Penguin DR 11/28
2024-11-28
R Markdown
# X = burrow dist, Y = Time in Burrow
xyplot(time_in_burrow_sec ~ burrow_dist_mts, data = Penguin_Data)
favstats(time_in_burrow_sec ~ burrow_dist_mts, data = Penguin_Data)## burrow_dist_mts min Q1 median Q3 max mean sd n missing
## 1 3 0 0 0 105 420 105 210.0000 4 0
## 2 4.5 0 0 0 0 0 0 NA 1 0
## 3 5 1200 1200 1200 1200 1200 1200 0.0000 2 0
## 4 5.1 0 0 0 0 0 0 NA 1 0
## 5 6 60 60 60 60 60 60 NA 1 0
## 6 6.2 1020 1020 1020 1020 1020 1020 NA 1 0
## 7 6.5 600 600 600 600 600 600 NA 1 0
## 8 6.9 0 0 0 0 0 0 NA 1 0
## 9 7 0 0 0 0 0 0 0.0000 2 0
## 10 7.1 0 0 0 0 0 0 NA 1 0
## 11 8 0 300 600 900 1200 600 848.5281 2 0
## 12 8.1 0 0 0 0 0 0 NA 1 0
## 13 8.5 0 0 0 0 0 0 0.0000 2 0
## 14 9.5 1200 1200 1200 1200 1200 1200 NA 1 0
## 15 10 0 0 0 0 0 0 0.0000 2 0
## 16 11.1 120 120 120 120 120 120 NA 1 0
## 17 12.7 0 0 0 0 0 0 NA 1 0
## 18 12.8 0 0 0 0 0 0 NA 1 0
## 19 13.2 0 0 0 0 0 0 NA 1 0
## 20 13.7 0 0 0 0 0 0 NA 1 0
## 21 15 0 0 0 0 0 0 NA 1 0
## 22 16 0 0 0 0 0 0 NA 1 0
## 23 17 0 0 30 240 420 138 186.8689 5 0
## 24 18 0 195 390 585 780 390 551.5433 2 0
## 25 18.4 480 480 480 480 480 480 NA 1 0
## 26 20 0 0 0 0 0 0 0.0000 2 0
## 27 20.4 0 0 0 0 0 0 NA 1 0
## 28 21.6 0 0 0 0 0 0 NA 1 0
## 29 22.1 0 0 0 0 0 0 NA 1 0
## 30 22.8 0 0 0 0 0 0 NA 1 0
## 31 23.2 0 0 0 0 0 0 NA 1 0
## 32 23.5 0 0 0 0 0 0 NA 1 0
## 33 24.4 0 0 0 0 0 0 NA 1 0
## 34 25 0 0 0 0 0 0 0.0000 2 0
## 35 25.7 0 0 0 0 0 0 NA 1 0
## 36 26 900 900 900 900 900 900 NA 1 0
## 37 27.9 0 0 0 0 0 0 NA 1 0
## 38 29.4 240 240 240 240 240 240 NA 1 0
## 39 30 0 255 510 765 1020 510 721.2489 2 0
## 40 30.7 0 0 0 0 0 0 NA 1 0
## 41 31.8 0 0 0 0 0 0 NA 1 0
## 42 33.1 0 0 0 0 0 0 0.0000 2 0
## 43 34.8 0 0 0 0 0 0 NA 1 0
## 44 38 0 0 0 0 0 0 0.0000 2 0
## 45 38.8 0 0 0 0 0 0 NA 1 0
## 46 40 0 0 0 0 0 0 0.0000 4 0
## 47 45 0 0 0 0 0 0 NA 1 0
## 48 47.1 0 0 0 0 0 0 NA 1 0
## 49 52.2 0 0 0 0 0 0 NA 1 0
## 50 60 0 0 0 0 0 0 NA 1 0
## 51 63 960 960 960 960 960 960 NA 1 0
## 52 64.8 0 0 0 0 0 0 NA 1 0
## 53 70 0 225 450 675 900 450 636.3961 2 0
## 54 74.2 0 0 0 0 0 0 NA 1 0
## 55 74.6 0 0 0 0 0 0 NA 1 0
## 56 75 0 0 0 0 0 0 NA 1 0
## 57 80 0 0 0 0 0 0 NA 1 0
## 58 104 360 360 360 360 360 360 NA 1 0
## 59 112.4 0 0 0 0 0 0 NA 1 0cor(time_in_burrow_sec ~ burrow_dist_mts, data = Penguin_Data)## [1] -0.09666462The correlation coefficient (r) is -0.0967. This suggests a negative association with a very weak linear relationship between burrow distance from the trail and time spent in the burrow.
