## [1] Table By Month of 2015 and 2016:
month_numbers month_names count_2015 count_2016
1 Jan 10 13
2 Feb 7 14
3 Mar 17 12
4 Apr 10 19
5 May 22 17
6 Jun 16 23
7 Jul 16 20
8 Aug 30 19
9 Sep 28 12
10 Oct 24 15
11 Nov 14 16
12 Dec 9 9 
## [1] Correlation between month of 2015 and 2016
## [1] 0.1713941

Result: the correlation between the variables is positive but quite low.

Plot for showing the correlation between 2015 and 2016:

## `geom_smooth()` using formula = 'y ~ x'

Checking assumptions for t-test:

Normality of the results: Shapiro-wilks test:

## [1] Shapiro Wilks test for 2015:
## 
##  Shapiro-Wilk normality test
## 
## data:  table_by_month$count_2015
## W = 0.933, p-value = 0.413
## [1] Shapiro Wilks test for 2016:
## 
##  Shapiro-Wilk normality test
## 
## data:  table_by_month$count_2016
## W = 0.98154, p-value = 0.9891

Results: for both 2015 and 2016 the results are non-significant.

That means that we proceed with the conclusion that the data is

normally distributed - so that means that independent-samples t-test

can be applied in that case.

Since the test is paired-samples t-test, we don’t need to check

differences between the variances, and so, we can proceed directly

to the relevatn statistical test- Paired samples t-test:

## 
##  Paired t-test
## 
## data:  table_by_month$count_2015 and table_by_month$count_2016
## t = 0.50674, df = 11, p-value = 0.6223
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -3.900623  6.233956
## sample estimates:
## mean of the differences 
##                1.166667

According to the results, there’s no significant difference between

the samples of 2015 and 2016, so the final conclusion is that

we support the null hypothesis, and fail to reject it -

there’s no significant differences between the samples.

## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout