setwd("C:/_MyData_/IIMK/Assignment 1")
library (readxl)
library (dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
agriData_org <- read_excel ("IMB733-XLS-ENG Spreadsheet 3.xlsx", sheet = "Data Sheet")
agriData <- agriData_org
str (agriData)
## tibble [123 x 26] (S3: tbl_df/tbl/data.frame)
## $ Month-Year : POSIXct[1:123], format: "2015-06-01" "2015-07-01" ...
## $ Week : chr [1:123] "Week4" "Week1" "Week2" "Week3" ...
## $ No of users : num [1:123] 2 1 1 4 6 12 13 10 7 12 ...
## $ Usage : num [1:123] 4 1 25 70 100 291 225 141 148 215 ...
## $ D1 : num [1:123] 0 0 0 4 1 12 7 4 1 5 ...
## $ D2 : num [1:123] 0 0 1 2 1 6 5 4 0 3 ...
## $ D3 : num [1:123] 1 0 2 3 0 11 6 8 1 6 ...
## $ D4 : num [1:123] 0 0 2 4 2 4 2 4 5 3 ...
## $ D5 : num [1:123] 0 0 0 2 0 5 5 3 4 6 ...
## $ D6 : num [1:123] 0 0 0 4 2 15 6 5 5 12 ...
## $ D7 : num [1:123] 0 0 2 1 7 7 4 8 3 7 ...
## $ D8 : num [1:123] 0 0 3 7 9 7 5 7 3 33 ...
## $ D9 : num [1:123] 0 0 2 3 2 6 6 6 3 11 ...
## $ D10 : num [1:123] 0 0 1 0 1 10 1 4 2 3 ...
## $ D11 : num [1:123] 0 0 1 3 4 12 6 3 5 8 ...
## $ V1 : num [1:123] 0 0 0 5 11 26 28 18 18 20 ...
## $ V2 : num [1:123] 0 1 0 4 8 20 19 11 16 15 ...
## $ V3 : num [1:123] 0 0 1 2 5 12 13 8 7 10 ...
## $ V4 : num [1:123] 0 0 1 2 5 13 8 7 6 6 ...
## $ V5 : num [1:123] 2 0 1 1 9 16 9 4 15 6 ...
## $ V6 : num [1:123] 0 0 1 3 3 22 14 4 10 10 ...
## $ V7 : num [1:123] 0 0 0 3 7 21 13 5 4 9 ...
## $ V8 : num [1:123] 0 0 0 2 6 14 9 5 10 7 ...
## $ V9 : num [1:123] 0 0 0 4 7 16 20 10 9 8 ...
## $ V10 : num [1:123] 0 0 1 4 7 23 17 5 14 10 ...
## $ Micronutrient: num [1:123] 1 0 6 7 3 13 22 8 7 17 ...
as.Date (agriData$`Month-Year`, "%Y-%m-%d")
## Warning in as.POSIXlt.POSIXct(x, tz = tz): unknown timezone '%Y-%m-%d'
## [1] "2015-06-01" "2015-07-01" "2015-07-01" "2015-07-01" "2015-07-01"
## [6] "2015-08-01" "2015-08-01" "2015-08-01" "2015-08-01" "2015-09-01"
## [11] "2015-09-01" "2015-09-01" "2015-09-01" "2015-10-01" "2015-10-01"
## [16] "2015-10-01" "2015-10-01" "2015-11-01" "2015-11-01" "2015-11-01"
## [21] "2015-11-01" "2015-12-01" "2015-12-01" "2015-12-01" "2015-12-01"
## [26] "2016-01-01" "2016-01-01" "2016-01-01" "2016-01-01" "2016-02-01"
## [31] "2016-02-01" "2016-02-01" "2016-02-01" "2016-03-01" "2016-03-01"
## [36] "2016-03-01" "2016-03-01" "2016-04-01" "2016-04-01" "2016-04-01"
## [41] "2016-04-01" "2016-05-01" "2016-05-01" "2016-05-01" "2016-05-01"
## [46] "2016-06-01" "2016-06-01" "2016-06-01" "2016-06-01" "2016-07-01"
## [51] "2016-07-01" "2016-07-01" "2016-07-01" "2016-08-01" "2016-08-01"
## [56] "2016-08-01" "2016-08-01" "2016-09-01" "2016-09-01" "2016-09-01"
## [61] "2016-09-01" "2016-10-01" "2016-10-01" "2016-10-01" "2016-10-01"