summary(lm(time_in_burrow_sec ~ burrow_dist_mts, data = Penguin_Data))$coefficients[,4]## (Intercept) burrow_dist_mts
## 0.001127552 0.390631668The p-value is 0.3906. Since the p-value is greater than 0.1, we have weak evidence that there is an association between burrow distance from the trail and time spent in burrow.
confint(lm(time_in_burrow_sec ~ burrow_dist_mts, data = Penguin_Data))## 2.5 % 97.5 %
## (Intercept) 84.074675 324.886843
## burrow_dist_mts -4.762156 1.881111We are 95% confident that a one meter increase in burrow distance from the trail is associated with an average increase of -4.762 to 1.881 seconds increase in time spent in the burrow in a given 20 minute period in the population of penguins represented by this sample. Since the number 0 is included in the confidence interval, there is strong evidence that there is NOT an association between burrow distance from the trail and time spent in burrow.
X = burrow dist, Y = % of time spent active
favstats(prop_active ~ burrow_dist_mts, data = Penguin_Data)## burrow_dist_mts min Q1 median Q3 max mean sd n missing
## 1 3 0.40 0.5125 0.600 0.7375 1.00 0.650 0.25495098 4 0
## 2 4.5 0.70 0.7000 0.700 0.7000 0.70 0.700 NA 1 0
## 3 5 0.15 0.1625 0.175 0.1875 0.20 0.175 0.03535534 2 0
## 4 5.1 1.00 1.0000 1.000 1.0000 1.00 1.000 NA 1 0
## 5 6 0.70 0.7000 0.700 0.7000 0.70 0.700 NA 1 0
## 6 6.2 0.15 0.1500 0.150 0.1500 0.15 0.150 NA 1 0
## 7 6.5 0.05 0.0500 0.050 0.0500 0.05 0.050 NA 1 0
## 8 6.9 0.15 0.1500 0.150 0.1500 0.15 0.150 NA 1 0
## 9 7 0.25 0.3750 0.500 0.6250 0.75 0.500 0.35355339 2 0
## 10 7.1 0.40 0.4000 0.400 0.4000 0.40 0.400 NA 1 0
## 11 8 0.00 0.0750 0.150 0.2250 0.30 0.150 0.21213203 2 0
## 12 8.1 0.20 0.2000 0.200 0.2000 0.20 0.200 NA 1 0
## 13 8.5 0.40 0.4625 0.525 0.5875 0.65 0.525 0.17677670 2 0
## 14 9.5 0.00 0.0000 0.000 0.0000 0.00 0.000 NA 1 0
## 15 10 0.35 0.3500 0.350 0.3500 0.35 0.350 0.00000000 2 0
## 16 11.1 0.90 0.9000 0.900 0.9000 0.90 0.900 NA 1 0
## 17 12.7 0.20 0.2000 0.200 0.2000 0.20 0.200 NA 1 0
## 18 12.8 0.30 0.3000 0.300 0.3000 0.30 0.300 NA 1 0
## 19 13.2 0.25 0.2500 0.250 0.2500 0.25 0.250 NA 1 0
## 20 13.7 0.20 0.2000 0.200 0.2000 0.20 0.200 NA 1 0
## 21 15 0.25 0.2500 0.250 0.2500 0.25 0.250 NA 1 0
## 22 16 1.00 1.0000 1.000 1.0000 1.00 1.000 NA 1 0
## 23 17 0.55 0.8000 1.000 1.0000 1.00 0.870 0.19874607 5 0
## 24 18 0.50 0.5500 0.600 0.6500 0.70 0.600 0.14142136 2 0
## 25 18.4 0.40 0.4000 0.400 0.4000 0.40 0.400 NA 1 0
## 26 20 0.10 0.2000 0.300 0.4000 0.50 0.300 0.28284271 2 0
## 27 20.4 0.65 0.6500 0.650 0.6500 0.65 0.650 NA 1 0
## 28 21.6 0.85 0.8500 0.850 0.8500 0.85 0.850 NA 1 0
## 29 22.1 0.35 0.3500 0.350 0.3500 0.35 0.350 NA 1 0
## 30 22.8 1.00 1.0000 1.000 1.0000 1.00 1.000 NA 1 0
## 31 23.2 0.70 0.7000 0.700 0.7000 0.70 0.700 NA 1 0
## 32 23.5 0.05 0.0500 0.050 0.0500 0.05 0.050 NA 1 0
## 33 24.4 0.10 0.1000 0.100 0.1000 0.10 0.100 NA 1 0
## 34 25 0.50 0.6125 0.725 0.8375 0.95 0.725 0.31819805 2 0
## 35 25.7 0.25 0.2500 0.250 0.2500 0.25 0.250 