MIS 345 Exam 2

The percentage of variation (R2) ranges from:

0-1

Approximately what percentage of the observed Y values are within one standard error of the estimate () of the corresponding fitted Y values?

67%

Its good to have both

Co and corr corr without co can be misleading by just looking at graph, not enough

Data collected from approximately the same period of time from a cross-section of a population are called:

Cross sectional

Which approach can be used to test for autocorrelation?

Durbin-Watson statistic

Independent Variable

Explanatory

In simple linear regression, the divisor of the standard error of estimate is n - 1, simply because there is only one explanatory variable of interest.

False

Multiple regression represents an improvement over simple regression because it allows any number of response variables to be included in the analysis.

False

Vertical distance between Horizontal axis to line

Fitted value (dep var above exp var)

the guidelines for including/excluding variables in a regression equation?

Look at the t-value and associated p-value. Check whether the t-value is less than or greater than 1.0. Use economic or physical theory to make the decision. The variables are logically related to one another.

Several Exp var=

Multiple Regression

Linear can be used to estimate

Non Linear or "Linarized" by math

Prediction=

Number of explanatory variables in analysis

Correlations

Numerical summary measures that indicate strength of relationship *only can tell linear strength -1 to 1 and unitless 0= no lin relation

Regression Equation

Observed Value= Fitted Value + Residual Value

Time Series Data

One or more variables (equally spaced points in time)

Parts of Regression Analysis

Overview of data (how world operates) Primary: Prediction Secondary: Data being analyzed (either cross sectional or time series)

Difference is in

Residual += above line -= below 0= directly on line

Vertical distance between line to point

Residual (diff between actual and fitted values of dep var)

Dependent Variable

Response or Target Var

Outliers

Scatterplots good for finding them*

Single Exp var=

Simple Regression

Line of Best Fit=

Smallest Sum of Squared Residual (r2) meaning least of squared lines Squared b/c sum would (+) would cancel out neg value

Linear vs. Non-Linear

Straight Line Relationship vs. Curved

Regression Analysis

Study of relationship between variables Most useful for all statistical models in business world

A confidence interval constructed around a point prediction from a regression model is called a prediction interval, because the actual point being estimated is not a population parameter.

True

In multiple regression, if there is multicollinearity between independent variables, the t-tests of the individual coefficients may indicate that some variables are not linearly related to the dependent variable, when in fact, they are.

True

The R2 can only increase when extra explanatory variables are added to a multiple regression model.

True

The adjusted R2 is used primarily to monitor whether extra explanatory variables really belong in a multiple regression model.

True

The percentage of variation explained,, is the square of the correlation between the observed Y values and the fitted Y values.

True

Unequal Variences

Variance depends on explanatory variable "Fan Shape"

Sum of Residuals is always = to

Zero

Intercept of Simple Linear Reg

a= Y(bar) - 5x(bar)

If you can determine that the outlier is not really a member of the relevant population, then it is appropriate and probably best to:

delete it

St error is used to

estimated several potential regression equations that would be most useful

Which definition best describes parsimony?

explaining the most with the least

The percentage of variation () can be interpreted as the fraction (or percent) of variation of the

explanatory variable explained by the regression

An interaction variable is the product of an explanatory variable and the dependent variable.

false

If a scatterplot of residuals shows a parabola shape, then a logarithmic transformation may be useful in obtaining a better fit.

false

Regression analysis can be applied equally well to cross-sectional and time series data.

false

The objective typically used in the tree types of equation-building procedures is to:

find the equation with a small se and a large R2

In regression analysis, the variables used to help explain or predict the response variable are called the:

independent var

When determining whether to include or exclude a variable in regression analysis, if the p-value associated with the variable's t-value is above some accepted significance value, such as 0.05, then the variable:

is a candidate for exclusion

Which statement is true regarding regression error, ε?

it cannot be calculated from the observed data.

The covariance is not used as much as the correlation because:

it is difficult to interpret

no relationship=

look at points and their shape

Standard Error

n-2 (emperical st. dev rules apply)

A correlation value of zero indicates.

no linear relationship

R2 is most quoted for

regression analysis 0-1 % of varience of dep var explained by regression

Autocorrelation=

relationship to past values

The t-value for testing is calculated using which of the following equations?

sb

Covariance

single number that measures strength as well also if + or - UNIT BOUND only apply to linear

Which of the following is the relevant sampling distribution for regression coefficients?

t-distribution with n-1-k degrees of freedom

Scatter plots may find outliers but NOT

tell you what to do with them You can always ignore or exclude them

The adjusted R2 adjusts R2 for:

the number of explanatory variables in a multiple regression model

In linear regression, the fitted value is:

the predicted value of the dependent variable

Correlation is a summary measure that indicates:

the strength of the linear relationship between pairs of variables

When the error variance is nonconstant, it is common to see the variation increases as the explanatory variable increases (you will see a "fan shape" in the scatterplot). There are two ways you can deal with this phenomenon. These are:

the weighted least squares and a logarithmic transformation

A constant elasticity, or multiplicative, model the dependent variable is expressed as a product of explanatory variables raised to powers.

true

Cross-sectional data are usually data gathered from approximately the same period of time from a cross-sectional of a population.

true

Heteroscedasticity means that the variability of Y values is larger for some X values than for others.

true

If a categorical variable is to be included in a multiple regression, a dummy variable for each category of the variable should be used, but the original categorical variables should not be sued.

true

If exact multicollinearity exists, redundancy exists in the data.

true

If the regression equation includes anything other than a constant plus the sum of products of constants and variables, the model will not be linear.

true

In a multiple regression analysis involving 4 explanatory variables and 40 data points, the degrees of freedom associated with the sum of squared errors, SSE, is 35.

true

In multiple regressions, if the F-ratio is small, the explained variation is small relative to the unexplained variation.

true

In regression analysis, homoscedasticity refers to constant error variance.

true

In regression analysis, we can often use the standard error of estimate to judge which of several potential regression equations is the most useful.

true

The Durbin-Watson statistic can be used to test for autocorrelation.

true

When the scatterplot appears as a shapeless swarm of points, this can indicate that there is no relationship between the response variable Y and the explanatory variable X, or at least none worth pursuing.

true

A single variable (X) can explain a large % of variation on some other variable (Y) when

two variables are HIGHLY CORRELATED

A "fan" shape in a scatterplot indicates:

unequal variance