## [66] "2016-11-01" "2016-11-01" "2016-11-01" "2016-11-01" "2016-12-01"
## [71] "2016-12-01" "2016-12-01" "2016-12-01" "2017-01-01" "2017-01-01"
## [76] "2017-01-01" "2017-01-01" "2017-02-01" "2017-02-01" "2017-02-01"
## [81] "2017-02-01" "2017-03-01" "2017-03-01" "2017-03-01" "2017-03-01"
## [86] "2017-04-01" "2017-04-01" "2017-04-01" "2017-04-01" "2017-05-01"
## [91] "2017-05-01" "2017-05-01" "2017-05-01" "2017-09-01" "2017-10-01"
## [96] "2017-10-01" "2017-10-01" "2017-10-01" "2017-11-01" "2017-11-01"
## [101] "2017-11-01" "2017-11-01" "2017-12-01" "2017-12-01" "2017-12-01"
## [106] "2017-12-01" "2018-01-01" "2018-01-01" "2018-01-01" "2018-01-01"
## [111] "2018-02-01" "2018-02-01" "2018-02-01" "2018-02-01" "2018-03-01"
## [116] "2018-03-01" "2018-03-01" "2018-03-01" "2018-04-01" "2018-04-01"
## [121] "2018-04-01" "2018-04-01" "2018-05-01"
case1Data <- subset (agriData, agriData$`Month-Year` >= "2017-10-01")
case1Test <- t.test (case1Data$D6, mu = 60, alernative = "greater")
case1Test
##
## One Sample t-test
##
## data: case1Data$D6
## t = 2.341, df = 28, p-value = 0.02658
## alternative hypothesis: true mean is not equal to 60
## 95 percent confidence interval:
## 61.05162 75.77597
## sample estimates:
## mean of x
## 68.41379
d6Proportion <- sum(agriData$D6) / sum(agriData$Usage)
se <- sqrt((0.15 * (1 - 0.15)) / 123) # We have 123 observations
z_stat_d6 <- (d6Proportion - 0.15) / se
d6pValue <- 1 - pnorm (z_stat_d6)
d6pValue
## [1] 0.9974213
agriData2015_16 <- subset (agriData, agriData$`Month-Year` >= "2015-01-01" & agriData$`Month-Year` <= "2016-12-31")
agriData2015_16$yearGroup <- "2015-16"
agriData2017_18 <- subset (agriData, agriData$`Month-Year` >= "2017-01-01" & agriData$`Month-Year` <= "2018-12-31")
agriData2017_18$yearGroup <- "2017-18"
agriDataByYearGroup <- rbind (agriData2015_16, agriData2017_18)
case3Test <- t.test (agriDataByYearGroup$`No of users` ~ agriDataByYearGroup$yearGroup, alternative = "greater", var.equal = TRUE)
case3Test
##
## Two Sample t-test
##
## data: agriDataByYearGroup$`No of users` by agriDataByYearGroup$yearGroup
## t = -9.2567, df = 121, p-value = 1
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -154.4945 Inf
## sample estimates:
## mean in group 2015-16 mean in group 2017-18
## 50.06849 181.10000
u1 = Average usage in 1st week of every month
u2 = Average usage in 2nd week of every month
u3 = Average usage in 3rd week of every month
u4 = Average usage in 4th week of every month
H0: u1 = u2 = u3 = u4
Ha: Not all u are equal
case4aData <- data.frame(Usage = agriData$Usage, Week = agriData$Week)
case4aData$Week <- factor (case4aData$Week)
agriAnova <- aov(Usage~Week, data = case4aData)
summary (agriAnova)