NA 1 0
## 36 26 0.20 0.2000 0.200 0.2000 0.20 0.200 NA 1 0
## 37 27.9 1.00 1.0000 1.000 1.0000 1.00 1.000 NA 1 0
## 38 29.4 0.60 0.6000 0.600 0.6000 0.60 0.600 NA 1 0
## 39 30 0.15 0.2125 0.275 0.3375 0.40 0.275 0.17677670 2 0
## 40 30.7 0.30 0.3000 0.300 0.3000 0.30 0.300 NA 1 0
## 41 31.8 1.00 1.0000 1.000 1.0000 1.00 1.000 NA 1 0
## 42 33.1 0.50 0.5125 0.525 0.5375 0.55 0.525 0.03535534 2 0
## 43 34.8 1.00 1.0000 1.000 1.0000 1.00 1.000 NA 1 0
## 44 38 0.45 0.5875 0.725 0.8625 1.00 0.725 0.38890873 2 0
## 45 38.8 0.95 0.9500 0.950 0.9500 0.95 0.950 NA 1 0
## 46 40 0.25 0.4750 0.725 0.9250 1.00 0.675 0.34278273 4 0
## 47 45 0.45 0.4500 0.450 0.4500 0.45 0.450 NA 1 0
## 48 47.1 0.30 0.3000 0.300 0.3000 0.30 0.300 NA 1 0
## 49 52.2 0.20 0.2000 0.200 0.2000 0.20 0.200 NA 1 0
## 50 60 1.00 1.0000 1.000 1.0000 1.00 1.000 NA 1 0
## 51 63 0.05 0.0500 0.050 0.0500 0.05 0.050 NA 1 0
## 52 64.8 0.40 0.4000 0.400 0.4000 0.40 0.400 NA 1 0
## 53 70 0.95 0.9500 0.950 0.9500 0.95 0.950 0.00000000 2 0
## 54 74.2 0.55 0.5500 0.550 0.5500 0.55 0.550 NA 1 0
## 55 74.6 1.00 1.0000 1.000 1.0000 1.00 1.000 NA 1 0
## 56 75 0.80 0.8000 0.800 0.8000 0.80 0.800 NA 1 0
## 57 80 0.35 0.3500 0.350 0.3500 0.35 0.350 NA 1 0
## 58 104 1.00 1.0000 1.000 1.0000 1.00 1.000 NA 1 0
## 59 112.4 0.55 0.5500 0.550 0.5500 0.55 0.550 NA 1 0xyplot(prop_active ~ burrow_dist_mts, data = Penguin_Data)
cor(prop_active ~ burrow_dist_mts, data = Penguin_Data)## [1] 0.2351067The correlation coefficient (r) is 0.235. This suggests a positive association with a weak to moderate linear relationship between burrow distance from the trail and the proportion of time spend being active.
summary(lm(prop_active ~ burrow_dist_mts, data = Penguin_Data))##
## Call:
## lm(formula = prop_active ~ burrow_dist_mts, data = Penguin_Data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.60437 -0.26752 -0.05805 0.27603 0.53892
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.451417 0.054316 8.311 2.16e-12 ***
## burrow_dist_mts 0.003221 0.001498 2.150 0.0346 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3179 on 79 degrees of freedom
## Multiple R-squared: 0.05528, Adjusted R-squared: 0.04332
## F-statistic: 4.622 on 1 and 79 DF, p-value: 0.03462The p-value is 0.03462. Since the p-value less than 0.05, we have strong evidence that there is an association between burrow distance from the trail and the proportion of time spend being active.
confint(lm(prop_active ~ burrow_dist_mts, data = Penguin_Data))## 2.5 % 97.5 %
## (Intercept) 0.3433043358 0.559530344
## burrow_dist_mts 0.0002389776 0.006203988We are 95% confident that a one meter increase in burrow distance from the trail is associated with an average increase of 0.0239 to 0.6204 percentage of time spend being active in the population of penguins represented by this sample. Since the number 0 is not included in the confidence interval, there is strong evidence that there is an association between burrow distance from the trail and time spent in burrow.
