week_4_assignment
2024-02-05
data <- read.csv("/Users/manojdannana/Desktop/Manoj/IUPUI/class work/intro to statistics/datasets/Occupancy_Estimation.csv")set.seed(42)sample_sizes <- sapply(1:5, function(x) round(nrow(data) * 0.5))
subsamples <- lapply(sample_sizes, function(size) data[sample(1:nrow(data), size, replace = TRUE), ])
df_1 <- subsamples[[1]]
df_2 <- subsamples[[2]]
df_3 <- subsamples[[3]]
df_4 <- subsamples[[4]]
df_5 <- subsamples[[5]]head(df_1)## Date Time S1_Temp S2_Temp S3_Temp S4_Temp S1_Light S2_Light
## 2369 23/12/17 7:49:48 25.00 25.00 24.44 25.31 3 4
## 5273 24/12/17 8:54:29 25.13 25.13 24.63 25.38 7 7
## 9290 11/01/18 1:47:41 25.19 25.19 24.75 25.25 0 0
## 1252 22/12/17 22:11:18 25.56 25.63 25.19 25.94 0 0
## 8826 10/01/18 21:47:43 25.38 25.38 25.00 25.50 0 0
## 356 22/12/17 14:20:33 26.19 26.75 26.06 26.38 18 22
## S3_Light S4_Light S1_Sound S2_Sound S3_Sound S4_Sound S5_CO2 S5_CO2_Slope
## 2369 18 13 0.08 0.05 0.06 0.06 355 -0.023076923
## 5273 35 23 0.07 0.05 0.05 0.07 360 -0.003846154
## 9290 0 0 0.07 0.05 0.06 0.09 345 0.000000000
## 1252 0 0 0.07 0.05 0.06 0.06 480 -1.307692308
## 8826 0 0 0.07 0.05 0.06 0.08 360 -0.238461538
## 356 96 59 0.07 0.05 0.06 0.06 965 0.050000000
## S6_PIR S7_PIR Room_Occupancy_Count
## 2369 0 0 0
## 5273 0 0 0
## 9290 0 0 0
## 1252 0 0 0
## 8826 0 0 0
## 356 0 0 0head(df_2)## Date Time S1_Temp S2_Temp S3_Temp S4_Temp S1_Light S2_Light
## 2609 23/12/17 9:53:52 25.06 25.13 24.69 25.38 8 9
## 7734 26/12/17 6:08:45 25.19 25.25 24.63 25.50 0 0
## 6886 25/12/17 22:49:39 25.38 25.38 25.06 25.88 0 0
## 1741 23/12/17 2:25:04 25.31 25.31 24.81 25.63 0 0
## 1749 23/12/17 2:29:09 25.31 25.25 24.81 25.69 0 0
## 3913 23/12/17 21:09:53 25.75 25.75 25.38 26.00 0 0
## S3_Light S4_Light S1_Sound S2_Sound S3_Sound S4_Sound S5_CO2 S5_CO2_Slope
## 2609 41 28 0.08 0.05 0.07 0.06 355 -0.03846154
## 7734 0 0 0.08 0.04 0.07 0.09 355 0.00000000
## 6886 0 0 0.08 0.06 0.06 0.10 355 0.00000000
## 1741 0 0 0.08 0.05 0.06 0.06 365 -0.05769231
## 1749 0 0 0.07 0.05 0.06 0.06 365 0.00000000
## 3913 0 0 0.07 0.05 0.06 0.07 710 -1.90769231
## S6_PIR S7_PIR Room_Occupancy_Count
## 2609 0 0 0
## 7734 0 0 0
## 6886 0 0 0
## 1741 0 0 0
## 1749 0 0 0
## 3913 0 0 0head(df_3)## Date Time S1_Temp S2_Temp S3_Temp S4_Temp S1_Light S2_Light
## 8656 10/01/18 20:20:24 25.50 25.50 25.13 25.63 0 0
## 9249 11/01/18 1:26:15 25.19 25.19 24.81 25.31 0 0
## 5140 24/12/17 7:46:04 25.06 25.13 24.50 25.44 3 3
## 4886 24/12/17 5:34:51 25.19 25.19 24.63 25.50 0 0
## 9920 11/01/18 7:11:55 25.06 25.06 24.56 25.19 