Hotel Analysis

Table of Contents

Introduction3

Findings (Analysis)3

Task 13

Task 27

Task 313

Task 414

Task 516

Conclusion16

Additional Data16

Hotel Analysis

Introduction

The hotel data collected contains mix variables which among which some are categorical; some are nominal and some are just numeric data. In order to analyze the requirements of directors of the hotel, we will start with the exploration of data using descriptive statistics. Later on we will assess the association and casual relationships between variables using appropriate statistics in Excel.

Findings (Analysis)

Task 1

There are many techniques available to estimate the missing values and complete the data set but as we have observed, only record # 43 and 81 were having missing values. While entering data, one can contact the respondents and obtain the value. Here since the data loss is only for the two records, we will remove these records.

It is important for the analysis to have no outliers as it creates abnormalities in the data distribution. We have observed that distance, advertising and employee variables have 1 outlier each while the Type A and Type B has two outliers each. As these observations are skewing the distribution and effecting the averages. We will remove them as they will affect our conclusions. The final data has 91 observations.

In our data besides the Hotel Variable, we have 4 categorical Variables and we will represent them using histogram.

Figure 1, Histogram of Region

Figure 2: Histogram of Size

Figure 3: Histogram of Gender

Figure 4: Histogram of Year

Following are the Histograms of sizes in each region

Figure 5: Distribution of Sizes in All regions

Figure 6: Histogram with Frequency Distribution of sizes of Hotels in Denmark.

Figure 7: Histogram of Frequency Distribution of sizes of Hotels in Holland.

Figure 8: Histogram of Frequency Distribution of sizes of Hotels in Germany.

Task 2

Following are the descriptive statistics of numerical data:

Table 1: Descriptive Statistics of Distance Variable

Distance

Mean

2.7425

Standard Error

0.49622

Median

2.125

Mode

1.4

Standard Deviation

4.962202

Sample Variance

24.62345

Kurtosis

92.90575

Skewness

9.471457

Range

50

Minimum

1

Maximum

51

Sum

274.25

Count

100

Confidence Level(95.0%)

0.984609

Table 2: Descriptive Statistics of Advertising

Advertising

Mean

1511.71

Standard Error

143.8146

Median

1410.5

Mode

2010

Standard Deviation

1438.146

Sample Variance

2068264

Kurtosis

42.85336

Skewness

5.296972

Range

13024

Minimum

106

Maximum

13130

Sum

151171

Count

100

Confidence Level(95.0%)

285.3594

Table 3: Descriptive Statistics of Employee Variable

Employees

Mean

20.15

Standard Error

0.715679

Median

20

Mode

20

Standard Deviation

7.156794

Sample Variance

51.2197

Kurtosis

17.39431

Skewness

2.954261

Range

56

Minimum

11

Maximum

67

Sum

2015

Count

100

Confidence Level(95.0%)

1.420063

Table 4: Descriptive Statistics of Type A

Type A

Mean

385620

Standard Error

10677.96

Median

369000

Mode

476000

Standard Deviation

106779.6

Sample Variance

1.14E+10

Kurtosis

1.741373

Skewness

0.328692

Range

716000

Minimum

0

Maximum

716000

Sum

38562000

Count

100

Confidence Level(95.0%)

21187.39

Table 5: Descriptive Statistics of Type B

Type B

Mean

210363

Standard Error

2604.55

Median

213000

Mode

223200

Standard Deviation

26045.5

Sample Variance

6.78E+08

Kurtosis

45.18853

Skewness

-6.13151

Range

228500

Minimum

0

Maximum

228500

Sum

21036300

Count

100

Confidence Level(95.0%)

5167.993

We have removed 9 observations from the total data set. We removed record 43 and 81 because of missing values. Record # 10 was removed due to outliers in distance variable. Record # 29 of was removed for outliers in advertisement variable. We removed the record of hotel # 29 due to outliers in employees. Record # 8 and 22 are removed due to outliers in Type A. Record # 2 and 5 are removed due to outliers in Type B variable.

Table 6: Descriptive Statistics of Distance Variable

Distance

Mean

2.278571

Standard Error

0.09967

Median

2

Mode

1.5

Standard Deviation

0.950793

Sample Variance

0.904008

Kurtosis

-1.12109

Skewness

0.430463

Range

3

Minimum

1

Maximum

4

Sum

207.35

Count

91

Confidence Level(95.0%)

0.198012

Table 7: Descriptive Statistics of Advertising

Advertising

Mean

1390.626

Standard Error

87.37846

Median

1410

Mode

2010

Standard Deviation

833.5374

Sample Variance

694784.5

Kurtosis

-1.32121

Skewness

-0.2885

Range

2515

Minimum

106

Maximum

2621

Sum

126547

Count

91

Confidence Level(95.0%)

173.5926

Table 8: Descriptive Statistics of Employee Variable

Employees

Mean

19.6044

Standard Error

0.570517

Median

20

Mode

20

Standard Deviation

5.442383

Sample Variance

29.61954

Kurtosis

-0.59447

Skewness

0.436909

Range

23

Minimum

11

Maximum

34

Sum

1784

Count

91

Confidence Level(95.0%)

1.133431

Table 9: Descriptive Statistics of Type A

Type A

Mean

384237.4

Standard Error

9462.925

Median

367000

Mode

476000

Standard Deviation

90270.56

Sample Variance

8.15E+09

Kurtosis

-0.6473

Skewness

0.518563

Range

407500

Minimum

225500

Maximum

633000

Sum

34965600

Count

91

Confidence Level(95.0%)

18799.75

Table 10: Descriptive Statistics of Type B

Type B

Mean

213849.5

Standard Error

865.5422

Median

212700

Mode

223200

Standard Deviation

8256.746

Sample Variance

68173861

Kurtosis

-1.39057

Skewness

0.033973

Range

28100

Minimum

200400

Maximum

228500

Sum

19460300

Count

91

Confidence Level(95.0%)

1719.551

Table 11 in appendix shows the Grouped Frequency Distribution of the Type A data:

The mean was calculated to be € ...