- X = time of day, Y = time in burrow
favstats(time_in_burrow_sec ~ time_day, data = Penguin_Data)## time_day min Q1 median Q3 max mean sd n missing
## 1 AFT 0 0 0 0 1200 107.0000 309.9405 30 0
## 2 MID 0 0 0 0 960 120.0000 270.6314 30 0
## 3 MOR 0 0 0 780 1200 311.4286 473.0569 21 0anova(lm(time_in_burrow_sec ~ time_day, data = Penguin_Data))## Analysis of Variance Table
##
## Response: time_in_burrow_sec
## Df Sum Sq Mean Sq F value Pr(>F)
## time_day 2 611935 305968 2.5428 0.08515 .
## Residuals 78 9385487 120327
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1The p-value is 0.08515. Since the p-value is between 0.05 and 0.1, we have #moderate evidence that there is an association between time of day and time the #penguins spent inside of their burrows.
dotPlot(~ time_in_burrow_sec | time_day, data = Penguin_Data, cex = 0.75, width = 1)
histogram(~ time_in_burrow_sec | time_day, data = Penguin_Data, width = 1)
bwplot(~ time_in_burrow_sec | time_day, horizontal = TRUE, data = Penguin_Data)
install.packages('tidyverse')##
## The downloaded binary packages are in
## /var/folders/8l/gzyk464x6rd4yf1gn1d4r0g40000gn/T//RtmpGlkZQ0/downloaded_packageslibrary(tidyverse)
ggplot(data=Penguin_Data, mapping=aes(x=time_day, y=time_in_burrow_sec))+
geom_boxplot()+
stat_summary(fun = "mean", geom = "point", shape = 8,
size = 2, color = "blue")+
scale_y_continuous(limits = c(-0.1, 1))
install.packages('pairwiseCI')##
## The downloaded binary packages are in
## /var/folders/8l/gzyk464x6rd4yf1gn1d4r0g40000gn/T//RtmpGlkZQ0/downloaded_packageslibrary(pairwiseCI)
pairwiseCI(time_in_burrow_sec ~ time_day, data = Penguin_Data, method="Param.diff")##
## 95 %-confidence intervals
## Method: Difference of means assuming Normal distribution, allowing unequal variances
##
##
## estimate lower upper
## MID-AFT 13.0 -137.43 163.4
## MOR-AFT 204.4 -35.41 444.3
## MOR-MID 191.4 -42.58 425.4
##
## We are 95% confident that the difference in population means regarding time in burrow between morning and afternoon is between -35.41 and 444.3 seconds. We are 95% confident that the difference in population means regarding time in burrow between midday and afternoon is between -137.43 and 163.4 seconds. We are 95% confident that the difference in population means regarding time in burrow between midday and morning is between –42.58 and 425.4 seconds.
X = time of day, Y = prop_active
histogram(~ prop_active |time_day, data = Penguin_Data, width = 1)
dotPlot(~ prop_active |time_day, data = Penguin_Data, cex = 0.75, width = 1)
bwplot(~ prop_active |time_day, horizontal = TRUE, data = Penguin_Data)
library(tidyverse)
ggplot(data=Penguin_Data, mapping=aes(x=time_day, y=prop_active))+
geom_boxplot()+
stat_summary(fun = "mean", geom = "point", shape = 8,
size = 2, color = "blue")+
scale_y_continuous(limits = c(-0.1, 1))
- X = time of day, Y = % of time spent active
favstats(prop_active ~ time_day, data = Penguin_Data)## time_day min Q1 median Q3 max mean sd n missing
## 1 AFT 0.00 0.3625 0.675 0.9500 1 0.6200000 0.3377410 30 0
## 2 MID 0.05 0.2625 0.450 0.6375 1 0.4816667 0.2765188 30 0
## 3 MOR 0.00 0.1500 0.450 0.9500 1 0.5095238 0.3614620 21 0anova(lm(prop_active ~ time_day, data = Penguin_Data))## Analysis of Variance Table
##
## Response: prop_active
## Df Sum Sq Mean Sq F value Pr(>F)
## time_day 2 0.3136 0.15679 1.5027 0.2289
## Residuals 78 8.1385 0.10434The p-value is 0.2289. Since the p-value is greater than 0.1, we have weak evidence that there is an association between time of day and the proportion of time penguins are active within a given 20 minute period.
library(pairwiseCI)
pairwiseCI(prop_active ~ time_day, data = Penguin_Data, method="Param.diff")##
## 95 %-confidence intervals
## Method: Difference of means assuming Normal distribution, allowing unequal variances
##
##
## estimate lower upper
## MID-AFT -0.1383 -0.2980 0.0213
## MOR-AFT -0.1105 -0.3126 0.0917
## MOR-MID 0.0279 -0.1621 0.2179
##
## We are 95% confident that the difference in population proportions of time active to total time between morning and afternoon is between -0.3126 and 0.0917. We are 95% confident that the difference in population proportions of time active to total time between midday and afternoon is between -0.2980 and 0.0213. We are 95% confident that the difference in population proportions of time active to total time between midday and morning is between -0.1621 and 0.2179.