0 0
## 2203 23/12/17 6:23:00 25.06 25.06 24.44 25.19 0 0
## S3_Light S4_Light S1_Sound S2_Sound S3_Sound S4_Sound S5_CO2 S5_CO2_Slope
## 8656 0 0 0.07 0.05 0.05 0.08 390 -0.88846154
## 9249 0 0 0.07 0.04 0.05 0.09 345 0.00000000
## 5140 17 12 0.07 0.04 0.06 0.06 360 0.04230769
## 4886 0 0 0.07 0.05 0.15 0.06 360 -0.10384615
## 9920 5 3 0.07 0.05 0.06 0.09 345 0.00000000
## 2203 0 0 0.08 0.05 0.06 0.05 355 -0.18846154
## S6_PIR S7_PIR Room_Occupancy_Count
## 8656 0 0 0
## 9249 0 0 0
## 5140 0 0 0
## 4886 0 0 0
## 9920 0 0 0
## 2203 0 0 0head(df_4)## Date Time S1_Temp S2_Temp S3_Temp S4_Temp S1_Light S2_Light
## 6542 25/12/17 19:51:58 25.44 25.44 25.19 25.94 0 0
## 1647 23/12/17 1:36:03 25.31 25.31 24.88 25.75 0 0
## 8336 10/01/18 17:35:29 25.94 26.19 25.88 25.94 146 230
## 6215 25/12/17 17:02:27 25.44 25.44 25.31 26.19 1 1
## 1742 23/12/17 2:25:35 25.25 25.31 24.81 25.69 0 0
## 6211 25/12/17 17:00:25 25.44 25.44 25.31 26.19 1 2
## S3_Light S4_Light S1_Sound S2_Sound S3_Sound S4_Sound S5_CO2 S5_CO2_Slope
## 6542 0 0 0.08 0.05 0.06 0.09 355 0.09230769
## 1647 0 0 0.07 0.04 0.06 0.06 370 0.00000000
## 8336 170 19 0.10 0.31 0.08 0.08 835 1.27692308
## 6215 9 6 0.08 0.05 0.05 0.10 350 0.00000000
## 1742 0 0 0.07 0.05 0.07 0.07 365 -0.06538461
## 6211 10 7 0.07 0.05 0.06 0.10 350 0.00000000
## S6_PIR S7_PIR Room_Occupancy_Count
## 6542 0 0 0
## 1647 0 0 0
## 8336 1 0 2
## 6215 0 0 0
## 1742 0 0 0
## 6211 0 0 0head(df_5)## Date Time S1_Temp S2_Temp S3_Temp S4_Temp S1_Light S2_Light
## 5997 25/12/17 15:10:07 25.44 25.44 25.44 26.13 14 17
## 9072 10/01/18 23:55:22 25.25 25.31 24.88 25.38 0 0
## 1989 23/12/17 4:32:43 25.19 25.19 24.63 25.44 0 0
## 9626 11/01/18 4:40:47 25.19 25.13 24.63 25.25 0 0
## 3338 23/12/17 16:10:41 26.06 26.81 25.50 26.31 119 22
## 8632 10/01/18 20:08:09 25.56 25.50 25.19 25.63 0 0
## S3_Light S4_Light S1_Sound S2_Sound S3_Sound S4_Sound S5_CO2 S5_CO2_Slope
## 5997 65 47 0.08 0.06 0.07 0.11 355 0.0000000
## 9072 0 0 0.07 0.05 0.05 0.08 345 0.0000000
## 1989 0 0 0.08 0.05 0.06 0.06 360 0.0000000
## 9626 0 0 0.08 0.05 0.06 0.08 345 0.0000000
## 3338 34 23 0.10 0.12 0.06 0.07 485 0.7076923
## 8632 0 0 0.08 0.05 0.06 0.09 415 -1.1192308
## S6_PIR S7_PIR Room_Occupancy_Count
## 5997 0 0 0
## 9072 0 0 0
## 1989 0 0 0
## 9626 0 0 0
## 3338 0 0 1
## 8632 0 0 0analyze_subsample <- function(subsample, subsample_number) {
cat("Analysis for Subsample", subsample_number, "\n")
# Summary statistics
summary_stats <- summary(subsample)
print(summary_stats)
