This is completely written using rStudio:

The Data and The Questions

An Ironman triathlon is an impressive endurance event that covers 140.6 miles (Swim 2.4 miles, Bike 112 miles, Run 26.2 miles). We are going to focus on the results from the Florida Ironman races from 2020 and 2021.

Our primary focus is on individuals who competed in both the 2020 and 2021 Ironman Florida. We want to determine if and how performance metrics from the 2020 race (swim time, bike time, run time, and transition time) along with demographic information (gender and age group) are useful for explaining overall performance in the 2021 race (overall time).

In addition to this primary question, your supervisor has asked you to also address the following secondary question:

Are the athletes that competed in both 2020 and 2021 substantially different in terms of performance metrics (time for completing swim, bike, and run) than the athletes that only competed in 2021?

The athlete results for the 2020 and 2021 Florida Ironman races are available in the files IM_FL_20.csv and IM_FL_21.csv, respectively (at the bottom of the page within 4 parts. Just upload to Excel using the 4 parts to make 2 spreadsheets.)

The following information is recorded for each athlete.

1. Bib = bib number assigned for the race
2. Name
3. Country
4. Gender - Male or Female
5. Division - Denotes gender and age group for most athletes (e.g. M40-44 means male in the 40-44 year old age bracket). Exceptions to this are MPRO, FPRO, MPC, and FPC where PRO means professional and PC means physically challenged.
6. DivisionRank - Overall rank compared to others in the same division
7. OverallTime - Overall time for completing the full race including swim, bike, run, and transition times. Reported in HH:MM:SS format.
8. OverallRank
9. SwimTime - Time for completing the swim portion of the race. Reported in HH:MM:SS format for those taking 1 hour or more. Reported in MM:SS:00 for those taking less that 1 hour.
10. SwimRank
11. BikeTime - Time for completing the bike portion of the race. Reported in HH:MM:SS format.
12. BikeRank
13. RunTime - Time for completing the run portion of the race. Reported in HH:MM:SS format.
14. RunRank
15. FinishStatus - Categorical variable with value DNF (did not finish), DNS (did not start), DQ (disqualified), or Finisher.

Project Three - Preliminary 1 - What to compute in rStudio:

For this assignment, you will investigate univariate relationships between individual event times (swim, bike, run, transition) in 2020 with the response variable of overall time in 2021. By univariate relationships, we mean that we are fitting simple linear regression models that consider a single predictor variable at a time. This will serve as an initial step in addressing our primary research question.

Steps to complete this weeks tasks:

• Fit four simple linear regression models predicting overall time in 2021; one model for each 2020 time metric (swim, bike, run, transition) as a predictor variable.
• Summarize your findings in a univariate regression table (JAMA example= (full article "Clinical Characteristics and Outcomes in Patients With Coronavirus Disease 2019 and Multiple Sclerosis"), see figure 3 for a table and forest plot that parallels this but in the context of logistic rather than linear regression).
• Create a forest plot that shows the estimated slope parameter and associated confidence interval for each 2020 event time component (swim, bike, run, transition).
• Write comments on any noteworthy patterns or features in your table and/or forest plot.

IM_Florida_20 data:

Bib	Name	Country	Gender	Division	DivisionRank	OverallTime
46	Chris Leiferman	United States	Male	MPRO	1	7:52:44
42	Matthew Hanson	United States	Male	MPRO	2	7:55:02
40	Sam Long	United States	Male	MPRO	3	7:55:33
45	Andreas Dreitz	Germany	Male	MPRO	4	7:56:51
43	Cody Beals	Canada	Male	MPRO	5	7:59:55
41	Matt Russell	United States	Male	MPRO	6	8:07:35
55	Pedro Gomes	Portugal	Male	MPRO	7	8:13:50
47	Brent Mcmahon	Canada	Male	MPRO	8	8:14:22
63	David Plese	Slovenia	Male	MPRO	9	8:22:54
65	Kevin Portmann	United States	Male	MPRO	10	8:31:21

and

OverallRank	SwimTime	SwimRank	BikeTime	BikeRank	RunTime	RunRank	FinishStatus
1	54:40:00	16	4:01:50	1	2:50:29	4	Finisher
2	55:17:00	20	4:11:24	5	2:41:57	1	Finisher
3	55:31:00	24	4:07:20	4	2:45:40	2	Finisher
4	54:02:00	8	4:02:57	2	2:52:58	5	Finisher
5	54:02:00	9	4:12:53	6	2:46:24	3	Finisher
6	54:39:00	15	4:04:25	3	3:00:44	10	Finisher
7	54:06:00	12	4:18:25	11	2:54:15	6	Finisher
8	53:11:00	4	4:14:01	8	3:00:52	11	Finisher
9	55:27:00	22	4:16:48	10	3:03:06	13	Finisher
10	1:01:09	53	4:16:38	9	3:06:37	16	Finisher

IM_Florida_21 Data:

Bib	Name	Country	Gender	Division	DivisionRank	OverallTime
51	Gustav Iden	Norway	Male	MPRO	1	7:42:57
52	Lionel Sanders	Canada	Male	MPRO	2	7:48:50
59	Robert Kallin	Sweden	Male	MPRO	3	8:08:13
54	Arnaud Guilloux	France	Male	MPRO	4	8:26:38
58	Colin Norris	United States	Male	MPRO	5	8:27:07
56	Pedro Gomes	Portugal	Male	MPRO	6	8:32:09
60	Luis Ohde	Brazil	Male	MPRO	7	8:41:17
64	Jesse Vondracek	United States	Male	MPRO	8	8:44:32
55	Justin Metzler	United States	Male	MPRO	9	8:47:22
69	Vicen Castell Serra	Spain	Male	MPRO	10	8:49:08

and

OverallRank	SwimTime	SwimRank	BikeTime	BikeRank	RunTime	RunRank	FinishStatus
1	58:09:00	4	4:05:11	4	2:34:51	1	Finisher
2	58:19:00	7	4:04:30	2	2:40:43	2	Finisher
3	57:59:00	2	4:03:59	1	3:00:06	10	Finisher
4	59:02:00	9			3:17:54	41	Finisher
5	58:22:00	8	4:32:56	7	2:48:22	4	Finisher
6	1:00:44	13	4:31:55	6	2:52:02	5	Finisher
7	58:11:00	5	4:39:20	15	2:57:23	8	Finisher
8	1:07:01	34	4:37:30	11	2:53:56	6	Finisher
9	58:03:00	3	4:58:04	46	2:42:57	3	Finisher
10	1:09:30	46	4:38:12	13	2:54:35	7	Finisher