory for the doctors attending on a case of a notifiable disease or by the head of the family, or the landlord, to the local health authority and for that there are rules. The data are usually incomplete, and often unreliable for want of correct diagnosis of the disease reported, and under registration. Collection is done at the state level from where the reports are sent to the World Health Organization (WHO). The list of notifiable diseases varies from area to area.
- Records of Health Institutions: The routine records include returns from hospitals, health centers, dispensaries and maternity homes. The institutions record all indoor and outdoor cases that come for treatment, their diagnosis and result. Monthly returns are sent to the State Director of Health Services. These data are biased because they do not cover any specified area or population. So they cannot be used as a general measure of morbidity. However, they reflect a gross picture of diseases prevalent in the catchment area of the institutions. Such data are mostly used to assess the hospital needs or efficacy of certain therapeutic measures.
- Reports of Special Surveys: Well conducted and comprehensive surveys give useful data about the health status of the community and the progress made to the measures adopted. Comprehensive surveys are carried out for the assessment of tuberculosis, leprosy and cancer prevalence. Sample surveys are made for finding the correct position when birth and death registration is not reliable. Appraisal of nutritional status is made by physical examination and diet surveys. Specified sample surveys are the only answer to diagnose many of the country’s health problems when existing registration is not reliable.
Question 27. Write a short note on primary data.
Answer. Data obtained directly from an individual is known as primary data. Primary data is the first hand information.
Primary data can be obtained by using following methods:
- Direct personal (face to face) interview
- Oral health examination
- Questionnaire method.
Direct Personal Interview
- In this method, there is a face to face contact with theinformation which is to be obtained.
- This method enables to measure subjective phenomenon such as oral health status, the opinion, beliefs and attitudes and some behavioral characteristics.
- An advantage of this method, is that all the information can be collected accurately but it is time consuming and require more personnel.
Oral Health Examination
- This method provides more valid information than health interviews.
- It is conducted by dentists, technicians and the investigators.
Questionnaire Method
- In this method a list of the questions pertaining to the survey known as questionnaire is prepared and the variable informants are requested to supply the information either personal or through post.
- This method is easy to adopt when a wide geographic area is to be covered.
- It is relatively cheap.
- The questions should be short, easy to understand. There should be no unambiguity while answering the questions.
- Disadvantage of this method is that the informants must be literate so that they can understand the question.
- Adoption of this method should be done for knowing general awareness and attitude of the people in community regarding their oral health practices.
Question 28. Write short note on protocol.
Answer. A protocol is a document that explicitly states the reasoning behind and structure of a research project.
- Protocol is a draft summary which indicates why and how the study will be taken.
- All protocols are divided into two main sections which are as follows:
- Problems to be investigated
- Project title
- Research problem
- Background
- Aims
- The hypothesis
- Methods of investigation
- Plan of the investigation
- Project milestones
- Resources required
- Dissemination of the results
- Problems to be investigated
Problem to be investigated
Project Title
- This is the one of the most important features of theprotocol as it attracts the attention of potential reader.
- Project title should be as short and to the point as possible.
- For an instance “An investigation to evaluate the effect of 2% iodine and chlorhexidine on Streptococcus. A randomized control trial” this title is very long, a preferable approach may be. “A randomized control trial of 2% iodine and chlorhexidine” so this title comes straight to the point and attracts reader.
Research Problem
- They are the explanatory devices.
- They carefully designed the sentences about what one is intended to find out.
- Statement of the problem should be expressed in a precise and concise form including essential points.
- When statement of the problem is written, words must show an understanding of the research phenomenon and should explicitly reveal the purpose.
- Information about the problem should be summarized so that the reader is not drowned in detail.
- So when protocol is read, reader will want to know the purpose of study immediately. Reader do not want to search via several pages of text to discover what the protocol is about.
- For effectiveness opening words should be clear and demand attention. For example:
- In this study I intend to find whether the use of 2%iodine will result in more Streptococcus reduction than chlorhexidine. If I can show that this occurs this will be an important finding for preventive care.
