Chapter 1: What is Statistics?

Randomized Block Design

Individuals are matched based on a specific variable. The subjects are them put into blocks of the same size as the number of treatments and then each block is assigned to different treatment groups randomly

Splash

The user just flops and splashes around to no effect at all...

Data

a collection of organized info that represents a certain phenomenon of interest

Parameter

a numerical measure that describes the outlined characteristic of the population such as central tendencies, spread and shape.

Statistic

a numerical measure that yields an estimate of a population parameter. A numerical measure that uses data from the sample to estimate the outlined characteristic of the population.

Sensitive

a statistical measure is "this" if the computed value changes readily even if a single observed data value is different.

Robust

a statistical measure is (this) if the decision is not strongly dependent on the assumptions

Treatment

any condition set forth that is applied to the individual or subject in an effort to determine differences among a variety of treatments as compared to each other or a control group

Instrument

any means by which info is gathered or measured, such as an exam, survey, or other rulers, barometers, thermometers, etc

Experiment Design

art of planning and executing experiments designed to gather info from the population,N, in such a way as to ensure the samples,n, are representative of the population, N

Extreme

characteristic farthest removed from the ordinary

Population data

complete collection of info from all of the individuals or subjects of interest in a given study

Outliers

data within a distribution of data but outside the overall pattern of the graph; extreme values that can distort the interpretation of data by creating misleading statistics

Validity

degree of accuracy to which a study reflects the specific concept or characteristic that the analyst or researcher is attempting to measure

Internal Validity

degree to which one can draw valid conclusions about the causal effect between variables

External Validity

degree to which one can extend the finding that are relevant to subjects and settings outside those included in the experimental design

Sample

denoted by (n), is a partial collection of info for only some of the individuals or subjects of interest in a given study opposed to a census(N)

Shape

describes the symmetry or lack thereof; a measure of the relationship between various measures that indicate the form or silhouette of the distribution

Observational Study

designed to observe without interference from the observer in that every effort is made not to sway the subject response or lead a subject in their response

Variable

distinct characteristic of an individual to be observed and or measured; can be qualitative or quantitative

Simple Random Sample

each individual has an equal likely chance of being selected, all groups of size n have an equally likely chance

Random Error

error in observed data due to nothing more than chance

Statistically Significant

event is this if its occurrence is unlikely to happen by chance

Systematic Sampling

every kth individual or item is measured

Explanatory Variable

extraneous variables that have been measured, but are not the primary variable of interest; they are used to understand the behavior of the response variable (independent)

Block

group of individuals stratified based on similar characteristics and given treatment

Cluster Sampling

groups are based on pre-existing groups that is arbitrary to the individual and not based on any characteristic of the individual

Confounding Variable

have been easured and are significantly contributing variables; however their independent contributions to the subject response are indistinguishable and are not deemed significantly contributing in the larger model

Blind Experiment

individual subjects do not know the treatments they receive; researchers do

Stratified Sampling

individuals are first grouped by specific characteristics such as gender and then samples are taken from each group or strata

Block Design

individuals are grouped into categories or blocks and then test blocks are treated as experimental units

Convenience Sampling

individuals are selected based upon ease of access. Such sampling techs are prone to bias

Measure

involves any standard of comparison, estimation, or judgment; property of an individual given a numerical value; a quantity, a count, a rate...

Inferential Statistics

involves methods of analyzing and interpreting descriptive statistics to draw conclusions regarding a particular characteristic in the population with a certain degree of assurance based on a preset level of significance and specified assumptions

Control Group

is a group created for the sake of comparison. This group can be one of the treatment groups or a group given a placebo

Distribution

list of all the values recorded in a sample; that is, the observed outcomes and their frequency

Ordinal Measure

measure a characteristic of an individual by the rank order of the entities measured or implied.

Correlation

measure of association between a response variable and an explanatory variable; measures the strength and direction of a simple linear relationship

Proportion

measure of how frequently a value occurs relative to the total number of observations

Deviation

measure of how the data differ from a fixed value, such as central tendency

Continuous Measure

measure such that the set of possible observed outcomes are infinite and uncountable.

Discrete Measure

measure such that the set of possible observed outcomes are separate, distinct, and finite such as a count

Spread

measure that indicates how the data values are distributed, a measure of the dispersion or variability within a group of values

Interval Measure

measures a characteristic of an individual where differences between measures have meaning; that is the distance between two adjacent units is the same but there is not a meaningful zero point

Variability

measures the degree of dispersion within a given data set

Descriptive Statistics

methods of organizing and summarizing info and presenting it numerically or visually

Multistage Sampling

more than one sampling tech is employed in the gathering of info

Double Blind Experiment

neither the subjects nor the researchers are aware of who received what treatment

Frequency

number of occurrences for a given event

Placebo Effect

occurs when a subject receives a false treatment or no treatment, but incorrectly believes he or she is in fact receiving treatment and responds favorably

Sample Size

of a sample is the number of the observations that constitute the sample. Where as the size of population is denoted by N, the size of sample is denoted by n.

Population

of size (N), is a group of individual persons, objects, or items that tone wishes to better understand and certain characteristics about and from which samples are taken for statistical measurement.

Nominal Measure

one that measures a characteristic of an individual by name only

Ratio Measure

one that measures a characteristic of an individual where not only do differences between measures have meaning, but ratios also have meaning

Individuals

people, places or things included in a study and for which info is gathered. In medical research studies, individuals are referred to as subjects in the study

Scientific Method

pose a question, perform background research, construct a hypothesis, test the hypothesis experimentally, analyze the data and draw a conclusion

Relative Frequency

ratio between frequency and total number of observations

Reliability

refers to the accuracy and precision of the actual measuring instruments or procedure. Small random error

Degree of Confidence

represents the proportion of times the statistical methodology used captures the true state of nature

Random Sample

sample of size n taken from a population of size N in such a way that each individual observed has an equally likely chance of being selected

Statistics

science of gather, organizing, analyzing and interpreting numerical and categorical data

Uniform

shape in which each outcome is equally likely

Skewed Left

shape in which mean<median

Skewed Right

shape in which mean>median

Bell Shaped

shape in which mode=mean=median

Symmetric

shape in which there is an axis about which the images are congruent

Regression

statistical procedure use dot estimate the relationship among variables specifically between the primary variable of interest and all other variables

Experimental Study

study designed to be observed with interference from the observer in that specific treatments are applied to the individuals, in an effort to measure difference in the subject response

Prospective Study (longitudinal)

study in which data is gathered over an extended period of time

Cross sectional Study

study of a single point in time

Retrospective Study

study using historical (past) data

Census

survey of every individual in the population; info becomes population data

Sample Survey

survey of only some of the individuals in the population. The info gathered is called sample data.

Bias

the consistent deviation of the statistic to one side of the parameter

Simulation

the imitation of a natural process using general characteristics or behaviors in an effort to mimic or model the natural system.

Experiment

the method that we follow to obtain data/info

Response Variable

the primary variable of interest; that is, the objective in the given study (dependent)

Hypothesis Testing

the use of a statistical method in arguing for or against a hypothesized value based on observed info and using this info to make a decision regarding a n initial hypothesis and an alternate hypothesis

Lurking Variable

unknown variables that have not been measured; however the do contribute to the response variable and are not included as an explanatory variable

Qualitative Variable

variable that describes the individual by placing it into a category or a group

Quantitative Variable

variable that describes the individual by taking on a real value or numerical measure of data

Location

within a distribution, this is a specific value within the domain of the data such as: extremes, central tendencies or quartiles