Chapter 3 Terms

Question 1

Computer-calculated plot or graph estimating the relationship between two variables.

Answer 1

Trend Line

Question 2

The text’s name for a one-tail test.

Answer 2

One sided Alternative

Question 3

The text’s name for a two-tailed test

Answer 3

Two sided Alternative

Question 4

Sometimes called “matched pairs” where two sets of data provide similar observations under similar conditions

Answer 4

Paired Data

Question 5

Common Excel test to assess similarity in the means between two similar sample groups for which population mean is unknown.

Answer 5

t- test, paired two sample for means

Question 6

Common Excel test to assess similarity in the means between two sets of data when the variance and standard deviations are unknown, but where the researcher believes that characteristics of the groups may be similar.

Answer 6

t-test, assuming equal variance

Question 7

Common Excel test to assess similarity in the means between two sets of data when the variance and standard deviations are unknown, and where the researcher believes that characteristics of the groups are not similar.

Answer 7

t-test, assuming unequal variance

Question 8

comparison of two columns of data testing for similarity in means and where there are different numbers of observed values.

Answer 8

Z-Test, 2 Sample for Means: Excel

Question 9

Two columns of data providing results from two separate and independent groups

Answer 9

Independent data

Question 10

Comparison of Expected Values with observed values to test how closely they match.

Answer 10

Goodness of Fit

Question 11

The sum of the squared differences between the observed values and the expected values used to assess how similar they are. Numerically high X2 values indicate poor fit between observed and expected values.

Answer 11

Chi Squared (X2) Statistic

Question 12

Term used for the differences (positive & negative) between observed values and expected values.

Answer 12

Residuals

Question 13

Comparison of two variables to see if values for one consistently affect values for the other

Answer 13

Test for Independence

Question 14

The variable presumed to cause change in the dependent variable

Answer 14

Independent Variable

Question 15

The variable presumed to be changed as a result of changes in the independent variable.

Answer 15

Dependent Variable

Question 16

(Sometimes called a scatter diagram.) A graphical illustration of the intersection of values of the independent variable x, and values of the dependent variable y.

Answer 16

Scatter plot

Question 17

Conversion of values for 2 variables in separate columns to a scatter plot diagram which can also produce a regression trendline, regression formula and R2 display

Answer 17

Excel Scatter plot

Question 18

Calculation of the relationship between two variables that produces a formula (y-hat= b0 + b1 x) calculating a straight line approximating the probable values resulting from a data set of x and y variables.

Answer 18

Simple Linear Regression

Question 19

Calculation of the relationship between more than one independent variable (x value) and the dependent variable (y value).

Answer 19

Multiple Linear Regression

Question 20

Portion of the distribution chosen to determine acceptable test results (e.g.95%)

Answer 20

Confidence level

Question 21

Conversion of confidence level to a decimal value (e.g. 95% to 0.9500

Answer 21

Confidence Coefficient

Question 22

A calculation performed by Excel measuring strength of the relationship (reliability) between the trendline created by the regression formula and the observed intersecting values of the x and y variables.

Answer 22

R Squared or R2 Calculation (aka Coefficient of Determination)

Question 23

A calculation performed by Excel measuring the strength of the relationship between the values of the x and y variables. It is the square root of the R2 value.

Answer 23

Multiple R (aka Correlation Coefficient)

Question 24

A value in a data set that is significantly higher or lower than 95% of the distribution which requires separate analysis and interpretation.

Answer 24

Outlier

Question 25

The value most likely to occur because of trends in past data or in data collected from a population or large sample.

Answer 25

Expected Value

Question 26

The measure of variability above and below a mean according to standard percentages of Standard Normal Distributions as defined by the Empirical Rule

Answer 26

Standard Deviation (σ) of a Random Variable

Question 27

A formal mathematical proof of the Law of Large Numbers which says that distributions with large numbers of observations (n) approximate a Standard Normal distribution (bell-shaped curve).

Answer 27

Central Limits Theorem (Law of Large Numbers)

Question 28

A conversion of the sample mean (or proportion) into an increment of standard deviations, called z-value, and used for comparison with limits of the chosen confidence level.

Answer 28

Critical Value (or z-value) of the test statistic

Question 29

Conversion of the z-value of the test statistic to probability value from 0 to 1.0 used for comparison with the probability values of the upper and lower limits of the chosen confidence level. For a 95% confidence level with z-value of ±1.96 z , the range in probability would be from 0.0250 to 0.9750 and used as a decision rule for accepting or rejecting the H0.

Answer 29

Probability Value (or p-value) of the test statistic: