Biometry is the statistical analysis of biological data; methods include descriptive statistics and inferential statistics.
The application of statistical analysis to biological data is called biometry. It includes descriptive and inferential statistics. These statistics are particularly useful in communicating the results of biological experiments and research.
Descriptive statistics are used to describe a collection of data. It summarizes the population data by describing what was observed in the sample numerically or graphically. Numerical descriptors include mean (average), median (middle value) and standard deviation for continuous data types like heights or weights, while frequency and percentage are more useful in terms of describing categorical data. Different descriptive statistics should be used depending on the data set – for example, the mean is much more sensitive to outliers than the median, so the median can be a more meaningful descriptor of datasets that include outliers.
Inferential statistics use patterns in the sample data to draw inferences about the population represented, accounting for randomness. These inferences may take the form of answering yes/no questions about the data or hypothesis testing, estimating numerical characteristics of the data or estimation, describing associations within the data or correlation, and modelling relationships within the data or regression analysis. Inference can extend to forecasting, prediction and estimation of unobserved values either in or associated with the population being studied. The methods in inferential statistics include analysis of variance (ANOVA), t-test, correlation test, and nonparametric test. A correlation test, for example, measures whether and how two variables are related. A positive correlation (with a correlation coefficient >0, <1) indicates that as one variable changes, the other variable changes in the same direction. A negative correlation (with a correlation coefficient <0, >-1) indicates that as one variable changes, the other variable moves in the opposite direction. For example, we would say that weight and height are positively correlated because one tends to increase as the other increases.
A research finding is considered meaningful if it passes a test of statistical significance. Statistical significance is the measurement of the likelihood that a finding is due to chance, or due to a the factor of interest.
These biometric statistics are used to describe the results of research studies across many fields, including Biology, and Psychology and Sociology. In Biology research, model organisms are often used to directly test the effects of a specific variable (ie disease-causing agent, genetic mutation). Two common types of experiments ask whether a variable is necessary for a specific biological process, and whether a variable is sufficient to cause the effect. In necessity experiments, the variable is removed and the process observed. In sufficiency experiments, the effect of that factor alone on the biological process of interest is tested. These kinds of experiments are important for proving causality, a key criteria drawing scientific conclusions.
There are several main definitions of research designs found in Psychology and Sociology research: Ethnographic research studies people or cultures in their own environment, in real social settings. In experimental research, variables are manipulated by researchers to compare control and experimental groups or conditions.
Studies can be cross-sectional, meaning that they look at one point in time, or longitudinal, meaning that they follow a specific population at multiple time points.
In all types of research, an independent variable is a variable whose variation is controlled by researchers, and usually goes on the X-axis of a graph. A dependent variable is the variable whose variation is unknown, and is being measured, and usually goes on the Y-axis of graph. In order to study a relationship between two variables, both of them must be change, and be recorded. If multiple measurements of the same variable are positively correlated, that supports the use of those measurements. Situational variables are conditions in the environment or setting of a research study that could alter the outcome (for example, the temperature of the room, the gender presentation of the researcher). It’s important to take situational variables into account when analyzing data.
In all types of research, research bias can occur if the study is set up with systematic errors in testing or sampling that make a specific outcome more likely. Sampling bias, for example, occurs when the study population is not representative of the general population of interest. Response bias in survey studies occurs when a certain people are more likely to respond to the survey. Observer bias occurs when there is bias on the part of the specific researcher – this could occur because of the researcher’s prior knowledge of the study, for example.
Research bias reduces the external validity of the findings, meaning that the conclusions from the study are less likely to apply to the general population of interest. It is important that findings are externally valid, so that they generalize outside of the study.
With all research involving human subjects, scientists must take steps to ensure that ethical guidelines are considered. For example, all subjects must participate in research studies willingly and have the freedom to withdraw from the study at any time.
Khan Academy
The role of alcohol abuse in pancreatitis
Race socioeconomic status and nutrition
Why do we believe that there are universal emotions
Marijuana usage as social behavior
Miller’s law chunking and the capacity of working memory
Gender differences in symptoms of major depressive disorder
Demographic disparities in food resources
Health after trauma correlates of PTSD
Socioeconomic gradients in health
Educational attainment, income, and psychiatric disorders
Can tickling help us understand some symptoms of schizophrenia?