# Check for anomalies in S6_PIR and S7_PIR
anomalies <- as.data.frame(table(subsample$S6_PIR, subsample$S7_PIR))
colnames(anomalies) <- c("S6_PIR", "S7_PIR", "Count")
cat("Anomalies in S6_PIR and S7_PIR:\n")
print(anomalies)
# Monte Carlo simulation for a selected column (e.g., S1_Temp)
column_to_simulate <- "S1_Temp"
num_simulations <- 1000
simulated_means <- replicate(num_simulations, mean(sample(subsample[[column_to_simulate]], replace = TRUE)))
cat("Monte Carlo Simulation for", column_to_simulate, "Mean:\n")
hist(simulated_means, main = paste("Distribution of Simulated Means for", column_to_simulate))
}list_df = list(df_1, df_2, df_3, df_4, df_5)
for (i in 1:5){
print(analyze_subsample(list_df[[i]], i))
}## Analysis for Subsample 1
## Date Time S1_Temp S2_Temp
## Length:5064 Length:5064 Min. :24.94 Min. :24.75
## Class :character Class :character 1st Qu.:25.19 1st Qu.:25.19
## Mode :character Mode :character Median :25.38 Median :25.38
## Mean :25.45 Mean :25.53
## 3rd Qu.:25.63 3rd Qu.:25.63
## Max. :26.38 Max. :28.94
## S3_Temp S4_Temp S1_Light S2_Light
## Min. :24.44 Min. :25.00 Min. : 0.00 Min. : 0.00
## 1st Qu.:24.69 1st Qu.:25.44 1st Qu.: 0.00 1st Qu.: 0.00
## Median :24.94 Median :25.75 Median : 0.00 Median : 0.00
## Mean :25.05 Mean :25.74 Mean : 24.03 Mean : 24.44
## 3rd Qu.:25.31 3rd Qu.:26.00 3rd Qu.: 11.00 3rd Qu.: 12.00
## Max. :26.19 Max. :26.50 Max. :165.00 Max. :257.00
## S3_Light S4_Light S1_Sound S2_Sound
## Min. : 0.00 Min. : 0.00 Min. :0.060 Min. :0.0400
## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.:0.070 1st Qu.:0.0500
## Median : 0.00 Median : 0.00 Median :0.080 Median :0.0500
## Mean : 32.42 Mean :13.03 Mean :0.165 Mean :0.1168
## 3rd Qu.: 49.00 3rd Qu.:22.00 3rd Qu.:0.080 3rd Qu.:0.0600
## Max. :280.00 Max. :74.00 Max. :3.830 Max. :3.4400
## S3_Sound S4_Sound S5_CO2 S5_CO2_Slope
## Min. :0.0500 Min. :0.05000 Min. : 345.0 Min. :-6.28846
## 1st Qu.:0.0600 1st Qu.:0.06000 1st Qu.: 355.0 1st Qu.:-0.04615
## Median :0.0600 Median :0.08000 Median : 360.0 Median : 0.00000
## Mean :0.1473 Mean :0.09941 Mean : 457.3 Mean :-0.02976
## 3rd Qu.:0.0700 3rd Qu.:0.10000 3rd Qu.: 450.0 3rd Qu.: 0.00000
## Max. :3.6600 Max. :1.54000 Max. :1270.0 Max. : 8.83846
## S6_PIR S7_PIR Room_Occupancy_Count
## Min. :0.00000 Min. :0.00000 Min. :0.0000
## 1st Qu.:0.00000 1st Qu.:0.00000 1st Qu.:0.0000
## Median :0.00000 Median :0.00000 Median :0.0000
## Mean :0.08531 Mean :0.06991 Mean :0.3726
## 3rd Qu.:0.00000 3rd Qu.:0.00000 3rd Qu.:0.0000
## Max. :1.00000 Max. :1.00000 Max. :3.0000
## Anomalies in S6_PIR and S7_PIR:
## S6_PIR S7_PIR Count
## 1 