- Predict the number of disease occurrence
- Read understand and criticize the medical literature
- The planning , conduct and interpretation of much of medicl research are becoming increasingly reliant on statistical methods.
Why should medical student learn biostatistics?
- We have to clarify the relationship between certain factors and disease
- Enumerate the occurrences of diseases
- Explain the etiology of disease (which factors cause which disease)
What is Statistics?
Role of Bio-Statistics
- Protocol Development
- Management
- Study Implementation
- Study Monitoring
- Data Analysis
- Report/Manuscript Writing
WHAT IS STATISTICS ?
BIOSTATISTICS
- The tools of statistics are employed in many fields like business, education, psychology, agriculture, economics etc.
- When the data analyzed are derived from the biological science we use the term biostatistics .
The Study of analyzing , collecting and distributing data which is applicable in field of medical science is known as biostatistics.
- Anjani Advani
- Ehtesham Ullah Khan
- Pooja Vasandani
- Farheen Abdul Kalam
- Syed Osama
- Kajal Kumari
- Wasey Ali
- Simran Chandwani
- Anum Kumari
BIOSTATISTICS
The Study of analyzing , collecting and distributing data which is applicable in field of medical science is known as biostatistics.
Statistics
Founder of Statistics
Is the art of and science of data.
It deals with:
Planing resreach
Collecting data
Describing data
Presenting data
Analyzing data
Interperting result
Reaching decision
- The median is the middle value of a set of Data
- The median is used in a variety of Statistics.
- Too calculate median , the numbers in a set of data are arranged in ascending or descending order .
ROLE OF BIOSTATISTICS IN PHYSIOTHERAPY
Measures of dispersion OR VARIABILITY
- The mode is the most frequent observed value in a Data.
FOR EXAMPLE:
- If you’d like to know the most popular new born baby boy name in hospital for 2008 year records you may go to the hospital website and find out that Jacob was the most popular.
Range
- Range
- Variance
- Coefficient of variation
- Standard deviation
- Standard error
- Quartile
- Semi-interquartile range
For any set of data, the range of the set is given by
Range = (greatest value in set) – (least value in set).
EXAMPLE:
The normal value of RBcs in human is 3000-11000 McL so the range of WBcs in human is 7000 McL which is standard by diagnosis.
IMPORTANCE OF STATISTICS
Sir Ronald A. Fisher
Measures Of Distribution
Use of Biostatistics In Medical Sector
Group of analytical tools that describes the spread or variability of a data set
- It presents a fact in a definite term
- It simplifies mass if figures
- Its facilitates comparisons
- It helps in formulating and testing hypothesis
- It helps in prediction
- It helps in formulation of suitable policies
- Documentation of medical history of diseases.
- Planning and conduct of clinical studies.
- Evaluating the merits of different procedures.
- In providing methods for definition of “normal” and “abnormal”.
- To provide the magnitude of any health problem in the community.
- To find out the basic factors underlying the illhealth.
- To evaluate the health programs which was introduced in the community (success/failure).
- To introduce and promote health legislation.
Standard Deviation & Variance
The positive not of square deviation is known as STANDARD DEVIATION.
Symbol: σ (sigma)
FORMULA:
Presented to:
Sir Umair Shaikh
Which to Use?
The square root of standard deviation known as VARIANCE.
Symbol: σ ²
FORMULA:
If you want to find the average availability of medicine in a group of patients in ward than simply add up all the patients in ward and divided by the number of patients.
- The MODE is appropriate at any level of measurement.
- The MEDIAN is appropriate with ordinal, interval, or ratio data.
- The MEAN is appropriate when data are measured at the interval or ratio level.
- The relationship between measures depends on the FREQUENCY DISTRIBUTION.
- When data are normally distributed, all values will be equal.
- Descriptive Statistics
- Inferential Statistics
Frequency Distribution
QUOTA SAMPLING
- Description of data, versus theoretical distribution ( Normal Distribution – Mean and a variance )
- The Formulas for frequencies of distribution from ungroup into group data are not accurately applicable when the no. of observations are too small or too large.
Is a types of non probability sample in which the researcher selects people according to some fixed quota.
In quota sampling the researcher arms to represent the major characteristics of the population by sampling a proportional amount of each
Find the standard deviation and variance of the weight (in lbs) of NEW BORN babies in a hospital is 1, 2, 8, 11, 13.
Measures of Central Tendency
Organize and summarize data
OR
A way to summarize data from a sample or a population
Distributed Statistic include the frequency distribution & its interpretation like mean mode and measure of dispersion.
Median:
Standard deviation is 4.77
Variance is 22.8
Median the observation which lies in the middle of the ordered observation
Or
The value that divides the frequency distribution in half.
Midrange = Smallest observation + Largest observation
2
PROBABILITY
A probability distribution is a table or an equation that links each outcome of a statistical experiment with its probability of occurrence.
Measures of Central Tendency
Mode:
- The value which occurs with the greatest frequency i.e. the most common value. or
- The value that occurs most often, there can be more than one—”multimodal” data.