Reciprocal altruism vampire bats and relatedness
Driving and talking on a cell phone
MCAT Official Prep (AAMC)
Practice Exam 1 C/P Section Passage 1 Question 2
Official Guide B/B Section Passage 6 Question 24
Biology Question Pack, Vol. 1 Passage 10 Question 66
Biology Question Pack, Vol. 1 Passage 10 Question 69
Biology Question Pack, Vol. 2 Passage 6 Question 33
Biology Question Pack, Vol. 2 Passage 6 Question 34
Biology Question Pack, Vol. 2 Passage 6 Question 38
Biology Question Pack, Vol 2. Passage 8 Question 55
Biology Question Pack, Vol 2. Passage 10 Question 70
Section Bank B/B Section Passage 4 Question 26
Section Bank B/B Section Passage 5 Question 36
Section Bank B/B Section Passage 6 Question 45
Section Bank B/B Section Passage 7 Question 50
Section Bank B/B Section Passage 12 Question 91
Practice Exam 1 B/B Section Passage 1 Question 2
Practice Exam 2 B/B Section Passage 5 Question 24
Practice Exam 2 B/B Section Passage 7 Question 33
Practice Exam 2 B/B Section Passage 7 Question 36
Practice Exam 2 B/B Section Passage 9 Question 48
Practice Exam 3 B/B Section Passage 6 Question 36
Practice Exam 4 B/B Section Passage 10 Question 55
Online Flashcards Sociology Question 20
Online Flashcards Sociology Question 23
Online Flashcards Sociology Question 24
Online Flashcards Sociology Question 25
Official Guide P/S Section Passage 1 Question 5
Official Guide P/S Section Passage 2 Question 9
Official Guide P/S Section Passage 4 Question 17
Section Bank P/S Section Passage 5 Question 37
Section Bank P/S Section Passage 5 Question 38
Section Bank P/S Section Question 66
Section Bank P/S Section Question 67
Section Bank P/S Section Passage 9 Question 68
Section Bank P/S Section Passage 9 Question 72
Section Bank P/S Section Passage 11 Question 89
Section Bank P/S Section Passage 12 Question 91
Sample Test P/S Section Passage 2 Question 8
Sample Test P/S Section Passage 5 Question 22
Sample Test P/S Section Passage 5 Question 32
Sample Test P/S Section Passage 8 Question 43
Sample Test P/S Section Passage 10 Question 52
Sample Test P/S Section Passage 10 Question 54
Practice Exam 1 P/S Section Passage 2 Question 10
Practice Exam 1 P/S Section Question 13
Practice Exam 1 P/S Section Passage 4 Question 21
Practice Exam 1 P/S Section Question 27
Practice Exam 1 P/S Section Question 28
Practice Exam 1 P/S Section Question 45
Practice Exam 1 P/S Section Question 47
Practice Exam 1 P/S Section Passage 10 Question 53
Practice Exam 1 P/S Section Question 58
Practice Exam 2 P/S Section Passage 4 Question 22
Practice Exam 2 P/S Section Question 29
Practice Exam 2 P/S Section Passage 6 Question 31
Practice Exam 2 P/S Section Passage 6 Question 32
Practice Exam 2 P/S Section Question 46
Practice Exam 2 P/S Section Passage 9 Question 52
Practice Exam 2 P/S Section Question 57
Practice Exam 3 P/S Section Passage 1 Question 3
Practice Exam 3 P/S Section Passage 2 Question 8
Practice Exam 3 P/S Section Passage 3 Question 15
Practice Exam 3 P/S Section Passage 4 Question 19
Practice Exam 3 P/S Section Passage 5 Question 25
Practice Exam 3 P/S Section Passage 7 Question 36
Practice Exam 3 P/S Section Passage 8 Question 40
Practice Exam 3 P/S Section Passage 10 Question 53
Practice Exam 4 P/S Section Question 9
Practice Exam 4 P/S Section Passage 3 Question 13
Practice Exam 4 P/S Section Passage 5 Question 21
Practice Exam 4 P/S Section Question 28
Practice Exam 4 P/S Section Passage 6 Question 30
Practice Exam 4 P/S Section Passage 7 Question 35
Practice Exam 4 P/S Section Passage 7 Question 36
Practice Exam 4 P/S Section Passage 10 Question 54
Practice Exam 4 P/S Section Passage 10 Question 55
Key Points
• Biometry is the statistical analysis of biological data; statistical methods include descriptive and inferential statistics.
• Descriptive statistics summarize the population data by describing what was observed in the sample numerically or graphically; it commonly includes mean, standard deviation, frequency, and percentage.
• Inferential statistics use patterns in the sample data to draw inferences about the population represented, accounting for randomness; the methods include analysis of variance (ANOVA), t-test, Correlation test, and Nonparametric test.
- Biology research often uses model organisms to test the necessity and sufficiency of variables on biological processes
- Human subjects research can include surveys methods, ethnographic research and experimental research that can be cross-sectional or longitudinal.
- Experimenters manipulate independent variables, to study their effect on dependent variables.
- Regardless of the method, all research must adhere to ethical guidelines.
- Research bias occurs when the design of the study favors a certain outcome. This decreases the generalizability of the findings, and therefore the impact of the research.
Key Terms
Inference: a conclusion reached based on evidence and reasoning
Sample: a subset of a population selected for measurement, observation, or questioning to provide statistical information about the population
Statistic: a numerical characteristic of the sample; a statistic estimates the corresponding population parameter.
Biometry: the application of statistical analysis to biological data
Descriptive statistic: a summary statistic that quantitatively describes or summarizes features from a collection of information
Inference statistics: uses data analysis to deduce properties of an underlying distribution of probability from a data set
ANOVA: analysis of variance is a collection of statistical models used to analyze the differences among group means in a sample
T-test: a type of inferential statistic used to determine if there is a significant difference between the means of two groups
Correlation test: is a statistical technique that can show whether and how strongly pairs of variables are related
Control group: In an experiment the group does not receive treatment by the researchers and is then used as a benchmark to measure how the other tested subjects do.
Statistical significance – the measurement of the likelihood that a finding is due to chance, or due to a the factor of interest.
Model organism: a species commonly used for lab experiments, well-studied and easily maintained in the lab
Necessity and sufficiency: scientific criteria that are met by doing specific experiments. Necessity is tested by removing the variable of interest, sufficiency is tested by observing the effect of the variable of interest alone
Causality: a scientific criteria, which can only be met if experiments prove the dependence of the results on a specific variable
Experimental research: research in which scientists manipulate variables to test the difference between an experimental and control group
Ethnographic research: research that studies people or cultures in their own environment
Cross-sectional research: describes a research study done at a specific point in time
Longitudinal research: describes a research study that follows the population or group of interest at multiple time points
Independent variable: variable that is controlled by researchers
Dependent variable: variable that is unknown and being measured in a study
Research bias: occurs when the design of a research study favors a certain outcome
Sampling bias: occurs when the study population is not representative of the general population
Response bias: occurs when certain people are more likely to respond to a research surveys than others
Observer bias: occurs when the researcher themself is biased towards a specific outcome
External validity: describes if the findings from a research study are applicable to the general population