0 0 4496
## 2 1 0 214
## 3 0 1 136
## 4 1 1 218
## Monte Carlo Simulation for S1_Temp Mean:
## $breaks
## [1] 25.430 25.435 25.440 25.445 25.450 25.455 25.460 25.465
##
## $counts
## [1] 11 120 332 379 132 24 2
##
## $density
## [1] 2.2 24.0 66.4 75.8 26.4 4.8 0.4
##
## $mids
## [1] 25.4325 25.4375 25.4425 25.4475 25.4525 25.4575 25.4625
##
## $xname
## [1] "simulated_means"
##
## $equidist
## [1] TRUE
##
## attr(,"class")
## [1] "histogram"
## Analysis for Subsample 2
## Date Time S1_Temp S2_Temp
## Length:5064 Length:5064 Min. :24.94 Min. :24.75
## Class :character Class :character 1st Qu.:25.19 1st Qu.:25.19
## Mode :character Mode :character Median :25.38 Median :25.38
## Mean :25.45 Mean :25.54
## 3rd Qu.:25.63 3rd Qu.:25.63
## Max. :26.38 Max. :29.00
## S3_Temp S4_Temp S1_Light S2_Light
## Min. :24.44 Min. :25.00 Min. : 0.00 Min. : 0.00
## 1st Qu.:24.69 1st Qu.:25.44 1st Qu.: 0.00 1st Qu.: 0.00
## Median :24.94 Median :25.75 Median : 0.00 Median : 0.00
## Mean :25.05 Mean :25.74 Mean : 24.26 Mean : 25.27
## 3rd Qu.:25.31 3rd Qu.:26.00 3rd Qu.: 10.00 3rd Qu.: 12.00
## Max. :26.13 Max. :26.50 Max. :165.00 Max. :257.00
## S3_Light S4_Light S1_Sound S2_Sound
## Min. : 0.00 Min. : 0.00 Min. :0.0600 Min. :0.040
## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.:0.0700 1st Qu.:0.050
## Median : 0.00 Median : 0.00 Median :0.0800 Median :0.050
## Mean : 32.88 Mean :12.86 Mean :0.1663 Mean :0.119
## 3rd Qu.: 49.00 3rd Qu.:21.00 3rd Qu.:0.0800 3rd Qu.:0.060
## Max. :280.00 Max. :74.00 Max. :3.8800 Max. :3.440
## S3_Sound S4_Sound S5_CO2 S5_CO2_Slope
## Min. :0.0400 Min. :0.0500 Min. : 345.0 Min. :-6.288462
## 1st Qu.:0.0600 1st Qu.:0.0600 1st Qu.: 355.0 1st Qu.:-0.042308
## Median :0.0600 Median :0.0800 Median : 360.0 Median : 0.000000
## Mean :0.1609 Mean :0.1039 Mean : 457.4 Mean :-0.005393
## 3rd Qu.:0.0700 3rd Qu.:0.1000 3rd Qu.: 445.0 3rd Qu.: 0.000000
## Max. :3.6700 Max. :3.4000 Max. :1270.0 Max. : 8.980769
## S6_PIR S7_PIR Room_Occupancy_Count
## Min. :0.00000 Min. :0.00000 Min. :0.0000
## 1st Qu.:0.00000 1st Qu.:0.00000 1st Qu.:0.0000
## Median :0.00000 Median :0.00000 Median :0.0000
## Mean :0.08491 Mean :0.07741 Mean :0.3809
## 3rd Qu.:0.00000 3rd Qu.:0.00000 3rd Qu.:0.0000
## Max. :1.00000 Max. :1.00000 Max. :3.0000
## Anomalies in S6_PIR and S7_PIR:
## S6_PIR S7_PIR Count
## 1 0 0 4477
## 2 1 0 195
## 3 0 1 157
## 4 1 1 235
## Monte Carlo Simulation for S1_Temp Mean:
## $breaks
## [1] 25.430 25.435 25.440 25.445 25.450 25.455 25.460 25.465 25.470
##
## $counts
## [1] 12 105 307 363 169 40 3 1
