Blog

Estimating is challenging for many reasons.   When estimating, we shouldn’t imply precision where precision doesn’t exist.  Which of the following are possible techniques for providing an estimate and avoiding implied precision?  Check all answers that apply.

The nurse is reviewing the results of a 67-year-old female patient’s bone mineral density testing. The patient’s T-score is +1. Based on this score, the nurse knows they need to teach the patient:

Conduct a t-test on the penguin_female dataset to determine if there is a difference in mass between the first and second year. Which of the following is true based on your results? (Select all that apply)  

Run a multiple regression on the mice data set where litter size is the response variable and body mass (g) and total length (mm) are the predictor variables. Based only on the F-statistic and its p-value what can we conclude about this model? (Select all that apply)

Based on the among group and within group sum of squares calculations, what would you conclude about the dataset?

Run a multiple regression on the mice data set where litter size is the response variable and body mass (g) and total length (mm) are the predictor variables. What is the adjusted R-squared value for this regression?

Answer the following question using the penguin_female data set. This includes body mass measurements for individual females over 2 years. We are interested in determining if there is a difference in body mass between the first and second years (mass_1 and mass_2, respectively). Note: an individual bird’s mass is being tracked across two years. penguin_female.csv

Conduct a t-test to determine if the number of caterpillars (NbrCaterpillars) is less than 150 on Veronica plants.  Based on your t-test what do you conclude? (Select all that apply)  

Select the best model using bidirectional selection for the grasslands data set. Use water content as the response variable and all other variables as predictors. Start with the full model. Which of the following is selected according to bidirectional model selection?

Use the ToothGrowth dataset to complete the following questions. This data set contains information on the effect of supplement given (supp) and dose of supplement (dose) on tooth length (len). For the following questions, len is the continuous response variable (Y) and dose is the categorical predictor variable (X). Note: supp has two levels (VC & OJ), use only OJ for the following questions (i.e., remove the data on the supplement “VC”).  ToothGrowth.csv