1- Introduction to Biostatistics

Page 1: Introduction to Biostatistics

• Biostatistics: The application of statistical methods to the field of biological sciences and medicine.

Page 2: Overview of Statistics and Biostatistics

• Statistics: Art and science of data that involves:

  • Planning research

  • Collecting data

  • Describing data

  • Summarizing and presenting data

  • Analyzing data

  • Interpreting results

  • Making decisions or discovering new knowledge

Page 3: Application of Biostatistics

• Biostatistics employs statistical tools across various fields including:

  • Business

  • Education

  • Psychology

  • Agriculture

  • Economics

• It specifically refers to the application of statistical methods to biological and medical data.

Page 4: Goals of Biostatistics

• Enhance the intellectual content of data.

• Organize data into comprehensible formats.

• Base validity on the test of experience.

Page 5: The Cycle of Statistical Investigation

• Identify real problems and foster curiosity.

• Pose a specific question.

• Design methods for data collection.

• Collect data and interpret the results:

  • Analysis and summary of data to address the original question.

Page 6: Understanding Data

• Data: Raw material for statistics; defined as figures obtained by:

  • Counting (e.g., patient numbers)

  • Measurement (e.g., temperature, weight, blood pressure).

Page 7: Sources of Data

• 1. Routinely Kept Records:

  • Hospital medical records are rich sources of patient data.

Page 8: External Data Sources

• 2. External Sources:

  • Published reports, data banks, and research literature may contain pre-existing data relevant to research questions.

Page 9: Surveys as Data Sources

• 3. Surveys:

  • Can be used to gather specific information (e.g., transportation modes for clinic visits).

Page 10: Experimental Data Collection

• 4. Experiments:

  • Data is collected as a result of experiments (e.g., testing strategies for patient compliance).

Page 11: Variables in Measurement

• Variable: A characteristic that can take on different values across subjects, such as:

  • Heart rate

  • Heights of adult males

  • Weights of preschool children

  • Patient ages.

Page 12: Constants in Observation

• Constant: An observation that does not vary (e.g., number of fingers, number of eyes).

Page 13: Types of Data Classification

• Different classifications for variables:

  • Categorical Measurements: Unordered categories.

  • Ordinal Measurements: Ranked categories.

  • Quantitative Measurements: Ordered intervals with equal spacing.

Page 14: Quantitative versus Qualitative Variables

• Quantitative Variables: Numeric scales (e.g., height, weight).

• Qualitative Variables: Characteristics that may not be measured but can be ranked (e.g., sex, blood group).

Page 15: Discrete and Continuous Variables

• Discrete Variable: Has gaps in possible values (e.g., daily hospital admissions).

• Continuous Variable: Can take any value within a given interval (e.g., height).

Page 16: Qualitative Variables

• Qualitative Variables (Categorical or Nominal): Often explored in categories.

Page 17: Binary Qualitative Variables

• Binary Variables (Two Categories): Attributes with a yes/no or presence/absence classification (e.g., male/female, disease/no disease).

Page 18: Qualitative Variables with Multiple Categories

• 1. Nominal: Variables without a rank (e.g., blood group).

• 2. Ordinal: Variables that can be ordered (e.g., stages of cancer).

Page 19: Conversion of Variables

• Quantitative variables can be converted into categorical variables for analysis.

Page 20: Examples of Quantitative Variable Categorization

• Systolic Blood Pressure Categorization:

  • 140 mm Hg: Hypertensive

  • 90-140 mm Hg: Normal

  • <90 mm Hg: Hypotensive

• Blood Glucose Categorization:

  • 120: Hyperglycemia

  • 80-120: Normal

  • <80: Hypoglycemia

Page 21: Avoiding Inaccuracies

• Address two main types of inaccuracies:

  • Imprecision: Random variability in results.

  • Bias: Systematic deviation from the truth.

Page 22: Understanding Population

• Population: The total collection of values of a variable that is of interest (e.g., weights of all children in a school).

  • Populations can be finite or infinite.

Page 23: Understanding Samples

• Sample: A subset taken from a population (e.g., weights of a fraction of children).