CONVENIENCE SAMPLING
Selection of which ever individuals are easiest to reach.
Is a non probability sampling technique where subjects are selected because of their convenient accessibility & proximity to the researchersexperiments.
Mean
Snowball Sampling
The mean is the average of all numbers and is sometimes called the arithmetic mean.
To calculate mean, add together all of the numbers in a set and then divide the sum by the total count of numbers.
TYPES OF PROBABILITY
Measures of Central Tendency
Mean:
Useful for finding subject who may not be dealing to close. Is a non probability sampling that is appropriate to use in research when the members of a population are difficult to locate.
JOINT PROBABILITY
Occurrence of two events simultaneously.
EXAMPLE
A component of Physiotherapy that is suspension therapy through tis a neurological impaired patient can get joint stability and relaxation
POSTERIOR PROBABILITY
Once study is carried out, the data is collected and the probability is modified in the light of result.
- The average, equal to the sum of the observations
- divided by the number of observations
- Arithmetic mean (mean) (Σ(x)/N)
- Sum of all observations
- Number of observations
Systemic Sampling
What is research ?
Sample arrange in order
Systemic sampling is a statistical method involving the selection if elements from an ordered sampling frame.
The systematic investigation into and study of materials and sources in order to establish facts and reach new conclusions.
A process of steps used to collect and analyze information to increase our understanding of a topic or issue.
It consists of three steps:
- Pose a question.
- Collect data to answer the question , present an answer to the question.
- Basically research is based on hypothesis
EXAMPLE
Inferential Statistics
Health department has reported that 84 deaths ,16 from cancer and from heart failure. The probability of death is 60% the health department use posterior probability.
Methods of presentation of data
Mathematical presentation
- Numerical presentation
- Graphical presentation
- Mathematical presentation
MUTUALLY EXCLUSIVE EVENT
Event that can not happen together
EXAMPLE
One person sick will not healthy simultaneously.
- Methods used to make inferences about the relationship between the dependent and independent variables in a population, based on a sample of observations from that population
OR
- Used to make an inference, on the basis of data, about the (non)existence of a relationship between the independent and dependent variable
- 3-Mathematical presentation
- Measures of location :
- Measures of central tendency
- Frequency distribution
- Measures of non central locations (Quartiles, Percentiles )
- Measures of dispersion
Sampling Process
- The sampling process comprises several stages:
- Defining the population of concern
- Specifying a sampling frame, a set of items or events possible to measure
- Specifying a sampling method for selecting items or events from the frame
- Determining the sample size
- Implementing the sampling plan
- Sampling and data collecting
- Data which can be selected
Numerical Presentation
Sampling
Distribution of 50 Students at the PHYSIOTHERAPY department of JINNAH hospital in Oct 2015 according to their ABO blood groups
Selecting observation provide adequate description to population
Doughnut
SAMPLING It is the process to draw the sample from population
POPULATION A set of object element or people who have similar of characteristics to represent set its identity
SAMPLE A small part of relevant population which is use to analyze through the process of sampling and hypothesis and characteristics of that sample represent the population
TYPES OF SAMPLING
Hypothesis
Bar Chart
There are two major types of sampling.
- Random sampling.
- Non random sampling.
- Hypothesis is an Intelligent or educated Guess
- Hypothesis testing involves determining if differences in dependent variable measures are due to sampling error, or to a real relationship between independent and dependent measures.
- Three basic steps: –
- Define the hypothesis
- Select appropriate statistical test
- Decide whether to accept or reject the hypothesis
TYPES OF HYPOTHESIS
There are three types of simple random sampling:
NULL HYPOTHESIS
The hypothesis which we want to test.
Denoted by Ho.
Graphical Representation
Pie Chart
Exercise: Physical exercise does not increase mood.
Statistics
ALTERNATIVE HYPOTHESIS
Simple random sampling.
Systemic sampling
Stratified sampling.
The opposite to the null hypothesis.
Denothypothesised by Ha.
Line graph
Histogram
Scatter plot
Pie Chart
Bar Graph
Example: Physical exercise increase mood.
Quantitative Charts
Line Graph
SIMPLE RANDOM SAMPILNG
Scatter Plot
Accepting or Rejecting the Null Hypothesis
A researcher thinks that if knee surgery patients go to physical therapy twice a week (instead of 3 times), their recovery period will be longer. Average recovery times for knee surgery patients is 8.2 weeks.
It is the random type of sampling in which each and every member has equal chance of selection.
TYPES
Simple random sample with replacement.
Simple random sample without replacement.
- The region of unlikely values is the level of significance Alpha (type I error) or Beta (type II error)
- Alpha (type I error) : When the null hypothesis is originally true and we reject it
- Beta (type II error) : When the null hypothesis is originally false and we accept it ( Power of Study )
Histogram
STATISTICAL TEST
The decision to reject the null hypothesis based on statistics called test statistics.
CRITICAL VALUE
It is used to separate the sample size into two regions.