X = Time of day, Y = # of calls
histogram(~ Calls |time_day, data = Penguin_Data, width = 1)
dotPlot(~ Calls |time_day, data = Penguin_Data, cex = 0.75, width = 1)
bwplot(~ Calls |time_day, horizontal = TRUE, data = Penguin_Data)
library(tidyverse)
ggplot(data=Penguin_Data, mapping=aes(x=time_day, y=Calls))+
geom_boxplot()+
stat_summary(fun = "mean", geom = "point", shape = 8,
size = 2, color = "blue")+
scale_y_continuous(limits = c(-0.1, 1))
#. X = time of day, Y = calls
favstats(Calls ~ time_day, data = Penguin_Data)## time_day min Q1 median Q3 max mean sd n missing
## 1 AFT 0 0 0 0 3 0.2333333 0.6260623 30 0
## 2 MID 0 0 0 0 2 0.1666667 0.4611330 30 0
## 3 MOR 0 0 0 0 3 0.3333333 0.9128709 21 0anova(lm(Calls ~ time_day, data = Penguin_Data))## Analysis of Variance Table
##
## Response: Calls
## Df Sum Sq Mean Sq F value Pr(>F)
## time_day 2 0.343 0.17160 0.3914 0.6774
## Residuals 78 34.200 0.43846The p-value is 0.6774. Since the p-value is greater than 0.1, we have weak evidence that there is an association between time of day and the number of calls the penguins did within a given 20 minute period.
library(pairwiseCI)
pairwiseCI(Calls ~ time_day, data = Penguin_Data, method="Param.diff")##
## 95 %-confidence intervals
## Method: Difference of means assuming Normal distribution, allowing unequal variances
##
##
## estimate lower upper
## MID-AFT -0.0667 -0.3514 0.2180
## MOR-AFT 0.1000 -0.3673 0.5673
## MOR-MID 0.1667 -0.2769 0.6103
##
## We are 95% confident that the difference in mean calls of the Magellanic Penguins between morning and afternoon is between -0.3673 and 0.5673 calls. We are 95% confident that the difference in mean calls of the Magellanic Penguins between morning and midday is between -0.2769 and 0.6103 calls. We are 95% confident that the difference in mean calls of the Magellanic Penguins between midday and afternoon is between -0.3514 and 0.2180 calls.
- X = burrow dist, Y = calls
xyplot(Calls ~ burrow_dist_mts, data = Penguin_Data)
favstats(Calls ~ burrow_dist_mts, data = Penguin_Data)## burrow_dist_mts min Q1 median Q3 max mean sd n missing
## 1 3 0 0.00 0.0 0.00 0 0.0 0.0000000 4 0
## 2 4.5 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 3 5 0 0.00 0.0 0.00 0 0.0 0.0000000 2 0
## 4 5.1 3 3.00 3.0 3.00 3 3.0 NA 1 0
## 5 6 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 6 6.2 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 7 6.5 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 8 6.9 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 9 7 0 0.00 0.0 0.00 0 0.0 0.0000000 2 0
## 10 7.1 1 1.00 1.0 1.00 1 1.0 NA 1 0
## 11 8 0 0.00 0.0 0.00 0 0.0 0.0000000 2 0
## 12 8.1 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 13 8.5 0 0.25 0.5 0.75 1 0.5 0.7071068 2 0
## 14 9.5 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 15 10 0 0.00 0.0 0.00 0 0.0 0.0000000 2 0
## 16 11.1 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 17 12.7 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 18 12.8 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 19 13.2 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 20 13.7 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 21 15 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 22 16 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 23 17 0 0.00 1.0 1.00 3 1.0 1.2247449 5 0
## 24 18 0 0.00 0.0 0.00 0 0.0 0.0000000 2 0
## 25 18.4 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 26 20 0 0.00 0.0 0.00 0 0.0 0.0000000 2 0
## 27 20.4 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 28 21.6 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 29 22.1 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 30 22.8 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 31 23.2 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 32 23.5 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 33 24.4 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 34 25 0 0.00 0.0 0.00 0 0.0 0.0000000 2 0
## 35 25.7 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 36 26 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 37 27.9 1 1.00 1.0 1.00 1 1.0 NA 1 0
## 38 29.4 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 39 30 0 0.00 0.0 0.00 0 0.0 0.0000000 2 0
## 40 30.7 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 41 31.8 1 1.00 1.0 1.00 1 1.0 NA 1 0
## 42 33.1 0 0.25 0.5 0.75 1 0.5 0.7071068 2 0
## 43 34.8 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 44 38 0 0.00 0.0 0.00 0 0.0 0.0000000 2 0
## 45 38.8 1 1.00 1.0 1.00 1 1.0 NA 1 0
## 46 40 0 0.00 0.0 0.00 0 0.0 0.0000000 4 0
## 47 45 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 48 47.1 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 49 52.2 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 50 60 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 51 63 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 52 64.8 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 53 70 0 0.00 0.0 0.00 0 0.0 0.0000000 2 0
## 54 74.2 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 55 74.6 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 56 75 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 57 80 0 0.00 0.0 0.00 0 0.0 NA 1 0
## 58 104 3 3.00 3.0 3.00 3 3.0 NA 1 0
## 59 112.4 2 2.00 2.0 2.00 2 2.0 NA 1 0cor(Calls ~ burrow_dist_mts, data = Penguin_Data)## [1] 0.2093953The correlation coefficient (r) is 0.2093953. This suggests a positive association with a weak linear relationship between burrow distance from the trail and the number of calls in a given 20-minute period.
