Introduction to Biostatistics

Introduction to Biostatistics

What statistics means

Statistics is part of everyday life, not just a mathematical subject. People encounter statistical information in annual reports, censuses, surveys, museum records, and social-media ratings. It can also inform everyday decisions, such as choosing a product based on customer feedback or understanding how common a disease is.

The word statistics is used in two related ways:

• Quantitative information: Information expressed as numbers or quantities.
• Methods for handling that information: Collecting, organizing, summarizing, describing, and drawing conclusions from data.

Descriptive and inferential statistics

The lecture distinguishes two main branches:

• Descriptive statistics organizes and summarizes data to describe the same group from which the data were collected. For example, reporting the grade distribution of one class describes that class; it does not automatically support conclusions about the whole university.
• Inferential statistics uses data from a sample to draw conclusions about the larger population from which the sample was taken. For example, researchers might measure the heights of a sample of university students and use those measurements to estimate the average height of all students.

What biostatistics is

Biostatistics is the branch of statistics used to interpret scientific data in biology, public health, and other health or biomedical sciences. Research in these fields relies on statistical procedures to analyze data and support conclusions.

Why statistical literacy matters

The lecture gives two main reasons:

1. To read and assess scientific literature. Understanding statistical terms and methods helps readers judge how a study reached its conclusions. The lecturer uses a bird-survey example: a reported chi-square test, its degrees of freedom, and a p-value indicate that the researchers compared the frequencies of first-year and older birds. Without basic statistical knowledge, it can be difficult to evaluate what such a result means.

2. To conduct and report research. Researchers need statistics to plan investigations, analyze results, and present findings credibly. Statistical methods should be considered before data collection, not chosen afterward simply to make results appear acceptable.

Role of statisticians

Statisticians can:

• Advise on the design of an experiment or survey before data are collected.
• Analyze the resulting data using suitable statistical procedures.
• Help interpret and present findings to researchers and decision-makers.

Step-by-Step Approach to Analyzing Biological Data

1. Specify the biological question. State clearly what the research is trying to answer.

2. Formulate biological hypotheses. Express the question as biological null and alternative hypotheses.

3. Formulate statistical hypotheses. Translate the biological question into statistical null and alternative hypotheses that can be tested with data.

4. Identify the relevant variables. Decide what information must be collected to address the question. For example, a study of smoking and lung cancer might record smoking status or history and whether individuals have lung cancer.

5. Classify the variables. Determine what kind of data each variable represents. The lecture mentions distinctions such as ordinal, continuous, and discontinuous variables, as well as measurement scales such as interval and ratio.

6. Choose an appropriate statistical test. Select a method that fits the research question, hypotheses, variables, and data. For instance, a chi-square test of independence may be appropriate for comparing frequencies between smoking-status and lung-cancer groups.

7. Conduct the experiment or collect the data. Carry out the planned investigation only after considering the question, hypotheses, variables, and proposed analysis.

8. Check whether the data meet the test’s assumptions. If the data or circumstances do not suit the chosen test, select a more appropriate one. New relevant variables—such as age in a study of lung cancer—may require changes to the analysis.

9. Analyze and interpret the results. Apply the selected method and integrate the findings into an interpretation.

10. Communicate the results effectively. Present findings clearly, often using tables or graphs suited to the data.

The overall sequence is: identify the biological question → plan the study and analysis → collect data → analyze results → present findings.

Suggested Learning Resources

The lecturer recommends:

• Fowler and Cohen’s Practical Statistics for Field Biology, described as suitable for beginners and grounded in biological examples.
• McDonald’s Handbook of Biological Statistics, described as an accessible introductory resource.
• Online statistical-calculation resources: statpages.org, socialstatistics.com, statistics.com, and vassarstats.net.

Speakers and Sources Featured

• Speaker: The lecturer/instructor; the video is attributed to the Benish Ali channel.
• Books mentioned: Fowler and Cohen, Practical Statistics for Field Biology; McDonald, Handbook of Biological Statistics.
• Websites mentioned: statpages.org, socialstatistics.com, statistics.com, and vassarstats.net.