02_Basic_statistical_concepts_part1_&_2_2024_08_21_07_21_001_2.pdf

Basic statistical concepts Dr. Hassaan A. Rathore, PhD College of Pharmacy University of Hail MMI Basic definitions MCP  Statistics : The study of methods for collecting, organizing and analyzing data  Descriptive Statistics: Procedures used to organize a...

Basic statistical concepts Dr. Hassaan A. Rathore, PhD College of Pharmacy University of Hail MMI Basic definitions MCP  Statistics : The study of methods for collecting, organizing and analyzing data  Descriptive Statistics: Procedures used to organize and present data in a convenient and communicable form  Inferential Statistics: Procedures employed to arrive at broader conclusions or inferences about population on the basis of samples  Statistics: The science of collecting, classifying, analyzing, describing and presenting data as well as drawing scientific conclusions about the phenomenon being studied.  Statistics is the science of earning from data.  Statistics is a way of reasoning in order to help us understand the world around us.  Statistics involves 3 main aspects  1. Research design: Planning and designing appropriate ways of collecting data for the investigation of a particular scientific problem.  2. Descriptive statistics: Description, summarization and presentation of data using both numerical and graphical methods (also known as exploratory data analysis).  3. Inferential statistics: Drawing scientific conclusions and making predictions about a population, based on the data obtained from a sample population. It involves:  Hypothesis tests  Confidence intervals  Making an estimate about a population based on a sample In general, a researcher applies descriptive statistics to their data first then applies inferential statistics to the same data. Purpose of statistics  Purpose of statistics is to have an objective, unbiased approach to learning from data:  To see the bigger picture (so you can see the forst instead of trees)  To compare treatments or groups in order to see which one is better, bigger, more effective etc.  To look for causation (cause-and-effect relationship) or association between variables. Variables  Variable: a characteristic which varies from one subject or individual to another.  Natural variation such as weight, force, energy, light, height, color, abundance, density etc.  Study units or experimental units:  This includes the individuals or subjects (people, animals or things) about which information or measurements are recorded.  Types of variables: ME  Qualitative variable A non-numerically valued variable (quality or attribute) e.g., color, gender (male/female), marital status, likes or dislikes, hobby, yes, no or indefferent to something, types of animals, languages etc.  Quantitative variable: numerically valued variable Weight, height, pH, distance, number of people etc  MCQ  Population: The complete set of actual or potential elements about which inferences are made.  Sample: A subset of the population selected using some sampling method.  Variable: An attribute of elements of a population or sample that can be measured. e.g. height, weight, IQ, hair color.  Data: Values of variable that have been observed.  Terminology  Quantitative / qualitative  Continuous – usually based on measurement  Categorical – usually based on subjective grouping  Parametric – data follows certain type of distribution that can be generalized/described using a particular statistic  Non-parametric– data does not follow any particular type of distribution and usually generalized/described using alternative statistic than parametric data  Numerical - number  Nominal - name  Categorical - grouped individuals in a categories DATA  DATA Just like variables, data can be classified as: Qualitative data: values of a qualitative variable Quantitative data: values of a quantitative variable Discrete data: values of a discrete variable Continuous data: values of a continuous variable  Types of data Binary  Yes / No  Present / Not present  Diseased / not diseases  Sex : male/female  Upper arch / lower arch  Right / left of jaws  Usually coded as 0 / 1 or 1 / 2 Types of data Continuous  Height (m, cm, feet/inches)  Weight (kg, pounds)  Age (years, months)  Blood pressure (mmHg)  Income (SR)  QoL score (unit)  Dmft/DMFT?  recorded as the original measurement scale  Types of data Time based data - hybrid data  Combined both continuous and binary data  E.g. time taken for AIDS symptoms to be first observed  Time – continuous  AIDS – present/not  E.g. length of stay in hospital after an admission into a hospital  Interest is more on the TIME. The occurrence of interest is an indicator to specify what the time is for.  recorded as the original time scale  Population size, sample size & inferential statistics Population: The entire collection of all individuals or terms under consideration in a statistical study. Population size (N): Total number of individuals or items in the population under study. Census: Collecting data about the entire population - often too expensive and mostly impossible. Sample: That part of the population from which information is obtained. -A sample is a relatively small number of observations from the population being investigated -It is a subject of the population -Usually it is impossible or to measure a variable in whole population so a sample of individuals is measured. Sample size (n): Number of observations or measurements in a single sample. Inferential statistics: Uses information from a sample to make decisions, conclusions and predictions about entire population. FEE i Example 1 talks  Suppose I would like to know the average of Saudi income. n= 1000 candidates are selected and their incomes are obtained. The average income of selected Saudis is SAR5,750. Describe population, sample, parameter and statistic in the above example. Example 2  Suppose I would like to know the proportion of my students who prefer sending emails instead of making an appointment to come to my office. n=100 of my students are selected and their preferences are obtained. Suppose it is found that 75 out of 100 prefer emails. Describe population, sample, parameter, statistic. Suppose I would like to know the proportion of my students who prefer sending emails instead of making an appointment to come to my office. n=100 of my students are selected and their preferences are obtained. Suppose it is found that 75 out of 100 prefer emails. Describe population, sample, parameter, statistic.  Thank you