## Df Sum Sq Mean Sq F value Pr(>F)
## Week 3 1515178 505059 2.22 0.0894 .
## Residuals 119 27074553 227517
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
model.tables (agriAnova, type = "means")
## Tables of means
## Grand mean
##
## 582.4959
##
## Week
## Week1 Week2 Week3 Week4
## 551.9 522.2 480 764.7
## rep 31.0 30.0 30 32.0
agriDataTillDec2015 <- subset (agriData, agriData$`Month-Year` <= "2015-12-31")
agriDataTillDec2015$YearGroup <- "Till_2015"
agriDataFromJan2016 <- subset (agriData, agriData$`Month-Year` >= "2016-01-01")
agriDataFromJan2016$YearGroup <- "From_2016"
case4bData <- rbind(agriDataTillDec2015, agriDataFromJan2016)
case4Test <- t.test (case4bData$Usage ~ case4bData$YearGroup, alternative = "less", var.equal = TRUE)
case4Test
##
## Two Sample t-test
##
## data: case4bData$Usage by case4bData$YearGroup
## t = 3.5721, df = 121, p-value = 0.9997
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf 541.7268
## sample estimates:
## mean in group From_2016 mean in group Till_2015
## 657.7041 287.6800
case5Data <- subset (agriData, agriData$`Month-Year` >= "2016-05-01") # We have data till May 2018. So select data from May 2016
groupByMonthCase5 <- group_by (case5Data, `Month-Year`)
case5Summary <- summarise(groupByMonthCase5, Users = sum(`No of users`), Usage = sum(Usage))
## `summarise()` ungrouping output (override with `.groups` argument)
cor.test (case5Summary$Users, case5Summary$Usage)
##
## Pearson's product-moment correlation
##
## data: case5Summary$Users and case5Summary$Usage
## t = 9.1887, df = 20, p-value = 1.287e-08
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.7691185 0.9577074
## sample estimates:
## cor
## 0.8991594
case6Data <- subset (agriData, agriData$`Month-Year` >= "2016-09-01")
groupByMonthCase6 <- group_by (case6Data, `Month-Year`)
case6Summary <- summarise (groupByMonthCase6, Usage = mean(Usage))
## `summarise()` ungrouping output (override with `.groups` argument)
case6Summary
## # A tibble: 18 x 2
## `Month-Year` Usage
## <dttm> <dbl>
## 1 2016-09-01 00:00:00 396.
## 2 2016-10-01 00:00:00 1215
## 3 2016-11-01 00:00:00 751
## 4 2016-12-01 00:00:00 496.
## 5 2017-01-01 00:00:00 442.
## 6 2017-02-01 00:00:00 429.
## 7 2017-03-01 00:00:00 681.
## 8 2017-04-01 00:00:00 356.
## 9 2017-05-01 00:00:00 203
## 10 2017-09-01 00:00:00 1923
## 11 2017-10-01 00:00:00 1398.
## 12 2017-11-01 00:00:00 1300.
## 13 2017-12-01 00:00:00 1446.
## 14 2018-01-01 00:00:00 1123.
## 15 2018-02-01 00:00:00 718
## 16 2018-03-01 00:00:00 865.
## 17 2018-04-01 00:00:00 623.
## 18 2018-05-01 00:00:00 380
plot (case6Summary$`Month-Year`, case6Summary$Usage, type="o", col = "red", xlab = "Year", ylab = "Average Usage",
main = "Line Graph for Average Usage by Month")
H0: A disease information is accessed more even when the weather condition is unfavorable to that disease
Ha: A disease information is accessed more when the weather condition is favorable to that disease
Weather condition is determined based on temperature and humidity
u1 = Mean access of the disease when the weather condition is favorable to that disease
u2 = Mean access of the disease when the weather condition is unfavorable to that disease
H0: u1 <= u2
Ha: u1 > u2
belagaviAgriData <- read_excel ("IMB733-XLS-ENG Spreadsheet 3.xlsx", sheet = "Belagavi_weather")
dharwadAgriData <- read_excel ("IMB733-XLS-ENG Spreadsheet 3.xlsx", sheet = "Dharwad_weather")
bel_d1FavorableData <- subset (belagaviAgriData, belagaviAgriData$Temperature >= 20 & belagaviAgriData$Temperature <= 24 & belagaviAgriData$`Relative Humidity` > 80)
