Computational Biology Unit 1

Statistics

the study of methods to describe and measure aspects of nature from samples

Sample

a smaller subset of individuals selected from the population

Population

the entire collection of individual units a researcher is interested in

estimation

the process of inferring an unknown quantity of a population using sample data

estimate

a quantity calculated from a sample

statistic

a quantity calculated from a sample (approximate value)

parameter

a quantity describing a population (true value)

hypothesis testing

using data to evaluate evidence for or against a specific claim (hypothesis) about a population

uncertainty

the magnitude of departure from the true value

accuracy

the extent to which estimates are centered on the true value

precision

the extent to which estimates are tightly grouped

sampling error

the chance difference between an estimate and the true population parameter

bias

a systematic discrepancy between an estimate and the true population parameter

bias vs. accuracy

random sampling

each member of a population has an equal and independent chance of being selected

equal

every unit in the population has the same probability of being selected

independent

the selection of one unit must not influence the selection of any other unit

example of sample bias: “sample of convenience”

researcher samples from population that is easily available to the researcher

example of sample bias: “volunteer bias”

a systematic difference between volunteers and the non-volunteer population. volunteer population is not representative of the general population

variable

any characteristic that differs among individuals

data

the measurements of variables for a sample

categorical variables (qualitative)

describe members of a group by characteristic

nominal variable

categorical variable whose categories have no discernible order

ordinal variable

a categorical variable whose categories have an inherent order

numerical variables

measurements are in numbers

continuous variable

a numerical variable that can take on any real-number value within a range

discrete variable

a numerical variable characterized by indivisible units

dependent variable

response variable; is affected by changes in the independent variable

independent variable

explanatory variable; predicts or affects the response variable (outcome)

observational study

researcher has no control over which individuals fall into which groups, can only point to correlation

experimental study

a researcher randomly assigns individuals to different treatment groups; allows for determination of cause and effect

Florence Nightingale’s wedge diagram

1858, visualized causes of death of troops in the crimean war. showed that infectious disease was a larger killer than combat wounds

primary purposes of graphs

analysis and presentation

Four principles of a good graph

1. present the data

2. patterns are clear

3. magnitudes are honest

4. graphics are clear