BIOM301 Chapter 1 Statistics 9 4 2012 Goals Overview of the field of statistics Introduce several basic vocabulary words used in studying statistics population variable statistic Learn basic process of sampling data What is Statistics Statistics the science of collecting describing and interpreting data o Two areas of statistics Descriptive collection presentation and description of sample data Inferential making decisions and drawing conclusions about populations o Descriptive and Inferential statistics have different roles in the scientific narrative Results Descriptive Discussion Inferential 8 Basic Terms Population a collection of individuals objects or events whose properties are to be analyzed defined by the researcher o A statistical population may not equal a biological population Ex Reproduction Sample a subset of a population o sample size n population size N Experimental Unit element 1 individual or object being studied in the population Variable a characteristic of an individual experimental unit Data Value the value of the variable associated with one experimental unit Data the set of values collected for the variable in a sample Statistic a numerical value summarizing the sample data Parameter a numerical value summarizing all the data of an entire population ONE GOAL OF STATISTICS ISTO MAKE AN INFERENCE FROM SAMPLE TO POPULATION Variables can be classified into several categories Quantitative Numerical Value ex Height Weight Length etc o Discrete Whole numbers only makes sense ex of Eggs of Zebras o Continuous Have to round off to record value ex Height Weight Age in Days Qualitative Attribute ex Gender color names etc o Nominal Names ex Species names colors No relative value o Ordinal Ordered with relative value ex Small medium large or level of satisfaction The World is Variable We want to measure and characterize variability in a SAMPLE This requires that we get a GOOD sample from the population o In order to make an inference from the sample to the population we need a GOOD sample What is a good sample A good sample would accurately reflect the population 4 components of a good sample o Random samples collected in such a way that every experimental unit has an equal chance of being tested Method of chance is used to determine which experimental unit will be chosen o Independent the selection of 1 experimental unit does NOT influence the selection of another o Covers entire population sample must represent the entire population that could be sampled o Not biased collecting samples that DON T vary in some systematic way from the population NO experimental unit DIRECTION Involves the use of random numbers that are assigned to every member of a population Random Sampling Use random numbers to choose experimental units No way you have influenced choice of subjects Requires element of chance Judgment Sampling Often random sampling is not always used because it is narrowly defined and not always possible to do Requires carefully thought o Are assumptions about independence no bias and covers whole population still reasonably met However by definitions Judgment samples are NOT random samples You never really know if your sample is a good one Size of a sample is important BUT small samples are NOT necessarily bad samples small samples may give values close to the true population value large samples have more information and provide a better guess of the true population value Methods Used to Collect Data Manipulative Study Experiment o Investigator controls or modifies the environment and observes the effect Observational Study Survey o The investigator does not modify the environment Type of Study Also Influences Inference Surveys do NOT get at cause and effect Need to ask the extent of the population you can infer to