- This will be an investigation to evaluate the effect of 2% iodine on S. mutans reduction.
- Above mentioned statement 1 is easy to read as it is in the first person, and this should be the preferred writing style as opposed to use of the passive voice. Care should also be taken that first person is not over used.
Background (Including the literature review)
- One of the important features of the background to project is that it should be brief and is directly to the point.
- For a research protocol background is not longer than 2 pages of A4 size paper.
- Literature which is relevant to the problem which is to be solved is concisely reviewed.
- When review is written, attention is drawn towards the good points and deficiencies of the study are quoted.
- In terms of a writing style it is a good practice to make a writing flow.
Aims
- It is an overall statement of the reason for undertaking the study. For example To determine the oral health of 10-yearold state school children in x,y,z districts.
- Aims of the project are explicitly stated and are confined to the intention of the project.
Hypothesis
- A hypothesis can be defined as a tentative prediction or explanation of the relationship between two or more variables.
- Hypothesis translates the problem statement into a precise, unambiguous prediction of expected outcomes.
- Hypothesis should reflect the depth of knowledge, imagination and experience of the investigator.
- Hypothesis should be simple in form and should predict the relationship between two variables, i.e. one independent and one dependent.
- So in formulating the hypothesis all variables relevant to the study are identified.
- In general practice hypothesis should be stated in the null form.
- So null hypothesis is: There is no difference in the effect of 2% iodine and chlorhexidine on S mutans and alternative hypothesis is there. So there is a difference in the effect of 2% iodine and chlorhexidine on dental caries incidence.
Methods of Investigation
- It is the description of tactics of research and is the easiest part of the research protocol.
- For making the method easy to read it should be used in active voice.
- In this study protocol method should be stated in the future tense.
- Method should be structured by using following subheadings, i.e. subjects, design, procedure, materials, measurements and apparatus used, sample size, calculation and finally the statistical method which is going to be used.
Resources Required
- So finally a list of all resources which are required to successfully complete the investigation must be made.
- If these resources have cost implications, the potential cost of investigation must be noted.
Dissemination of the Results
- Preparing and presenting a protocol is one of the most difficult part of carrying out the research project and it can also be most interesting and satisfying.
- Result of the process should be a short document which clearly outlines the research project.
- If protocol is poorly prepared and not adhered to, it is unlikely that project will yield the information which is hoped for.
Question 29. Write a short note on random sampling.
Answer. Random sampling is the process in which each individual in the population has an equal chance of appearing.
It is of three types, i.e.
- Simple random sampling
- Systemic random sampling
- Stratified random sampling
Simple Random Sampling
- Sampling procedure in which units are selected in a way that all unit in a population has equal chances of being selected.
- Selection is based on the occurrence of events.
- In this type of sampling, each and every item in the population has an equal chance of inclusion in the sample.
- This is done by assigning a number of each unit in the sampling frame.
- The easiest way for random sampling is to use random number table or lottery methods.
- Importance: This method endows each sampling unit with the same probability of being selected. It can be with or without replacement. In this sample is the representative of population. This technique provides the greatest number of possible samples.
Systematic Random Sampling
- It is obtained by selecting one unit at random and then selecting additional units at evenly spaced interval till sample of required size is obtained.
- By this method, each unit in the sampling frame would have the same chance of being selected but the number of possible samples are greatly reduced.
- Importance: In this method, only first unit is selected at random, rest being selected automatically as per a predetermined pattern. Pattern followed involve regular spacing of units.
Stratified Random Sampling
- This method of sampling adopted when the population can be split in group with regard to same characteristic.
- From each group appropriate number of units is randomly selected to form a sample.
- This method is particularly useful where one is interested in analyzing the data by certain characteristics of population, example—Hindus, Muslims, Christians, age groups, sex groups etc.
- Depending on the characteristics, they are divided into subgroups and random sample drawn independently from each group.
- Importance: In this method, every unit in stratum has equal chances of being selected. By this technique the adequate representation of minority subgroups of interest can be achieved.
Leave a Reply