Studies employing quantitative methods in the field of ecotourism can be classified into two broad categories. First, there are studies that examine essentially demographic data through the use of descriptive statistics, typically with the objective of characterizing the economic and social environment of a host population or target market. Second, more comprehensive studies examine complex relationships and cause-and-effect associations between variables describing the hosts or markets and their behavior. These latter studies often employ factor-cluster segmentation procedures, or other simpler forms of clustering procedures (Aeero, 1994). They typically include different statistical tests for examining the differences between the groups obtained. The tests observed were chi-squared, t-test, and analysis of variance. In addition, some studies used multiple regressions to model the variables explaining certain behavioral patterns.
Question 1
Descriptive Statistics
Mean
Std. Deviation
N
Sales
1.6878E2
85.38775
26
Reps
50.0769
12.93344
26
Brands
8.5385
2.26682
26
Adspend
5.3731
1.88882
26
Crime Index
9.3846
4.39160
26
Correlations
Sales
Reps
Brands
Adspend
Crime Index
Pearson Correlation
Sales
1.000
.591
-.697
.166
.387
Reps
.591
1.000
-.147
.103
.457
Brands
-.697
-.147
1.000
-.182
-.002
Adspend
.166
.103
-.182
1.000
-.158
Crime Index
.387
.457
-.002
-.158
1.000
Sig. (1-tailed)
Sales
.
.001
.000
.208
.025
Reps
.001
.
.236
.309
.010
Brands
.000
.236
.
.186
.497
Adspend
.208
.309
.186
.
.221
Crime Index
.025
.010
.497
.221
.
N
Sales
26
26
26
26
26
Reps
26
26
26
26
26
Brands
26
26
26
26
26
Adspend
26
26
26
26
26
Crime Index
26
26
26
26
26
Model Summaryc
Model
R
R Square
Adjusted R Square
Std. Error of the Estimate
Change Statistics
R Square Change
F Change
df1
df2
Sig. F Change
1
.854a
.729
.706
46.30649
.729
31.003
2
23
.000
2
.874b
.763
.718
45.35397
.034
1.488
2
21
.249
a. Predictors: (Constant), Brands, Reps
b. Predictors: (Constant), Brands, Reps, Adspend, Crime Index
c. Dependent Variable: Sales
Coefficientsa
Model
Unstandardized Coefficients
Standardized Coefficients
t
Sig.
B
Std. Error
Beta
1
(Constant)
203.957
54.936
3.713
.001
Reps
3.299
.724
.500
4.556
.000
Brands
-23.465
4.131
-.623
-5.680
.000
2
(Constant)
190.524
61.827
3.082
.006
Reps
2.623
.812
.397
3.233
.004
Brands
-23.717
4.108
-.630
-5.773
.000
Adspend
1.997
5.025
.044
.397
.695
Crime Index
4.119
2.388
.212
1.725
.099
a. Dependent Variable: Sales
Question 2
Descriptive Statistics
Mean
Std. Deviation
N
y
7.0771
6.86242
28
x
78.8286
131.23091
28
Correlations
y
x
Pearson Correlation
y
1.000
-.567
x
-.567
1.000
Sig. (1-tailed)
y
.
.001
x
.001
.
N
y
28
28
x
28
28
Model Summaryb
Model
R
R Square
Adjusted R Square
Std. Error of the Estimate
Change Statistics
R Square Change
F Change
df1
df2
Sig. F Change
1
.567a
.321
.295
5.76168
.321
12.302
1
26
.002
a. Predictors: (Constant), x
b. Dependent Variable: y
ANOVAb
Model
Sum of Squares
df
Mean Square
F
Sig.
1
Regression
408.385
1
408.385
12.302
.002a
Residual
863.121
26
33.197
Total
1271.506
27
a. Predictors: (Constant), x
b. Dependent Variable: y
Coefficientsa
Model
Unstandardized Coefficients
Standardized Coefficients
t
Sig.
B
Std. Error
Beta
1
(Constant)
9.413
1.276
7.375
.000
x
-.030
.008
-.567
-3.507
.002
a. Dependent Variable: y
Question 3
exponential
logistic
time
model
model
1
1.0
1.0
2
1.3
1.3
3
1.8
1.8
4
2.5
2.3
5
3.3
3.0
6
4.5
3.8
7
6.0
4.8
8
8.2
6.0
9
11.0
7.3
10
14.9
8.8
11
20.1
10.3
12
27.1
11.8
13
36.6
13.2
14
49.4
14.4
15
66.7
15.6
16
90.0
16.5
17
121.5
17.3
18
164.0
17.9
19
221.4
18.4
20
298.9
18.8
21
403.4
19.1
22
544.6
19.3
23
735.1
19.5
24
992.3
19.6
25
1339.4
19.7
26
1808.0
19.8
27
2440.6
19.8
28
3294.5
19.9
29
4447.1
19.9
30
6002.9
19.9
exponential
logistic
N
growth rate
growth rate
0
0
0
1
0.3
0.285
2
0.6
0.54
3
0.9
0.765
4
1.2
0.96
5
1.5
1.125
6
1.8
1.26
7
2.1
1.365
8
2.4
1.44
9
2.7
1.485
10
3
1.5
11
3.3
1.485
12
3.6
1.44
13
3.9
1.365
14
4.2
1.26
15
4.5
1.125
16
4.8
0.96
17
5.1
0.765
18
5.4
0.54
19
5.7
0.285
20
6
0
21
6.3
-0.315
22
6.6
-0.66
23
6.9
-1.035
24
7.2
-1.44
Quantitative approaches to the study of language draw numerically-based comparisons between different types of language use: for instance, they may look at the frequency with which certain linguistic forms are used across speakers, groups of speakers, texts or text types. Quantitative approaches use descriptive statistics and inferential statistics for data analysis (Babbie, 1995).
Quantitative approaches are associated particularly with variationist sociolinguistics in the tradition inspired by William LABOV so much so that the terms quantitative sociolinguistics or the quantitative paradigm are found for this tradition. For instance, in his study of the language of New York City (e.g. Labov, 1966, 1972a) Labov was able to identify systematic patterns in the frequency distribution of certain pronunciation features across different social groups and speaking styles (Barron, 1998).
A quantitative approach informs other sociolinguistic traditions, for example quantitative patterns have been identified in the use of interactional features such as interruptions. It is also typical for much work in corpus linguistics (researchers have analysed corpora of several million words to identify systematic patterns of usage across a range of text types; see e.g. ...