##
## $density
## [1] 2.4 21.0 61.4 72.6 33.8 8.0 0.6 0.2
##
## $mids
## [1] 25.4325 25.4375 25.4425 25.4475 25.4525 25.4575 25.4625 25.4675
##
## $xname
## [1] "simulated_means"
##
## $equidist
## [1] TRUE
##
## attr(,"class")
## [1] "histogram"
## Analysis for Subsample 3
## Date Time S1_Temp S2_Temp
## Length:5064 Length:5064 Min. :24.94 Min. :24.75
## Class :character Class :character 1st Qu.:25.19 1st Qu.:25.19
## Mode :character Mode :character Median :25.38 Median :25.38
## Mean :25.46 Mean :25.54
## 3rd Qu.:25.63 3rd Qu.:25.69
## Max. :26.38 Max. :28.94
## S3_Temp S4_Temp S1_Light S2_Light
## Min. :24.44 Min. :24.94 Min. : 0.00 Min. : 0.00
## 1st Qu.:24.69 1st Qu.:25.44 1st Qu.: 0.00 1st Qu.: 0.00
## Median :24.94 Median :25.75 Median : 0.00 Median : 0.00
## Mean :25.06 Mean :25.75 Mean : 25.44 Mean : 25.54
## 3rd Qu.:25.38 3rd Qu.:26.00 3rd Qu.: 12.00 3rd Qu.: 14.00
## Max. :26.13 Max. :26.50 Max. :165.00 Max. :258.00
## S3_Light S4_Light S1_Sound S2_Sound
## Min. : 0.00 Min. : 0.0 Min. :0.0600 Min. :0.040
## 1st Qu.: 0.00 1st Qu.: 0.0 1st Qu.:0.0700 1st Qu.:0.050
## Median : 0.00 Median : 0.0 Median :0.0800 Median :0.050
## Mean : 34.15 Mean :12.8 Mean :0.1635 Mean :0.121
## 3rd Qu.: 49.00 3rd Qu.:21.0 3rd Qu.:0.0800 3rd Qu.:0.060
## Max. :280.00 Max. :74.0 Max. :3.8400 Max. :3.440
## S3_Sound S4_Sound S5_CO2 S5_CO2_Slope
## Min. :0.0500 Min. :0.0500 Min. : 345.0 Min. :-6.288462
## 1st Qu.:0.0600 1st Qu.:0.0600 1st Qu.: 355.0 1st Qu.:-0.046154
## Median :0.0600 Median :0.0800 Median : 360.0 Median : 0.000000
## Mean :0.1628 Mean :0.1034 Mean : 462.3 Mean :-0.009192
## 3rd Qu.:0.0700 3rd Qu.:0.1000 3rd Qu.: 475.0 3rd Qu.: 0.000000
## Max. :3.6600 Max. :3.4000 Max. :1270.0 Max. : 8.838462
## S6_PIR S7_PIR Room_Occupancy_Count
## Min. :0.00000 Min. :0.00000 Min. :0.000
## 1st Qu.:0.00000 1st Qu.:0.00000 1st Qu.:0.000
## Median :0.00000 Median :0.00000 Median :0.000
## Mean :0.08452 Mean :0.07682 Mean :0.394
## 3rd Qu.:0.00000 3rd Qu.:0.00000 3rd Qu.:0.000
## Max. :1.00000 Max. :1.00000 Max. :3.000
## Anomalies in S6_PIR and S7_PIR:
## S6_PIR S7_PIR Count
## 1 0 0 4493
## 2 1 0 182
## 3 0 1 143
## 4 1 1 246
## Monte Carlo Simulation for S1_Temp Mean:
## $breaks
## [1] 25.442 25.444 25.446 25.448 25.450 25.452 25.454 25.456 25.458 25.460
## [11] 25.462 25.464 25.466 25.468 25.470 25.472 25.474
##
## $counts
## [1] 1 10 28 57 94 107 178 152 125 111 82 34 12 4 2 3
##
## $density
## [1] 0.5 5.0 14.0 28.5 47.0 53.5 89.0 76.0 62.5 55.5 41.0 17.0 6.0 2.0 1.0
## [16] 1.5
##
## $mids
## [1] 25.443 25.445 25.447 