Data & Sampling PDF

Data & Sampling Prof Dr Adel Al-Wehedy Prof. Dr. Mohamed El-Helaly Biomedical Research and Biostatistics (CMC 181) CONTENTS Statistics (Biostatistics) Definition Importance Types Data Variables Population and sample Sampling strategies and types...

Data & Sampling Prof Dr Adel Al-Wehedy Prof. Dr. Mohamed El-Helaly Biomedical Research and Biostatistics (CMC 181) CONTENTS Statistics (Biostatistics) Definition Importance Types Data Variables Population and sample Sampling strategies and types Statistics ( Biostatistics) is the science of collecting, summarizing, presenting, analyzing and testing data for accuracy and significance by statistical methods (depending on probability) to make inference and to take a decision. Statistics means Facts From Figures (3F). Importance of statistics Simplifies mass of figures (reduce volume of data) Presenting data. Facilitates comparison. Helps in formulating and testing hypothesis. Importance of statistics Helps in prediction, planning and administration. Helps in formulation of suitable policies. Serves in measuring the standards of health. Statistics are classified into Descriptive statistics Numerical and graphical description and summarizing of data: tables, graphs, central tendency, dispersion Analytic (inference) statistics: Inferential statistics is a technique used to draw conclusions and trends about a large population based on a sample taken from it. Data collection Data can be collected from the total population or a sample of the target population.  Data & Variables Data Vs. information Data consists of discrete observations or events that carry little meaning when considered alone and are inadequate for planning. Information is a reduced, summarized and adjusted data, to be used for comparison over time and place.  Data & Variables Primary Vs. secondary data primary data are collected directly from the individuals e.g. census data, while secondary data are obtained from outside source e.g. published primary data (reports and research).  Data & Variables Data enter and analysis Computer and software are used for data entery and analysis. After entery data should be edited or cleaned for errors and completeness. Several statistical methods were used for data analysis. SPSS, Epi-Info, SAS and excel are the commonest softwares used for data entery and analysis.  Data & Variables Variable a characteristic, observation or event which assumes different values in different individuals (item of data that can be observed or measured on individuals). Data & Variables Types of variables  Data & Variables Types of variables (A)Quantitative (numerical): have numerical value. They are sub classified into: 1. Discrete: Discrete number without fractions (separated) that are counted ( nothing in-between them) e.g. number of students, patients, heart rate, respiratory rate  Types of variables A)Quantitative (numerical): 2. Continuous: Numerical values which may have fractions and is measured on a continuous scale (uninterrupted range of values) Example; age, height, weight, blood pressure, hemoglobin, temperature. Sub classified into: Interval: Numerical values without a true zero point. 0 does not indicate a complete lack of the quantity being measured Example: degrees Celsius or Fahrenheit Ratio: Numerical values with a true zero point. 0 indicates a complete lack of the quantity being measured Example: age, height, weight,, blood pressure, distance.  Types of variables (B)Qualitative ( categorical): Non-numerical have no statement of magnitude. Discontinuous variable that describe quality. They are sub classified into: 1. Nominal: No natural order and sub classified into: Binary (Dichotomous): 2 categories: Yes/No, Gender: male or female Multinomial: > 2 categories: blood group (A, B, AB or O), diagnosis (e.g. diabetes, hypertension etc), occupation. 2. Ordinal: Can be arranged in order (ascending or descending) Example: Social class, Cancer Staging, Educational level, degree of anemia (mild, moderate, severe). Population and sample  Population and sample The Whole or theoretical population: It is the all people you want to infer or generalize the conclusion of your study, to them: (the Egyptian medical students, in millions) Because it is difficult to study the whole population ( because of time and money restriction) the researchers should find a representative sample (or subset) of that population to study.  Population and sample The Target Population: (study population, source population) It is the practical or accessible population who we actually sample from: (The NMU medical students, in thousands) The Sampling Frame: is a listing of the members of the target population from which the sample is to be drawn, using telephone directory, email addresses list,..etc: (NMU medical students email addresses) Sampling: The selection the study sample form the target population using the sampling frame It should be representative of the population in question. The Sample: It is a subset of population that is used to gain information about the entire population: (400 NMU medical students). A good sample will represent the population well. Population and sample Sampling strategies & types  Population and sample Sampling strategies & types A - Non-probability (non-random, biased) sample Every individual in the target population does not has the same chance of being represented (selected) in the sample. The results will not be correctly generalized to the whole population. Types: 1.Quata Sample 2.Convenience sample. 3.Snowball sample. Population and sample Sampling strategies & types  Population and sample Sampling strategies & types B - Probability (random, non-biased) sample Every individual in the target population has an equal chance to be represented (selected) in the sample. The results can be generalized to the whole population. Types: 1.Simple random sample. 2.Systematic (pseudo-simple) random sample 3.Stratified random sample. 4.Multistage random sample 5.Cluster sample Population and sample Sampling strategies & types Population and sample Sampling strategies & types Population and sample Sampling strategies & types Thanks