summary(lm(Calls ~ burrow_dist_mts, data = Penguin_Data))$coefficients[,4]## (Intercept) burrow_dist_mts
## 0.50002506 0.06063846The p-value is 0.0606. Since the p-value is between 0.05 and 0.1, we have moderate evidence that there is an association between burrow distance from the trail and the number of calls in a given 20-minute period.
confint(lm(Calls ~ burrow_dist_mts, data = Penguin_Data))## 2.5 % 97.5 %
## (Intercept) -0.1450315643 0.29473091
## burrow_dist_mts -0.0002654631 0.01186623We are 95% confident that a one meter increase in burrow distance from the trail is associated with an average increase of -0.000265 to 0.011866 calls in a 20-minute period for the population of penguins represented by this sample. Since the number 0 is included in the confidence interval, there is not strong evidence that there is an association between burrow distance from the trail and number of calls.
X = Wind speed, Y = Time in Burrow
xyplot(time_in_burrow_sec ~ Wind_kph, data = Penguin_Data)
favstats(time_in_burrow_sec ~ Wind_kph, data = Penguin_Data)## Wind_kph min Q1 median Q3 max mean sd n missing
## 1 12.9 0 0 0 900 1200 400.00000 619.6773 6 0
## 2 14.5 0 0 0 0 600 93.33333 205.9126 9 0
## 3 19.3 0 0 0 0 120 13.33333 40.0000 9 0
## 4 20.9 0 0 0 630 1200 296.00000 448.6933 15 0
## 5 24.1 0 0 0 0 960 115.00000 292.2172 12 0
## 6 25.7 30 135 240 330 420 230.00000 195.1922 3 0
## 7 32.2 0 0 0 360 1200 286.66667 483.5287 9 0
## 8 37 0 0 0 0 900 100.00000 300.0000 9 0
## 9 40.2 0 0 0 0 0 0.00000 0.0000 6 0
## 10 46.7 0 0 0 0 0 0.00000 0.0000 3 0cor(time_in_burrow_sec ~ Wind_kph, data = Penguin_Data)## [1] -0.1318761The correlation coefficient (r) is -0.1319. This suggests a negative association with a weak linear relationship between wind speed and the time the penguins spent inside their burrows.
summary(lm(time_in_burrow_sec ~ Wind_kph, data = Penguin_Data))$coefficients[,4]## (Intercept) Wind_kph
## 0.01273802 0.24056696The p-value is 0.2406. Since the p-value is greater than 0.1, we have weak evidence that there is an association between wind speed and the time the penguins spent inside their burrows.
confint(lm(time_in_burrow_sec ~ Wind_kph, data = Penguin_Data))## 2.5 % 97.5 %
## (Intercept) 64.03243 520.360051
## Wind_kph -13.40403 3.413333We are 95% confident that a one kilometer increase in wind speed is associated with an average increase of -13.4 to 3.4 seconds increase in time spent in the burrow in a given 20 minute period in the population of penguins represented by this sample.