25.449 25.451 25.453 25.455 25.457 25.459 25.461
## [11] 25.463 25.465 25.467 25.469 25.471 25.473
##
## $xname
## [1] "simulated_means"
##
## $equidist
## [1] TRUE
##
## attr(,"class")
## [1] "histogram"
## Analysis for Subsample 4
## Date Time S1_Temp S2_Temp
## Length:5064 Length:5064 Min. :24.94 Min. :24.75
## Class :character Class :character 1st Qu.:25.19 1st Qu.:25.19
## Mode :character Mode :character Median :25.38 Median :25.38
## Mean :25.44 Mean :25.53
## 3rd Qu.:25.56 3rd Qu.:25.63
## Max. :26.38 Max. :28.94
## S3_Temp S4_Temp S1_Light S2_Light
## Min. :24.44 Min. :24.94 Min. : 0.00 Min. : 0.00
## 1st Qu.:24.69 1st Qu.:25.44 1st Qu.: 0.00 1st Qu.: 0.00
## Median :24.94 Median :25.75 Median : 0.00 Median : 0.00
## Mean :25.05 Mean :25.74 Mean : 24.13 Mean : 24.98
## 3rd Qu.:25.31 3rd Qu.:26.00 3rd Qu.: 11.00 3rd Qu.: 12.00
## Max. :26.13 Max. :26.50 Max. :165.00 Max. :257.00
## S3_Light S4_Light S1_Sound S2_Sound
## Min. : 0.00 Min. : 0.00 Min. :0.0600 Min. :0.0400
## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.:0.0700 1st Qu.:0.0500
## Median : 0.00 Median : 0.00 Median :0.0800 Median :0.0500
## Mean : 32.78 Mean :13.04 Mean :0.1667 Mean :0.1158
## 3rd Qu.: 48.00 3rd Qu.:21.00 3rd Qu.:0.0800 3rd Qu.:0.0600
## Max. :280.00 Max. :74.00 Max. :3.8400 Max. :3.4400
## S3_Sound S4_Sound S5_CO2 S5_CO2_Slope
## Min. :0.0400 Min. :0.0500 Min. : 345.0 Min. :-6.296154
## 1st Qu.:0.0600 1st Qu.:0.0600 1st Qu.: 355.0 1st Qu.:-0.042308
## Median :0.0600 Median :0.0800 Median : 360.0 Median : 0.000000
## Mean :0.1492 Mean :0.1007 Mean : 455.1 Mean : 0.004828
## 3rd Qu.:0.0700 3rd Qu.:0.1000 3rd Qu.: 450.0 3rd Qu.: 0.000000
## Max. :3.6600 Max. :1.5400 Max. :1265.0 Max. : 8.838462
## S6_PIR S7_PIR Room_Occupancy_Count
## Min. :0.00000 Min. :0.00000 Min. :0.0000
## 1st Qu.:0.00000 1st Qu.:0.00000 1st Qu.:0.0000
## Median :0.00000 Median :0.00000 Median :0.0000
## Mean :0.08946 Mean :0.07938 Mean :0.3839
## 3rd Qu.:0.00000 3rd Qu.:0.00000 3rd Qu.:0.0000
## Max. :1.00000 Max. :1.00000 Max. :3.0000
## Anomalies in S6_PIR and S7_PIR:
## S6_PIR S7_PIR Count
## 1 0 0 4466
## 2 1 0 196
## 3 0 1 145
## 4 1 1 257
## Monte Carlo Simulation for S1_Temp Mean:
## $breaks
## [1] 25.426 25.428 25.430 25.432 25.434 25.436 25.438 25.440 25.442 25.444
## [11] 25.446 25.448 25.450 25.452 25.454 25.456 25.458
##
## $counts
## [1] 1 4 3 10 47 78 111 142 158 166 114 68 58 27 9 4
##
## $density
## [1] 0.5 2.0 1.5 5.0 23.5 39.0 55.5 71.0 79.0 83.0 57.0 34.0 29.0 13.5 4.5
## [16] 2.0
##
## $mids
## [1] 25.427 25.429 25.431 