Experimental Design
Ultimately, you want to do this when designing an experiment.
What is replication?
Adding a constant to a random variable does this to the mean.
What is shifting the mean by the constant?
This is the standard error for inference of means.
What is s/sqrt(n)?
This menu tab in the calculator section is for statistics.
What is 6?
This type of study is best for determining a causal relationship.
What is an experiment?
You add this value of two random variables to get the standard deviation of the sum of the random variables.
What is the variance?
This is the standard error for a 2 sample t-test for difference of means.
What is sqrt(s1^2/n1 + s2^2/n2)?
This menu tab in the spreadsheet section is for statistics.
What is 4?
If you are comparing the effects of a sealant on the waterproofing of a pair of rain boots, this method of design would be effective.
What is a matched pairs design? (one boot has the sealant; one doesn’t)
This is the standard deviation of a random variable X with discrete probability distribution P(x).
What is sqrt(Σ((X-Xbar)^2*P(X))?
Assume assumptions and conditions have been met. If a sample of 30 has a mean of 5 and standard deviation of 2, this is the 95% confidence interval for population mean.
What is 4.253 < mu < 5.749?
WORK: tInterval(sample mean, sample stdev, sample size, confidence level) = tInterval(5,2,30,0.95) = 4.253<mu<5.749.
When plotting 2 variable quantitative data, press this series of buttons to plot a linear regression line. (two valid answers; you only need to get one of them)
What is menu-4-6-1 OR menu-4-6-2?
To ensure a sample’s distribution follows the population, use this sample.
What is a stratified random sample?
Let X and Y be random variables representing the outcome of rolling a D6 and D8, respectively. This is mu(X+Y).
What is 8?
WORK: mu(D6) = (1+2+3+4+5+6)/6 = 3.5; mu(D8) = (1+2+3+4+5+6+7+8)/8 = 4.5; mu(D6+D8) = mu(D6)+mu(D8) = 3.5+4.5 = 8.
With a population size of 3700, this interval of sample sizes guarantees assumptions for inference have been met (if population distribution is NOT known).
What is 30-370?
WORK: the sample size has to be less than 10% the population size to assume the samples are independent, so this puts an upper bound of 370. As we don’t know the population distribution, we can assume it is normal if the sample size is greater than 30. This yields 30-370.
These inference tests cannot be done directly in the Calculator Page because the Nspire doesn’t parse the inputted lists correctly.
What is a chi-square goodness of fit and linear regression t-test?
This is the best sample to use for a study when attempting to generalize the study to a population.
What is a census?
This is the mean and standard deviation of a single D8.
What are 4.5 and 2.291?
WORK: (1+2+3+4+5+6+7+8)/8 = 4.5; sqrt(sum(n = 1 to 8)(((n-4.5)^2)/8) = 2.291
The management of a particular company wants to determine whether the average amount of time the workers spend in the rest rooms is greater than 3 minutes. They create a sample of 25 (of the 300 total) workers by watching the cameras and timing the duration between a worker entering and exiting the rest rooms. They perform a 1-sample t-test for population mean, and yield a test score of 2.12 and a p-value of 0.022. At an alpha level of 0.05, the management determined this interpretation of the test.
What is inconclusive?
WORK: as the sample was a convenience sample and not random, the assumptions and conditions have failed.
A student is trying to plot a normal probability plot for residuals for inference. They first plot the explanatory and response variables, plot the regression line, and plot the residual plot. They then create a new plot, do this particular step, and set the plot type to Normal Probability plot.
What is plotting the x values on the new plot as the residuals?