Statistics

Question 1

An organized scientific undertaking with a defined set of purposes or objectives.

Answer 1

Study investigation

Question 2

Altering existing conditions in a defined manner in order to assess the effect of one or more treatments. For example, an appetite suppressant is administered to one group of obese subjects and a placebo (inert substance) is given to another group in order to assess the comparative response. In this example, the state of nature is altered by the researcher to gain comparative information. Most experimental studies are comparative.

Answer 2

Experiment

Question 3

The detailed specification of the procedures whereby information will be obtained. The study design includes a statement of objectives, a specific definition of units and of the population, and a description of procedures for selecting units from the population. If the study is experimental, the design includes a description of procedures for assigning treatments to the selected units.

Answer 3

Design

Question 4

The procedures for summarizing and extracting numerical information on the variables observed on the units selected for study and for making inferences from these data.

Answer 4

Analysis

Question 5

A research tool used to assess conditions as they exist in nature, altering them as little as possible.

Answer 5

survey

Question 6

The smallest object or individual that can be investigated; the source of the basic information. Units thus have some observable characteristic in common. In surveys, the units are called sampling units; in experiments, experimental units.

Answer 6

Unit

Question 7

The characteristic observable on the units. For example, resting heart rate, cholesterol concentrations, or a response to a medication are all variables. The characteristic is called a variable since it can vary. Characteristics that do not vary are called constants. In scientific research, it is routine to study variables. A good research study, however, alters only one variable at a time. An independent variable is one that is manipulated by a researcher, whereas a dependent variable is observed. In general, the independent variable is manipulated and the resulting effects on the dependent variable are measured.

Answer 7

Variable:

Question 8

A variable that can potentially take any value within a range. Examples are temperature, time, blood pressure, serum cholesterol, weight, height, etc. Variables are generally not available in continuous form for analysis, but are recorded in discrete forms (i.e., to the nearest degree, mmHg, mg/dL, kg, cm, etc.). For example, although actual temperature exists between the nearest whole degrees, it is recorded to a determined accuracy of measurement. It is the actual, rather than the recorded, value that determines whether a variable is labeled as continuous or discrete.

Answer 8

continous variable

Question 9

A variable is intrinsically “gappy”, in the sense that between any two potentially obtainable values lies at least one unobtainable value. The best example is a count. Counts take values of 0,1, 2, 3…. For example a household can have 1, 2 or 3 children, etc. It is not possible to have 1.2 or 4.1 children. The opposite of a discrete variable is not an indiscrete variable but rather is referred to as a continuous variable.

Answer 9

discrete variable

Question 10

A random variable is a quantity that takes various values or sets of values with various probabilities.

Answer 10

random variable

Question 11

The set of all possible values with their associated probabilities is called the distribution of the random variable. This distribution is usually presented as a table or graph.

Answer 11

distribution of a random variable

Question 12

The mean is the mathematical average of a set of numbers. The average is calculated by adding up two or more scores and dividing the total by the number of scores.

Answer 12

mean

Question 13

The median is the central value of an ordered distribution. To find it, arrange the data from smallest to largest. For an odd number of data values, the median is the middle data value; for an even number of data values, the median is the mean of the two middle values.

Answer 13

median

Question 14

The mode of a data set is the value that occurs most frequently.

Answer 14

mode

Question 15

A very large (possibly infinite) group of units about which scientific inferences are to be made.

Answer 15

population

Question 16

A characteristic of a population.

Answer 16

parameter

Question 17

A subset of units in the underlying population. The sample provides the actual numerical information used in making inferences about the population.

Answer 17

Sample

Question 18

A characteristic of a sample, used for making inferences about a parameter.

Answer 18

Statistic

Question 19

A random sample is a sample drawn from a population of units in such a way that every unit of the population has the same probability of selection and different units are selected independently.

Answer 19

Random Sample

Question 20

A conclusion about a population on the basis of information contained in a sample; a statement about a parameter based on the observed value of the corresponding statistic. Note that we will never know population values exactly, since it’s not practical to study EVERYONE on the planet. Instead, we study only a part of the population, a sample, and make statistical inferences utilizing the laws of probability to arrive at conclusions.

Answer 20

Statistical inference

Question 21

A procedure whereby the validity of a stated hypothesis is tested by examining a value of the test statistic computed from a sample. Based on this statistical analysis, we reject or accept the hypothesis.

Answer 21

test of hypothesis

Question 22

A measure of how much evidence we have for or against the hypothesis being tested. It is the level at which the observed value of the test statistic would be considered significant. The smaller the p-value, the more evidence that any observed difference in the sample is a real difference in the population. Generally, one accepts a p-value equal to or less than 0.05 as the cut-off for significance. At P 0.05, we can say that there is less than or equal to a 5% chance that the observed difference is an aberration. Less than a 5% chance is typically sufficient to instill confidence that observed differences are real.

Answer 22

p-value