The Scientific Method + Biostats Study Guide

Objectives

• Understand the steps of the scientific method.

• Learn how to display collected data in charts and graphs.

• Comprehend the use of variables in controlled experiments and their relevance.

• Understand how biostatistics can be used to assess the validity of data.

• Analyze charts and graphs to draw conclusions from collected data.

• Know how to create a controlled experiment and select the best graph to display data.

The Scientific Method

Overview

The scientific method is a systematic approach used by scientists to investigate natural phenomena, acquire new knowledge, or correct and integrate previous knowledge. It is not a strictly linear process; rather, it is iterative and often involves revisiting earlier steps as new information emerges.

• Steps of the Scientific Method:

  1. Ask a question

  2. Formulate a hypothesis

  3. Perform experiments

  4. Collect data

  5. Draw conclusions

• In practice, these steps are repeated and refined as new data and ideas are generated.

Good Scientific Questions

• Lead to further discussion and investigation.

• Include measurable values.

• Identify independent and dependent variables.

• Example of improvement: Instead of "Is more fertilizer better for plants?", specify measurable outcomes and variables.

Hypotheses

• Null Hypothesis (H0): States that any observed difference is due to chance; there is no significant relationship between variables.

• Alternate Hypothesis (H1): States that there is a significant relationship between variables; the difference is not due to chance.

• Only one hypothesis can be supported by the data.

Characteristics of a Good Hypothesis

• Is a statement, not a question.

• Plausible and testable.

• Falsifiable (can be proven false).

• Defines measurable variables.

• Based on background research or prior knowledge.

Hypothesis vs. Prediction

Prediction	Hypothesis
A statement estimating what will occur at the end of an experiment.	A proposed explanation for an observation, including reasoning, to be tested by experiment.

Scientific Laws and Theories

• Natural Law: A set of repeatable and verifiable observed phenomena (e.g., law of gravity).

• Scientific Theory: A tentative and falsifiable explanation of a set of observations that has been repeatedly verified (e.g., theory of evolution).

• Theories and hypotheses cannot be proven true, only supported or falsified by evidence.

Experimental Design

Variables

• Independent Variable: The variable that is manipulated by the researcher.

• Dependent Variable: The variable that is measured (the data collected).

• Constants: Other variables that must be kept the same to ensure a fair test.

Control and Experimental Groups

Group	Description
Control Group	Does not receive the treatment (independent variable); serves as a baseline for comparison. Negative control shows what happens without treatment; positive control shows a known response.
Experimental Group	Receives the treatment (independent variable); used to test the effect of the variable.

Types of Data

• Quantitative Data: Numerical, measurable, suitable for statistical analysis.

• Qualitative Data: Non-numerical, subjective, not suitable for statistical analysis.

Data Collection and Tables

• Use tables to record data with clear titles and correct metric units.

• Independent variable in the first column (ascending order), dependent variables in subsequent columns.

Biostatistics

Definition and Importance

Biostatistics involves the application of statistical methods to biological research, including experiment design, data collection, analysis, and interpretation.

Types of Biostatistics

• Descriptive Statistics: Describe data using numbers (sample size, minimum, maximum, mean, standard deviation, standard error, confidence intervals).

• Graphical Representation: Visualize data trends (histograms, bar charts, scatter charts, line graphs).

• Association Statistics: Identify relationships (R2, chi-square, t-test).

Descriptive Statistics

• Minimum: Lowest value in the data set.

• Maximum: Highest value in the data set.

• Range: Difference between maximum and minimum values.

• Mean: Central value of a data set. $\bar{x} = \frac{\sum x}{N}$

• Standard Deviation (SD, s): Measures how much values deviate from the mean. $s = \sqrt{\frac{\sum (x - \bar{x})^2}{N-1}}$

• Standard Error (SE): Measures how close the sample mean is to the true mean. $SE_{\bar{x}} = \frac{s}{\sqrt{N}}$

• 95% Confidence Interval: Range within which the true mean is expected to fall 95% of the time $(+/-2SE)$.

Normal Distribution (Bell Curve)

• Many biological variables are normally distributed, with most values clustered around the mean.

• Standard deviation indicates the spread: ~68.3% of data within ±1 SD, ~95.5% within ±2 SD, ~99.7% within ±3 SD.

Significance and Error Bars

• Error bars on graphs represent variability (SD or SE).

• If error bars overlap, differences are not statistically significant; if they do not overlap, differences are likely significant.

• Statistical tests (e.g., t-test, chi-square) are used to determine if observed differences are significant.

Graph Types and Their Uses

Graph Type	Purpose
Histogram	Shows distribution of data (frequency of values).
Bar Graph	Compares averages between groups.
Pie Chart	Displays data as percentages of a whole.
Line Graph	Shows changes over time (continuous data).
Scatter Plot	Shows relationship between two continuous variables.

Summary Table: Key Statistical Formulas

Statistic	Formula (LaTeX)	Description
Mean	$\bar{x} = \frac{\sum x}{N}$	Average value
Standard Deviation	$s = \sqrt{\frac{\sum (x - \bar{x})^2}{N-1}}$	Spread of data
Standard Error	$SE_{\bar{x}} = \frac{s}{\sqrt{N}}$	Uncertainty in mean
Range	$\text{Range} = \text{Max} - \text{Min}$	Difference between highest and lowest values

Conclusion

The scientific method is a dynamic, iterative process that relies on careful experimental design, data collection, and statistical analysis. Understanding how to formulate hypotheses, design controlled experiments, and analyze data using biostatistics is fundamental to scientific inquiry in biology.