bel_d1FavorableData$D1Favorable <- "Yes"
bel_d1UnfavorableData <- subset (belagaviAgriData, !(belagaviAgriData$Temperature >= 20 & belagaviAgriData$Temperature <= 24 & belagaviAgriData$`Relative Humidity` > 80))
bel_d1UnfavorableData$D1Favorable <- "No"
belagaviD1Data <- rbind (bel_d1FavorableData, bel_d1UnfavorableData)
belagaviD1Data <- arrange (belagaviD1Data, belagaviD1Data$Months)
belagaviD1Test <- t.test (D1 ~ D1Favorable, data = belagaviD1Data, alternative = "greater", var.equal = TRUE)
dhar_d1FavorableData <- subset (dharwadAgriData, dharwadAgriData$Temperature >= 20 & dharwadAgriData$Temperature <= 24 & dharwadAgriData$`Relative Humidity` > 80)
dhar_d1FavorableData$D1Favorable <- "Yes"
dhar_d1UnfavorableData <- subset (dharwadAgriData, !(dharwadAgriData$Temperature >= 20 & dharwadAgriData$Temperature <= 24 & dharwadAgriData$`Relative Humidity` > 80))
dhar_d1UnfavorableData$D1Favorable <- "No"
dharwadD1Data <- rbind (dhar_d1FavorableData, dhar_d1UnfavorableData)
dharwadD1Data <- arrange (dharwadD1Data, dharwadD1Data$Months)
dharwadD1Test <- t.test (D1 ~ D1Favorable, data = dharwadD1Data, alternative = "greater", var.equal = TRUE)
belagaviD1Test
##
## Two Sample t-test
##
## data: D1 by D1Favorable
## t = -2.7605, df = 22, p-value = 0.9943
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -41.64827 Inf
## sample estimates:
## mean in group No mean in group Yes
## 11.91669 37.59305
dharwadD1Test
##
## Two Sample t-test
##
## data: D1 by D1Favorable
## t = -4.5934, df = 20, p-value = 0.9999
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -34.49083 Inf
## sample estimates:
## mean in group No mean in group Yes
## 6.515126 31.590651
bel_d2FavorableData <- subset (belagaviAgriData, belagaviAgriData$Temperature >= 21.5 & belagaviAgriData$Temperature <= 24.5 & belagaviAgriData$`Relative Humidity` > 83)
bel_d2FavorableData$D2Favorable <- "Yes"
bel_d2UnfavorableData <- subset (belagaviAgriData, !(belagaviAgriData$Temperature >= 21.5 & belagaviAgriData$Temperature <= 24.5 & belagaviAgriData$`Relative Humidity` > 83))
bel_d2UnfavorableData$D2Favorable <- "No"
belagaviD2Data <- rbind (bel_d2FavorableData, bel_d2UnfavorableData)
belagaviD2Data <- arrange (belagaviD2Data, belagaviD2Data$Months)
belagaviD2Test <- t.test (D2 ~ D2Favorable, data = belagaviD2Data, alternative = "greater", var.equal = TRUE)
dhar_d2FavorableData <- subset (dharwadAgriData, dharwadAgriData$Temperature >= 21.5 & dharwadAgriData$Temperature <= 24.5 & dharwadAgriData$`Relative Humidity` > 83)
dhar_d2FavorableData$D2Favorable <- "Yes"
dhar_d2UnfavorableData <- subset (dharwadAgriData, !(dharwadAgriData$Temperature >= 21.5 & dharwadAgriData$Temperature <= 24.5 & dharwadAgriData$`Relative Humidity` > 83))
dhar_d2UnfavorableData$D2Favorable <- "No"
dharwadD2Data <- rbind (dhar_d2FavorableData, dhar_d2UnfavorableData)
dharwadD2Data <- arrange (dharwadD2Data, dharwadD2Data$Months)
dharwadD2Test <- t.test (D2 ~ D2Favorable, data = dharwadD2Data, alternative = "greater", var.equal = TRUE)
belagaviD2Test
##
## Two Sample t-test
##
## data: D2 by D2Favorable
## t = -3.7247, df = 22, p-value = 0.9994
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -29.52222 Inf
## sample estimates:
## mean in group No mean in group Yes
## 9.173547 29.380223
dharwadD2Test
##
## Two Sample t-test
##
## data: D2 by D2Favorable
## t = -4.0726, df = 20, p-value = 0.9997
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -48.45349 Inf
## sample estimates:
## mean in group No mean in group Yes
## 6.096486 40.134921
bel_d3FavorableData <- subset (belagaviAgriData, belagaviAgriData$Temperature >= 22 & belagaviAgriData$Temperature <= 24)