25.433 25.435 25.437 25.439 25.441 25.443 25.445
## [11] 25.447 25.449 25.451 25.453 25.455 25.457
##
## $xname
## [1] "simulated_means"
##
## $equidist
## [1] TRUE
##
## attr(,"class")
## [1] "histogram"
## Analysis for Subsample 5
## Date Time S1_Temp S2_Temp
## Length:5064 Length:5064 Min. :24.94 Min. :24.75
## Class :character Class :character 1st Qu.:25.19 1st Qu.:25.19
## Mode :character Mode :character Median :25.38 Median :25.38
## Mean :25.45 Mean :25.54
## 3rd Qu.:25.63 3rd Qu.:25.63
## Max. :26.38 Max. :28.94
## S3_Temp S4_Temp S1_Light S2_Light
## Min. :24.44 Min. :25.00 Min. : 0.00 Min. : 0.00
## 1st Qu.:24.69 1st Qu.:25.44 1st Qu.: 0.00 1st Qu.: 0.00
## Median :24.94 Median :25.75 Median : 0.00 Median : 0.00
## Mean :25.05 Mean :25.75 Mean : 25.26 Mean : 25.83
## 3rd Qu.:25.38 3rd Qu.:26.00 3rd Qu.: 11.00 3rd Qu.: 12.00
## Max. :26.13 Max. :26.50 Max. :165.00 Max. :257.00
## S3_Light S4_Light S1_Sound S2_Sound
## Min. : 0.00 Min. : 0.00 Min. :0.0600 Min. :0.0400
## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.:0.0700 1st Qu.:0.0500
## Median : 0.00 Median : 0.00 Median :0.0800 Median :0.0500
## Mean : 33.68 Mean :12.62 Mean :0.1672 Mean :0.1194
## 3rd Qu.: 49.00 3rd Qu.:21.00 3rd Qu.:0.0800 3rd Qu.:0.0600
## Max. :280.00 Max. :74.00 Max. :3.8800 Max. :3.4400
## S3_Sound S4_Sound S5_CO2 S5_CO2_Slope
## Min. :0.0400 Min. :0.0500 Min. : 345.0 Min. :-6.296154
## 1st Qu.:0.0600 1st Qu.:0.0600 1st Qu.: 355.0 1st Qu.:-0.046154
## Median :0.0600 Median :0.0800 Median : 360.0 Median : 0.000000
## Mean :0.1547 Mean :0.1061 Mean : 460.1 Mean : 0.003468
## 3rd Qu.:0.0700 3rd Qu.:0.1000 3rd Qu.: 465.0 3rd Qu.: 0.000000
## Max. :3.6700 Max. :3.4000 Max. :1265.0 Max. : 8.946154
## S6_PIR S7_PIR Room_Occupancy_Count
## Min. :0.00000 Min. :0.00000 Min. :0.0000
## 1st Qu.:0.00000 1st Qu.:0.00000 1st Qu.:0.0000
## Median :0.00000 Median :0.00000 Median :0.0000
## Mean :0.08333 Mean :0.07563 Mean :0.3944
## 3rd Qu.:0.00000 3rd Qu.:0.00000 3rd Qu.:0.0000
## Max. :1.00000 Max. :1.00000 Max. :3.0000
## Anomalies in S6_PIR and S7_PIR:
## S6_PIR S7_PIR Count
## 1 0 0 4487
## 2 1 0 194
## 3 0 1 155
## 4 1 1 228
## Monte Carlo Simulation for S1_Temp Mean:
## $breaks
## [1] 25.436 25.438 25.440 25.442 25.444 25.446 25.448 25.450 25.452 25.454
## [11] 25.456 25.458 25.460 25.462 25.464 25.466 25.468
##
## $counts
## [1] 1 5 10 29 53 90 120 170 160 133 103 62 38 23 2 1
##
## $density
## [1] 0.5 2.5 5.0 14.5 26.5 45.0 60.0 85.0 80.0 66.5 51.5 31.0 19.0 11.5 1.0
## [16] 0.5
##
## $mids
## [1] 25.437 25.439 25.441 25.443 25.445 25.447 25.449 25.451 25.453 25.455
## [11] 25.457 25.459 25.461 25.463 25.465 25.467
##
## $xname
## [1] "simulated_means"
##
## $equidist
## [1] TRUE
##
## attr(,"class")
## [1] "histogram"Inferences:
Subsample 1 (S1_Temp):
