# Teltzrow et al.:Multi-Channel Consumer Perceptions

All path coefficients display a significant t-value on the 5% level. Goodness of fit statistics provide a χ2 - value of 96.17 with 48 degrees of freedom, leading to a p-value of 0.00005. Since the χ2 fit index in linear structural models is highly dependent on the sample size [Byrne 1998] and tends to underestimate the model fit in larger samples, further fit indices are considered for model assessment. The Root Mean Square Error of Approximation (RMSEA) of 0.044 leads to a p-value for Test of Close Fit of .778, which indicates a good model fit. A Goodness- of-Fit Index (GFI) of 0.99 and an Adjusted Goodness-of-Fit Index (AGFI) of 0.99 also hint at a good overall model fit, but since the parsimony indices PNFI and PGFI are less good (.721 and .612 respectively), the model is held to show an overall acceptable fit.

The above measures may be biased since the model is induced from the same sample that delivered the factors in the confirmatory factor analysis. An unbiased test of the model can be achieved by applying it to the second sample of n=524 participants. The model for sample 2 gives a χ2 - value of 97.31 with 48 degrees of freedom, leading to a p-value of 0.00003. This RMSEA-value of 0.044 leads to a p-value for Test of Close Fit of .758, a PGFI of .611, a PNFI of .719 and an AGFI of .996. In summary, these measures point out an acceptable model fit with path coefficients in the same range as in the previous model. The relevant path coefficients and fit indices for the two sub-samples as well as for the full sample are summarized in Table 4. All path coefficients in the samples are significant on the 5% level except the coefficient from perceived size to trust in the second sub sample. However, the coefficient is significant in the full sample.

0.52

PS

0.25

PS2

0.44

PS3

0.11

PR1

0.08

PR2

0.08

PR3

0.06

PRI1

Perceived Size

0.17

Perceived Reputatio n

0.41

Perceived Privacy

0.46

0.75

0.96

0.97

0.99

0.69

0.87

0.94

0.96

## Trust

0.89

TR1

0.21

0.95

TR2

0.09

0.84

TR3

0.29

0.02

PRI2

0.00

PRI3

1.00

Chi-Square=96.17, df=48, P-value=0.00005, RMSEA=0.044

Sample

N

Path perceived size Î trust

Path perceived reputation Î trust

Path perceived privacy Î trust

χ2

df

P

RMSEA

P (close fit)

1st 2nd

524 524

0.17* 0.04^{ns }

0.41* 0.47*

0.46* 0.47*

96.17 97.31

48 48

0.00005 0.00003

0.044 0.044

0.778 0.758

Full

1048

0.11*

0.42*

0.46*

106.80

48

0

0.034

0.999

Figure 2: Linear structural model for the influence of perceived size (PS), perceived reputation (PR), perceived privacy (PRI) on trust (TR) for sample 1 (N=524).

# Table 4: Overview of relevant path coefficients and fit indices for sub samples and entire sample

Note. * indicates a significant t-value on 5%-level. ns = not significant.

Page 24