bel_d3FavorableData$D3Favorable <- "Yes"
bel_d3UnfavorableData <- subset (belagaviAgriData, !(belagaviAgriData$Temperature >= 22 & belagaviAgriData$Temperature <= 24))
bel_d3UnfavorableData$D3Favorable <- "No"
belagaviD3Data <- rbind (bel_d3FavorableData, bel_d3UnfavorableData)
belagaviD3Data <- arrange (belagaviD3Data, belagaviD3Data$Months)
belagaviD3Test <- t.test (D3 ~ D3Favorable, data = belagaviD3Data, alternative = "greater", var.equal = TRUE)
dhar_d3FavorableData <- subset (dharwadAgriData, dharwadAgriData$Temperature >= 22 & dharwadAgriData$Temperature <= 24)
dhar_d3FavorableData$D3Favorable <- "Yes"
dhar_d3UnfavorableData <- subset (dharwadAgriData, !(dharwadAgriData$Temperature >= 22 & dharwadAgriData$Temperature <= 24))
dhar_d3UnfavorableData$D3Favorable <- "No"
dharwadD3Data <- rbind (dhar_d3FavorableData, dhar_d3UnfavorableData)
dharwadD3Data <- arrange (dharwadD3Data, dharwadD3Data$Months)
dharwadD3Test <- t.test (D3 ~ D3Favorable, data = dharwadD3Data, alternative = "greater", var.equal = TRUE)
belagaviD3Test
##
## Two Sample t-test
##
## data: D3 by D3Favorable
## t = -2.2224, df = 22, p-value = 0.9816
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -34.29296 Inf
## sample estimates:
## mean in group No mean in group Yes
## 11.61233 30.95773
dharwadD3Test
##
## Two Sample t-test
##
## data: D3 by D3Favorable
## t = -1.5057, df = 20, p-value = 0.9261
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -60.73424 Inf
## sample estimates:
## mean in group No mean in group Yes
## 11.96166 40.26971
bel_d4FavorableData <- subset (belagaviAgriData, belagaviAgriData$Temperature >= 22 & belagaviAgriData$Temperature <= 26 & belagaviAgriData$`Relative Humidity` > 85)
bel_d4FavorableData$D4Favorable <- "Yes"
bel_d4UnfavorableData <- subset (belagaviAgriData, !(belagaviAgriData$Temperature >= 22 & belagaviAgriData$Temperature <= 26 & belagaviAgriData$`Relative Humidity` > 85))
bel_d4UnfavorableData$D4Favorable <- "No"
belagaviD4Data <- rbind (bel_d4FavorableData, bel_d4UnfavorableData)
belagaviD4Data <- arrange (belagaviD4Data, belagaviD4Data$Months)
belagaviD4Test <- t.test (D4 ~ D4Favorable, data = belagaviD4Data, alternative = "greater", var.equal = TRUE)
dhar_d4FavorableData <- subset (dharwadAgriData, dharwadAgriData$Temperature >= 22 & dharwadAgriData$Temperature <= 26 & dharwadAgriData$`Relative Humidity` > 85)
dhar_d4FavorableData$D4Favorable <- "Yes"
dhar_d4UnfavorableData <- subset (dharwadAgriData, !(dharwadAgriData$Temperature >= 22 & dharwadAgriData$Temperature <= 26 & dharwadAgriData$`Relative Humidity` > 85))
dhar_d4UnfavorableData$D4Favorable <- "No"
dharwadD4Data <- rbind (dhar_d4FavorableData, dhar_d4UnfavorableData)
dharwadD4Data <- arrange (dharwadD4Data, dharwadD4Data$Months)
dharwadD4Test <- t.test (D4 ~ D4Favorable, data = dharwadD4Data, alternative = "greater", var.equal = TRUE)
belagaviD4Test
##
## Two Sample t-test
##
## data: D4 by D4Favorable
## t = -1.793, df = 22, p-value = 0.9566
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -22.15349 Inf
## sample estimates:
## mean in group No mean in group Yes
## 12.97384 24.28984
dharwadD4Test
##
## Two Sample t-test
##
## data: D4 by D4Favorable
## t = -2.3147, df = 20, p-value = 0.9843
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -47.21957 Inf
## sample estimates:
## mean in group No mean in group Yes
## 12.10875 39.16667
bel_d5FavorableData <- subset (belagaviAgriData, belagaviAgriData$Temperature >= 22 & belagaviAgriData$Temperature <= 24.5 & belagaviAgriData$`Relative Humidity` >= 77 & belagaviAgriData$`Relative Humidity` <= 85)
