Regression with time and date

[Slink]

Hey guys,

as a beginner I need some help with my task.

I need to explain from my marketing data how important the type of TV spot is in relation to placement and time of broadcast.

I already converted the date for example:

2020-12-25 17:31:37

to Weekdays (monday, tuesday etc.)

But now I have difficulties with making a regression with the Spots 1-5 (as a dependent variable) and time and weekdays as a independent variable. How do I "extract" time out of the example above? It always say that Variable lengths are different

Hope you get the point.

Thanks!

[nirgrahamuk]

Probably using lubridate package which has convenience functions for extracting hours/seconds/minutes from a time vector would help you.
Do more with dates and times in R (r-project.org)

A Reprex from you would be useful in order to provide you specific help
FAQ: How to do a minimal reproducible example ( reprex ) for beginners

[nirgrahamuk]

you don't need dummy variables, lm would make them automatically.

#made up data
(wd <- weekdays(seq(from=Sys.Date()-99,to=Sys.Date(),by=1)))
(someval <- 20*nchar(wd) +rnorm(100,1,1))

#look at it
par(mfrow=c(1,2))
plot(factor(wd))
plot(someval)

#do regression
(lm1 <- lm(someval ~ wd))
par(mfrow=c(2,2))
plot(lm1)