Central Tendency: By examining the Monte Carlo simulation, we can identify where the majority of the data points cluster, providing insights into the average temperature that is most frequently observed.
Variability: By looking at how spread out the data is, we can see if temperatures in Subsample 1 tend to vary a lot.
Likelihood of Extreme Temperatures: Peaks at the ends of the graph show how often really high or low temperatures might occur just by chance.
Subsample 2 (S1_Temp):
Comparison with S1: Both subsample 1 and subsample 2 seem to have a central tendency and similar spread of data by looking at the histograms.
Identifying Patterns or Anomalies: While comparing S2 with S1 we can see that there seem to be fewer data points at the right end of the distribution which could be mistook for outliers when only the sample is considered
Subsample 3 (S1_Temp):
Assessment of Outliers: With The Monte Carlo simulation we can see that S3 has a rich distribution spread centrally across many data points. This shows a basic normal distribution
Detecting Non-Random Factors: No Significant deviations of the observed mean temperature in Subsample 3 which indicates that this subsample although random still holds good in terms of
Subsample 4 (S1_Temp):
Central Tendency: The Monte Carlo simulation reveals the central tendency of S4_Temp, indicating the most likely range of mean temperatures that could occur by chance.
Variability: Compared to other samples S4 has a bigger distribution indicating that Variance in this subsample might be greater compared to other samples, which could mean that this distribution might hold few outliers when analysis is done using the whole data.
Subsample 5 (S1_Temp):
- Comparison with Other Subsamples: Comparing with other samples S5 seems to be in line with other samples except for S4 which has a lower S1_temp value.
From the monte-carlo simulation and the graphs we have made the above inferences.
From the above samples we can see that there are no major outlier scares in any of the samples except S4 which although is a cause of concern however can only be judged when it’s analysed using the complete data.
The data for all the samples seems to have a major Central Tendency which indicates that the data has been sampled in a proper way without any major issues.