X = Wind speed, Y = Proportion Active
xyplot(prop_active ~ Wind_kph, data = Penguin_Data)
favstats(prop_active ~ Wind_kph, data = Penguin_Data)## Wind_kph min Q1 median Q3 max mean sd n missing
## 1 12.9 0.00 0.2000 0.375 0.8875 1.00 0.4916667 0.4317600 6 0
## 2 14.5 0.05 0.3500 0.600 0.9500 1.00 0.6222222 0.3518799 9 0
## 3 19.3 0.05 0.2500 0.450 0.9000 1.00 0.5500000 0.3614208 9 0
## 4 20.9 0.15 0.2250 0.450 0.7000 1.00 0.5200000 0.3138471 15 0
## 5 24.1 0.05 0.3250 0.450 0.5500 0.95 0.4625000 0.2797117 12 0
## 6 25.7 0.80 0.9000 1.000 1.0000 1.00 0.9333333 0.1154701 3 0
## 7 32.2 0.00 0.1500 0.300 0.5500 1.00 0.4055556 0.3753702 9 0
## 8 37 0.20 0.3000 0.400 0.5500 1.00 0.4611111 0.2509703 9 0
## 9 40.2 0.35 0.3875 0.650 0.9500 1.00 0.6666667 0.3060501 6 0
## 10 46.7 0.65 0.7000 0.750 0.8250 0.90 0.7666667 0.1258306 3 0cor(prop_active ~ Wind_kph, data = Penguin_Data)## [1] 0.02962801The correlation coefficient (r) is 0.02963. This suggests a positive association with a weak linear relationship between wind speed and the proportion of time the penguins were active.
summary(lm(prop_active ~ Wind_kph, data = Penguin_Data))$coefficients[,4]## (Intercept) Wind_kph
## 6.456605e-06 7.928857e-01The p-value is 0.7929. Since the p-value is greater than 0.1, we have weak evidence that there is an association between wind speed and the proportion of time the penguins were active.
confint(lm(prop_active ~ Wind_kph, data = Penguin_Data))## 2.5 % 97.5 %
## (Intercept) 0.302264205 0.725355435
## Wind_kph -0.006764334 0.008828148We are 95% confident that a one kilometer increase in wind speed is associated with an average increase of -0.676 to 0.883 percentage increase in time spent active in a given 20 minute period in the population of penguins represented by this sample.
X = Temperature, Y = Time in Burrow
xyplot(time_in_burrow_sec ~ Temperature_C, data = Penguin_Data)
favstats(time_in_burrow_sec ~ Temperature_C, data = Penguin_Data)## Temperature_C min Q1 median Q3 max mean sd n missing
## 1 10 0 0 0 0 600 93.33333 205.9126 9 0
## 2 11.1 0 0 0 0 480 50.00000 139.7400 12 0
## 3 12.2 0 0 0 90 1200 215.00000 432.2562 12 0
## 4 12.8 0 0 0 900 1200 400.00000 619.6773 6 0
## 5 15 0 0 0 0 960 115.00000 292.2172 12 0
## 6 16.1 0 0 0 60 1200 231.42857 423.5361 21 0
## 7 17.2 0 0 0 0 0 0.00000 0.0000 6 0
## 8 20 30 135 240 330 420 230.00000 195.1922 3 0cor(time_in_burrow_sec ~ Temperature_C, data = Penguin_Data)## [1] 0.05504059The correlation coefficient (r) is 0.05504. This suggests a positive association with a weak linear relationship between temperature and time the penguins spent inside their burrows.
summary(lm(time_in_burrow_sec ~ Temperature_C, data = Penguin_Data))$coefficients[,4]## (Intercept) Temperature_C
## 0.7667600 0.6255242The p-value is 0.6256. Since the p-value is greater than 0.1, we have weak evidence that there is an association between temperature and time the penguins spent inside their burrows.
confint(lm(time_in_burrow_sec ~ Temperature_C, data = Penguin_Data))## 2.5 % 97.5 %
## (Intercept) -358.15501 484.10040
## Temperature_C -22.40259 37.03275We are 95% confident that a one degree Celsius increase in temperature is associated with an average increase of -22.40 to 37.03 seconds increase in time spent in the burrow in a given 20 minute period in the population of penguins represented by this sample.
X = Temperature, Y = Proportion Active
xyplot(prop_active ~ Temperature_C, data = Penguin_Data)
favstats(prop_active ~ Temperature_C, data = Penguin_Data)## Temperature_C min Q1 median Q3 max mean sd n missing
## 1 10 0.05 0.3500 0.600 0.9500 1.00 0.6222222 0.3518799 9 0
## 2 11.1 0.05 0.2000 0.400 0.7000 1.00 0.4750000 0.3071127 12 0
## 3 12.2 0.00 0.1500 0.350 0.6625 1.00 0.4458333 0.3677069 12 0
## 4 12.8 0.00 0.2000 0.375 0.8875 1.00 0.4916667 0.4317600 6 0
## 5 15 0.05 0.3250 0.450 0.5500 0.95 0.4625000 0.2797117 12 0
## 6 16.1 0.15 0.3000 0.550 0.7500 1.00 0.5619048 0.2978694 21 0
## 7 17.2 0.35 0.3875 0.650 0.9500 1.00 0.6666667 0.3060501 6 0
## 8 20 0.80 0.9000 1.000 1.0000 1.00 0.9333333 0.1154701 3 0cor(prop_active ~ Temperature_C, data = Penguin_Data)## [1] 0.162404The correlation coefficient (r) is 0.1624. This suggests a positive association with a weak linear relationship between temperature and the porportion of time the penguins were active.
