Learning Log
Cassandra Carter
April 10, 2018
For this learning log we are suppose to discuss the changes that still need to be made to our projects before the presentation. Some of the most obvious changes that need to be made are the inclusion of VIF and multicolinearity and fulfilling all the requirements of prior research. Another small area that needs improvemnt is that we are missing prediction and confidence intervals.
During class we also talked about seasonal data. What we want to be modeling is constant seasonal variation and transform increasing seasonal variation with a log transformation.
install.packages(faraway)
library(faraway)## Warning: package 'faraway' was built under R version 3.4.4data(airpass)
attach(airpass)
head(airpass)## pass year
## 1 112 49.08333
## 2 118 49.16667
## 3 132 49.25000
## 4 129 49.33333
## 5 121 49.41667
## 6 135 49.50000names(airpass)## [1] "pass" "year"plot(pass ~ year, type = "l")
As we can see there is obvious increasing seasonal variation
transform1 <- log(year)
transform2 <- log(pass)
plot(transform2 ~ transform1, type = "l")
Now the data looks much better!
We then talked about modeling seasonal variation using dummy variables. One example of a dummy variable would being using a different category for each season and sorting the seasons by month. An example of this is shown below.
with(airpass, plot(pass~year, type = "l"))
with(airpass, plot(log(pass)~year, type = "l"))
justyear <- floor(airpass$year)
modecimal <- airpass$year - justyear
mofactor <-factor(round(modecimal*12))
cbind(airpass$year, mofactor)## mofactor
## [1,] 49.08333 2
## [2,] 49.16667 3
## [3,] 49.25000 4
## [4,] 49.33333 5
## [5,] 49.41667 6
## [6,] 49.50000 7
## [7,] 49.58333 8
## [8,] 49.66667 9
## [9,] 49.75000 10
## [10,] 49.83333 11
## [11,] 49.91667 12
## [12,] 50.00000 1
## [13,] 50.08333 2
## [14,] 50.16667 3
## [15,] 50.25000 4
## [16,] 50.33333 5
## [17,] 50.41667 6
## [18,] 50.50000 7
## [19,] 50.58333 8
## [20,] 50.66667 9
## [21,] 50.75000 10
## [22,] 50.83333 11
## [23,] 50.91667 12
## [24,] 51.00000 1
## [25,] 51.08333 2
## [26,] 51.16667 3
## [27,] 51.25000 4
## [28,] 51.33333 5
## [29,] 51.41667 6
## [30,] 51.50000 7
## [31,] 51.58333 8
## [32,] 51.66667 9
## [33,] 51.75000 10
## [34,] 51.83333 11
## [35,] 51.91667 12
## [36,] 52.00000 1
## [37,] 52.08333 2
## [38,] 52.16667 3
## [39,] 52.25000 4
## [40,] 52.33333 5
## [41,] 52.41667 6
## [42,] 52.50000 7
## [43,] 52.58333 8
## [44,] 52.66667 9
## [45,] 52.75000 10
## [46,] 52.83333 11
## [47,] 52.91667 12
## [48,] 53.00000 1
## [49,] 53.08333 2
## [50,] 53.16667 3
## [51,] 53.25000 4
## [52,] 53.33333 5
## [53,] 53.41667 6
## [54,] 53.50000 7
## [55,] 53.58333 8
## [56,] 53.66667 9
## [57,] 53.75000 10
## [58,] 53.83333 11
## [59,] 53.91667 12
## [60,] 54.00000 1
## [61,] 54.08333 2
## [62,] 54.16667 3
## [63,] 54.25000 4
## [64,] 54.33333 5
## [65,] 54.41667 6
## [66,] 54.50000 7
## [67,] 54.58333 8
## [68,] 54.66667 9
## [69,] 54.75000 10
## [70,] 54.83333 11
## [71,] 54.91667 12
## [72,] 55.00000 1
## [73,] 55.08333 2
## [74,] 55.16667 3
## [75,] 55.25000 4
## [76,] 55.33333 5
## [77,] 55.41667 6
## [78,] 55.50000 7
## [79,] 55.58333 8
## [80,] 55.66667 9
## [81,] 55.75000 10
## [82,] 55.83333 11
## [83,] 55.91667 12
## [84,] 56.00000 1
## [85,] 56.08333 2
## [86,] 56.16667 3
## [87,] 56.25000 4
## [88,] 56.33333 5
## [89,] 56.41667 6
## [90,] 56.50000 7
## [91,] 56.58333 8
## [92,] 56.66667 9
## [93,] 56.75000 10
## [94,] 56.83333 11
## [95,] 56.91667 12
## [96,] 57.00000 1
## [97,] 57.08333 2
## [98,] 57.16667 3
## [99,] 57.25000 4
## [100,] 57.33333 5
## [101,] 57.41667 6
## [102,] 57.50000 7
## [103,] 57.58333 8
## [104,] 57.66667 9
## [105,] 57.75000 10
## [106,] 57.83333 11
## [107,] 57.91667 12
## [108,] 58.00000 1
## [109,] 58.08333 2
## [110,] 58.16667 3
## [111,] 58.25000 4
## [112,] 58.33333 5
## [113,] 58.41667 6
## [114,] 58.50000 7
## [115,] 58.58333 8
## [116,] 58.66667 9
## [117,] 58.75000 10
## [118,] 58.83333 11
## [119,] 58.91667 12
## [120,] 59.00000 1
## [121,] 59.08333 2
## [122,] 59.16667 3
## [123,] 59.25000 4
## [124,] 59.33333 5
## [125,] 59.41667 6
## [126,] 59.50000 7
## [127,] 59.58333 8
## [128,] 59.66667 9
## [129,] 59.75000 10
## [130,] 59.83333 11
## [131,] 59.91667 12
## [132,] 60.00000 1
## [133,] 60.08333 2
## [134,] 60.16667 3
## [135,] 60.25000 4
## [136,] 60.33333 5
## [137,] 60.41667 6
## [138,] 60.50000 7
## [139,] 60.58333 8
## [140,] 60.66667 9
## [141,] 60.75000 10
## [142,] 60.83333 11
## [143,] 60.91667 12
## [144,] 61.00000 1levels(mofactor) <- c("Jan", "Feb", "Mar", "Apr", "May",
"Jun", "Jul", "Aug", "Sep", "Oct",
"Nov", "Dec")
summary(mofactor) ## Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
## 12 12 12 12 12 12 12 12 12 12 12 12lev <- c("Jan", "Feb", "Mar", "Apr", "May",
"Jun", "Jul", "Aug", "Sep", "Oct",
"Nov", "Dec")
lev <- factor(lev)
levels(lev) <- list(Winter = c("Jan", "Feb", "Mar"), Spring = c("Apr", "May","Jun"),
Summmer = c("Jul", "Aug", "Sep"), Fall = c("Oct", "Nov", "Dec"))
summary(lev)## Winter Spring Summmer Fall
## 3 3 3 3