If more scores are clustered toward the low end of a frequency distribution and only a
few scores are at the high end, then the distribution is
negatively skewed
positively skewed
multimodal
unimodal
Which of the following regression diagnostic tools is used to study the possible
presence of multicollinearity?
Scatter diagram
Residual plot
The correlation matrix
Durbin-Watson test
Interaction exists in a multiple regression model when:
one independent variable affects the relationship between another independent
variable and the dependent variable.
the regression model is overall insignificant.
multicollinearity is present in a regression model.
a polynomial model used.
In one city, 20% of adults smoke. In groups of size 100 of adults, what is the variance
of the number that smoke?
8
16
20
36
If the results of an experiment using on way ANOVA were summarized as
F(2, 28) = 2.79 , p-value >α = 0.05 , then you would know that 0 H was
and was .
μ1 = μ2 ; not rejected
μ1 = μ2 ; rejected
μ1 = μ2 = μ3 ; rejected
μ1 = μ2 = μ3 ; not rejected
The sum of the residuals when using a least-squares regression line is .
equal to the variance of the Y variable
normally distributed around the mean of X
equal to zero
normally distributed around the mean of Y
If scores are measured on a nominal scale, then the best measure of central tendency
for the scores is the .
median
mean
mode
correlation coefficient
A standard error of the mean is a standard deviation of a .
population mean
sampling distribution of the mean
population
sample
In a normal distribution, what proportion of scores fall within the interval between the
mean to one standard deviation above the mean?
0.8413
0.1359
0.6826
0.3413
The probability function for random variable X is specified as: f (X ) = X /10 for
X = 1, 2, 3 or 4 The expected value of X is
2.000
2.333
3.000
3.500
After a linear forecasting model is found for a time series, if the Durbin-Watson
statistic is 1.98, this means that:
no positive autocorrelation exists, a nonlinear model should be tried.
positive autocorrelation exists, a nonlinear model should be tried.
positive autocorrelation exists, the linear model is adequate.
no positive autocorrelation exists, the linear model is adequate.
A bar graph is used to present data, whereas a histogram is used to present
data.
qualitative; quantitative
statistical; population
continuous; discrete
quantitative; qualitative
If the correlation coefficient for variables X and Y is zero, then the .
regression equation will predict Y exactly
mean of X will be higher than the mean of Y
Y-intercept is equal to 1.0
best prediction of Y is the mean of Y
The student t distribution varies with the .
range of values in the sample
value of the sample variance
value of the sample mean
size of the sample
If cars arrive to a service center randomly and independently at a rate of 1 car per hour
on average, what is the probability of 0 cars arriving in a given hour? (e = 2.7183)
0.0067
0.1755
0.3679
0.5000
Which of the following statements is correct?
The lower the confidence level, the smaller the confidence interval.
The greater the population variance, the smaller the confidence interval.
The higher the confidence level, the smaller the confidence interval.
None of the above.
A percentile is .
always the midpoint of a class interval
a score at or above which a specified percentage of the scores in a distribution fall
a score at or below which a specified percentage of the scores in a distribution fall
the percentage of scores in a distribution equal to or greater than a particular score
If we are testing for the difference between the means of two paired populations with
samples of 120 n and 2 20 n = , the number of degrees of freedom is equal to:
19
39
38
18
Representativeness of a sample is principally determined by the .
symmetry of the population distribution
method of sampling used
standard error of the mean
size of the sample
A and B are mutually exclusive outcomes in a probability distribution. The
p(A) = 0.24 and the p(B) = 0.13 . The p(A or B) then equals
0.03
0.37
1.85
0.11
以下是六個與統計有關的英文專有名詞,試說明每個名詞的統計意義,只有英翻
中則不計分
(一) Significant Level α
(二) Population Parameter
(三) Variance Inflationary Factor
(四) Sum of Square for Error
(五) Treatment Effect
(六) Best Linear Unbiased Estimator
可觀看題目詳解,並提供模擬測驗!(免費會員無法觀看研究所試題解答)