STRATIFIED SAMPLING
In stratified random sampling the start are formed based on members of shared characteristics random sample from each stratum is taken in a number proportional to the stratum’s size when compared to the population
- Collecting Data
- e.g., Sample, Survey, Observe, Simulate
- Characterizing Data
- e.g., Organize/Classify, Count, Summarize
- Presenting Data
- e.g., Tables, Charts, Statements
- Interpreting Results
- e.g. Infer, Conclude, Specify Confidence
EXAMPLE
A drug being used to treat a disease. If we reject the null hypothesis in this situation, then our claim is that the drug does in fact have some effect on a disease. But if the null hypothesis is true, then in reality the drug does not combat the disease at all. The drug is falsely claimed to have a positive effect on a disease.
A type II error would occur if we accepted that the drug had no effect on a diseases.
ROLE OF BIOSTATISTICS IN PHYSIOTHERAPY
There are three types of non random sampling
TEST OF SIGNIFICANCE
ANOVA Test
1) Convenience sampling
2) Quota sampling
3) Snow ball sampling
Significance test is the process used, by researcher, to determine whether the null hypothesis is rejected, in favors of alternative research hypothesis or not.
Z-test:
This test is applicable in both case that is parametric and non parametric.
When the association of more than 2 samples are checked than it is applicable as parametric.
When we check out the association more than 2 population mean than it is applicable as non parametric
PROPERTIES OF TEST OF SIGNIFICANCE :
It is the heart of analytical statistics depend on the role of chance.
It is divided into two types
It is used to check the association of sample with its its relevant population.
Sample size must be greater than 30.
Example:
The mean blood sugar level of 71 pt of septicemia was 160 with s.d of 0.9 and the mean blood sugar level of all pts in hospital was 122.
- Parametric test
- Non Parametric test
Chi square test
Types of Chi Square Test:
Test of significance that makes assumption s about the parameters of population distribution(s)from which ones data are drawn.
A study was conducted among the population of 5000 out of which 2000 were smokers and 3000 were non smokers .Among smokers 84 had develop lungs cancer while on the other hand 87 among non smokers had develop lungs cancer. To check the association b/w smokers & lungs cancer.
Test of significance used to check the association of two variables b/w contingency table.
Chi-square tests enable us to compare observed and expected frequencies objectively
Types of parametric test:
- Chi square test
- T test
- Z test
- Anova test
- Row X column chi square test
- Fisher Exact chi square test
- McNamara chi square test
- Maental Haezal chi square test
- Chi square test for trends
- Test of homogeneity.
The Formula for calculating chi-square (χ²) is:
Types Of Non Parametric Test :
- Wilcoxon signed rank test
- Wilcoxon rank test
- Spearmans correlation test
For Example:
T-Test or Student TEST:
Two sample T-Test:
Test of significance used to compare the sample mean with the population mean to check weather the observed value is differentiate or not.
In T-Test or Student the sample size must be less than 30.
FORMULA:
The following example that the mean values obtained in a laboratory test comparing hip and lower back flexion of randomly taken males and females. The following measurements in centimeters were obtained by using specific test.
A test used to compare two population means based on independent samples from two populations or groups.
The Process
Paired T-Test:
A significant test used to compare two variables on same individuals.
Sample size should be less than 30.
For example:
A group of 19 people who suffered from frozen shoulder , initially this group was treated with muscle energy technique for a month.MMT readings that came before and after treatment are:
Use Of Statistical Techniques in Physical Therapy
10 most common statistical techniques used in Physical Therapy are as follows
- Descriptive statistics
- One-way analysis of variance (ANOVA)
- t test, factorial ANOVA,
- infraclass correlation
- appropriate post hoc analyses
- Pearson correlation
- Regression
- Chi square
- nonparametric tests analogous to the t test
Areas Of Physical Therapy
Physiotherapy contributes to the health and well-being of people in a variety of ways in a range of different settings such as in hospital, GP surgeries, at home or in private practice. Others may be employed in the workplace, in schools, sports clubs and leisure centers or care homes.
- Working with people of all ages to increase activity levels, improving general health and addressing related conditions such as obesity
- Preventing people incurring injury in work and helping them to return to work after a period of incapacity, for example as the result of a musculoskeletal disorder like back pain
- Preventing and treating sports injuries - from elite sportsmen and women, such as footballers or Olympic athletes, to those of us who injure ourselves in leisure activities such as gardening
- Supporting women with ante- and post-natal care, exercise and posture and rehabilitation following gynecological operations
- Providing rehabilitation services to help people recover from a heart attack or a stroke
- Supporting children with developmental movement problems or learning difficulties
- Supporting people with long-term conditions, such as Chronic Obstructive Pulmonary Disease (COPD) or diabetes, to manage their condition and maintain their independence
- Treating elderly patients with arthritis or helping them to recover from a fall and prevent it happening again, supporting them to maintain mobility and independence
- Contributing to the health and well-being of people with mental health problems
- Working as part of palliative care teams to help patients and their carers manage the condition, including pain relief.
ANY QUESTIONS ?? ...