Blog

Examine the US_births_2000_2014 dataset in the fivethirtyeight package (be careful: there are 2 datasets with different years). What was the average number of births per day registered in the US from 2000-2014? The same data can be found at  https://raw.githubusercontent.com/jddbucknole/MAcc/master/US_birth_2000_2014.csv if you don’t want to use R

What does overfitting mean?

While this course was very time-consuming and difficult at times, I feel I’ve gotten a good grasp on the basics of statistical concepts and R programming skills that will suit me well as I continue in the MAcc program and in my job going forward. (Hint: The answer is true!)

Suppose 10% of all people who shop at Conrads bookstore buy an OSU t-shirt.  If we select 15 random people who shopped at Conrads last week, what is the probability that exactly 2 of them purchased an OSU t-shirt? Report 4 decimal places in your answer

Examine the Cereal dataset in the Lock5Data package. A model was fit to predict Calories based on the amount of sugar in the cereal and the following output was generated. Call:lm(formula = Calories ~ Sugars, data = Cereal) Residuals:Min            1Q            Median         3Q           Max -36.574   -25.282        -2.549       17.796      51.805 Coefficients:                    Estimate       Std. Error         t value            Pr(>|t|) (Intercept)     88.9204         10.8120           8.224            5.96e-09 ***Sugars            4.3103           0.9269           4.650            7.22e-05 ***—Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 Residual standard error: 26.61 on 28 degrees of freedomMultiple R-squared: 0.4357, Adjusted R-squared: 0.4156 F-statistic: 21.62 on 1 and 28 DF, p-value: 7.217e-05 What percent of the variability in Calories is explained by Sugars? Report your answer to 4 decimal places

When another predictor is added to a model, the unadjusted R2 can NEVER decrease.

Using the nycflights13 data. I want to know if there is a difference in the average dep_delay between United (UA) and Delta (DL) on flights leaving JFK for LAX. What is the appropriate test?

Which of these measures is robust to (not affected much by) outliers? Select all that apply

A model was fit to predict the Calories based on the sugars (g/cup) and Company.  There were 3 Companies (G = General Mills, K = Kellogg’s , and Q = Quaker). > summary(mod) Call:lm(formula = Calories ~ Sugars + Company, data = Cereal) Residuals:Min                    1Q            Median           3Q                  Max -39.697        -25.414          -1.459          16.559             55.349 Coefficients:                        Estimate        Std. Error        t value           Pr(>|t|) (Intercept)         85.3035          12.5365          6.804           3.2e-07 ***Sugars                4.3146            0.9556          4.515           0.000121 ***CompanyK          6.6755          11.2324          0.594           0.557443 CompanyQ         5.6221          13.5345          0.415           0.681266 —Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 Residual standard error: 27.41 on 26 degrees of freedomMultiple R-squared: 0.4442, Adjusted R-squared: 0.3801 F-statistic: 6.926 on 3 and 26 DF, p-value: 0.001405 Based on this output, which company had the HIGHEST  caloric content after Sugars were accounted for?

The probability model below describes the number of repair calls that an appliance repair shop may receive during an hour   Repair calls 0 1 2 3 Prob 0.10 0.30 0.40 0.20   What is the average number of calls received in an hour?