Statistical Modelling

Running head: STATISTICAL MODELLING
Statistical Modelling
Name of the Student:
Name of the University:
Author Note:

1
STATISTICAL MODELLING
Table of Contents
Section 1: Introduction...............................................................................................................2
Section 2: Summary, Description of Price and T-test................................................................3
Section 3: Price across Brands and ANOVA Test.....................................................................6
Section 4: Students Preference...................................................................................................9
Section 5: Discussion and Conclusion.....................................................................................10
Reference and Bibliography.....................................................................................................11

2
STATISTICAL MODELLING
Section 1: Introduction
There are several studies on the petrol and gasoline prices that changes depending on
the dynamic nature of the market. In the last couple of decades Spanish petrol market
experienced a restructuration process that influenced by the privatization and liberalisation.
Prior to the liberalisation, the petrol market was monopoly in Spain. To increase the petrol
station networking, reduction of the minimum distance among the petrol distance was
focused and it raised the competition too. This research studied the market of petrol price
using a dynamic price model, current economic situations and did an empirical study
(Escribano, and Torrado 2018). The used data in the study was on retail prices, the spot prices
and the demand for the petrol and gasoline. The motive of the paper is to analyse the effects
of demand and cost on current margins.
In this study the data is secondary and collected form government website. A subset
off data is used here for the analysis and the extracted data contains few important variables.
The data contains the variables like, the address of the petrol station, suburb and postcode,
Brand of the petrol, fuel code and price of the petrol. This data is used to check whether the
prices of the petrol produced by different brands is same or different and if it is different then
which brand price is lower.
The second data set is primary data that is collected on the variable that are brand of
the petrol, price of the petrol and the address of the service station. The analysis used only the
variable brand name to check which one is mostly used. The limitation of the data set is it
contains less amount of observation which is just not small but 30 observations (Quinlan et
al. 2019). The data contains only the brand name of petrol which only can tell about the
preference of brad among the students.

3
STATISTICAL MODELLING
The paper shows the summary of the price in section 2, section 3 discuses about the
average price of different brands that are different, the section discusses the preference of the
brand and the last part contains a summary of the study and a suggestion for further study.
Section 2: Summary, Description of Price and T-test
The mean value of the price is 122.496 Australian cent and the standard deviation is
13.485. The lower bound of 95% confidence interval of price is (122.496-0.837) = 121.66
and the upper bound of 95% confidence interval of price is (122.496+0.837) = 123.333. The
standard error is 0.426 which is very low to the number of observation which is equal to
1000. This implies that there exist a very low amount of error. The skewness in negative and
the kurtosis is positive this implies that the data is negatively skewed with a high peak. The
spread of the distribution is from 57.9 to 166.7. The location of the distribution is at 122.496
and the shape is defined by the mode which is equal to 129.9.
Table 1: Summary statistics of Price
Price
Mean 122.496
Standard Error 0.426
Median 121.950
Mode 129.900
Standard Deviation 13.485
Sample Variance 181.857
Kurtosis 1.904
Skewness -0.462
Range 108.800
Minimum 57.900
Maximum 166.700
Sum 122496.500
Count 1000
Confidence Level (95.0%) 0.837