summary(lm(prop_active ~ Temperature_C, data = Penguin_Data))$coefficients[,4]## (Intercept) Temperature_C
## 0.1738436 0.1474623The p-value is 0.1474623. Since the p-value is greater than 0.1, we have weak evidence that there is an association between temperature and the porportion of time the penguins were active.
confint(lm(prop_active ~ Temperature_C, data = Penguin_Data))## 2.5 % 97.5 %
## (Intercept) -0.118829977 0.64647891
## Temperature_C -0.007156834 0.04684863We are 95% confident that a one degree Celsius increase in temperature is associated with an average increase of 0.716 to 4.684 percentage increase in time spent active in a given 20 minute period in the population of penguins represented by this sample.
X = Wind, Y = Calls
xyplot(Calls ~ Wind_kph, data = Penguin_Data)
favstats(Calls ~ Wind_kph, data = Penguin_Data)## Wind_kph min Q1 median Q3 max mean sd n missing
## 1 12.9 0 0 0 0 0 0.0000000 0.0000000 6 0
## 2 14.5 0 0 0 0 1 0.2222222 0.4409586 9 0
## 3 19.3 0 0 0 0 1 0.2222222 0.4409586 9 0
## 4 20.9 0 0 0 0 0 0.0000000 0.0000000 15 0
## 5 24.1 0 0 0 0 0 0.0000000 0.0000000 12 0
## 6 25.7 1 1 1 2 3 1.6666667 1.1547005 3 0
## 7 32.2 0 0 0 1 3 0.7777778 1.3017083 9 0
## 8 37 0 0 0 0 2 0.3333333 0.7071068 9 0
## 9 40.2 0 0 0 0 0 0.0000000 0.0000000 6 0
## 10 46.7 0 0 0 0 0 0.0000000 0.0000000 3 0cor(Calls ~ Wind_kph, data = Penguin_Data)## [1] 0.09783985The correlation coefficient (r) is 0.0978. This suggests a positive association with a weak linear relationship between wind and the number of penguin calls within a given 20-minute period.
summary(lm(Calls ~ Wind_kph, data = Penguin_Data))$coefficients[,4]## (Intercept) Wind_kph
## 0.7837789 0.3848692The p-value is 0.385. Since the p-value is greater than 0.1, we have weak evidence that there is an association between wind and the number of penguin calls within a given 20-minute period.
confint(lm(Calls ~ Wind_kph, data = Penguin_Data))## 2.5 % 97.5 %
## (Intercept) -0.36689979 0.48469913
## Wind_kph -0.00880334 0.02258124We are 95% confident that a one kilometer increase in wind speed is associated with an average increase of -0.8803 to 2.258 calls in a given 20 minute period in the population of penguins represented by this sample.
X = Temperature, Y = Calls
xyplot(Calls ~ Temperature_C, data = Penguin_Data)
favstats(Calls ~ Temperature_C, data = Penguin_Data)## Temperature_C min Q1 median Q3 max mean sd n missing
## 1 10 0 0 0 0.00 1 0.2222222 0.4409586 9 0
## 2 11.1 0 0 0 0.00 1 0.1666667 0.3892495 12 0
## 3 12.2 0 0 0 0.25 3 0.5833333 1.1645002 12 0
## 4 12.8 0 0 0 0.00 0 0.0000000 0.0000000 6 0
## 5 15 0 0 0 0.00 0 0.0000000 0.0000000 12 0
## 6 16.1 0 0 0 0.00 2 0.1428571 0.4780914 21 0
## 7 17.2 0 0 0 0.00 0 0.0000000 0.0000000 6 0
## 8 20 1 1 1 2.00 3 1.6666667 1.1547005 3 0cor(Calls ~ Temperature_C, data = Penguin_Data)## [1] 0.08137067The correlation coefficient (r) is 0.0814. This suggests a positive association with a weak linear relationship between temperature and the number of penguin calls within a given 20-minute period.
summary(lm(Calls ~ Temperature_C, data = Penguin_Data))$coefficients[,4]## (Intercept) Temperature_C
## 0.9084304 0.4702009The p-value is 0.4702. Since the p-value is greater than 0.1, we have weak evidence that there is an association between temperature and the number of penguin calls within a given 20-minute period.
confint(lm(Calls ~ Temperature_C, data = Penguin_Data))## 2.5 % 97.5 %
## (Intercept) -0.82668697 0.73609150
## Temperature_C -0.03503812 0.07524228