bel_d5FavorableData$D5Favorable <- "Yes"
bel_d5UnfavorableData <- subset (belagaviAgriData, !(belagaviAgriData$Temperature >= 22 & belagaviAgriData$Temperature <= 24.5 & belagaviAgriData$`Relative Humidity` >= 77 & belagaviAgriData$`Relative Humidity` <= 85))
bel_d5UnfavorableData$D5Favorable <- "No"
belagaviD5Data <- rbind (bel_d5FavorableData, bel_d5UnfavorableData)
belagaviD5Data <- arrange (belagaviD5Data, belagaviD5Data$Months)
belagaviD5Test <- t.test (D5 ~ D5Favorable, data = belagaviD5Data, alternative = "greater", var.equal = TRUE)
dhar_d5FavorableData <- subset (dharwadAgriData, dharwadAgriData$Temperature >= 22 & dharwadAgriData$Temperature <= 24.5 & dharwadAgriData$`Relative Humidity` >= 77 & dharwadAgriData$`Relative Humidity` <= 85)
dhar_d5FavorableData$D5Favorable <- "Yes"
dhar_d5UnfavorableData <- subset (dharwadAgriData, !(dharwadAgriData$Temperature >= 22 & dharwadAgriData$Temperature <= 24.5 & dharwadAgriData$`Relative Humidity` >= 77 & dharwadAgriData$`Relative Humidity` <= 85))
dhar_d5UnfavorableData$D5Favorable <- "No"
dharwadD5Data <- rbind (dhar_d5FavorableData, dhar_d5UnfavorableData)
dharwadD5Data <- arrange (dharwadD5Data, dharwadD5Data$Months)
dharwadD5Test <- t.test (D5 ~ D5Favorable, data = dharwadD5Data, alternative = "greater", var.equal = TRUE)
belagaviD5Test
##
## Two Sample t-test
##
## data: D5 by D5Favorable
## t = -3.6675, df = 22, p-value = 0.9993
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -38.2594 Inf
## sample estimates:
## mean in group No mean in group Yes
## 10.51547 36.57407
dharwadD5Test
##
## Two Sample t-test
##
## data: D5 by D5Favorable
## t = -0.10853, df = 20, p-value = 0.5427
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -18.75428 Inf
## sample estimates:
## mean in group No mean in group Yes
## 13.06725 14.17749
bel_d7FavorableData <- subset (belagaviAgriData, belagaviAgriData$Temperature > 25 & belagaviAgriData$`Relative Humidity` > 80)
bel_d7FavorableData$D7Favorable <- "Yes"
bel_d7UnfavorableData <- subset (belagaviAgriData, !(belagaviAgriData$Temperature > 25 & belagaviAgriData$`Relative Humidity` > 80))
bel_d7UnfavorableData$D7Favorable <- "No"
belagaviD7Data <- rbind (bel_d7FavorableData, bel_d7UnfavorableData)
belagaviD7Data <- arrange (belagaviD7Data, belagaviD7Data$Months)
belagaviD7Test <- t.test (D7 ~ D7Favorable, data = belagaviD7Data, alternative = "greater", var.equal = TRUE)
dhar_d7FavorableData <- subset (dharwadAgriData, dharwadAgriData$Temperature > 25 & dharwadAgriData$`Relative Humidity` > 80)
dhar_d7FavorableData$D7Favorable <- "Yes"
dhar_d7UnfavorableData <- subset (dharwadAgriData, !(dharwadAgriData$Temperature > 25 & dharwadAgriData$`Relative Humidity` > 80))
dhar_d7UnfavorableData$D7Favorable <- "No"
dharwadD7Data <- rbind (dhar_d7FavorableData, dhar_d7UnfavorableData)
dharwadD7Data <- arrange (dharwadD7Data, dharwadD7Data$Months)
dharwadD7Test <- t.test (D7 ~ D7Favorable, data = dharwadD7Data, alternative = "greater", var.equal = TRUE)
belagaviD7Test
##
## Two Sample t-test
##
## data: D7 by D7Favorable
## t = -3.4275, df = 22, p-value = 0.9988
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -77.17649 Inf
## sample estimates:
## mean in group No mean in group Yes
## 21.00642 72.42328
dharwadD7Test
##
## Two Sample t-test
##
## data: D7 by D7Favorable
## t = -0.72663, df = 20, p-value = 0.7621
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -50.91364 Inf
## sample estimates:
## mean in group No mean in group Yes
## 19.90822 35.00000