Testing of my hypothesis

[sravankumardv]

Hi Everyone,

I am doing my master's thesis and I completed collecting my data. I am trying to test my hypothesis using Smart PLS. I created the model and loaded the model with the help of the data I have . I run the PLS algorithm and bootstrapping and generated the reports. But am unable to understand how to test whether my hypothesis are valid or not.

I am unable to identify the t-values , p, z - values etc from the model and the report generated. As I am new to this I cannot identify the different parameters from the model and test the validity of my hypothesis. I did not find any standard procedure to test the validity of hypothesis online.

Please someone help me in identifying different parameters from the model and steps to test the validity of hypothesis.

Please help me in this process which is highly appreciable.

[sat7n]

from a previouse post by prof. Bido
PLS analysis summary:
The assessment of the measurement model:

1.1) Run the PLS algorithm:

Report / PLS / Quality criteria / Overview:
- AVE equal or greater than .5 (convergent validity)
- reliability equal or greater than .7

Report / PLS / Quality criteria / Latent Variable Correlations
- all correlations should be lower than the AVE squared root (discriminant validity)

Report / PLS / Quality criteria / Cross loadings
- the outer loading of each indicator should be greater in its LV and lower in the others (discriminant validity).
- the outer loading should be greater than .7 (convergent validity).


1.2) Run the bootstrap
Report / Bootstrapping / Bootstrapping / Outer loadings (Mean, standard deviation, T-values)
- all t values should be greater than 1.96 (5%, two tail)
The assessment of the structural model:

2.1) Run the PLS algorithm:
- in the model you will see the path coefficients and inside the blue balls the R2

Report / PLS / Calculation results / Path coefficients
- The same results that were showed in the model

Report / PLS / Quality criteria / Total effects
- you could assess the direct, indirect, and total effects.

2.2) Run the bootstrap
- in the model you will see the t-values of the path coefficients

Report / Bootstrapping / Bootstrapping / path coefficients (Mean, STDEV, T-values)
- all t values should be greater than 1.96 (5%, two tail)

[sravankumardv]

Thanks you very much for the help.

[sat7n]

Good luck:-)

[Hengkov]

For addition, calculate effect size: R2 Inc - R2 Exc : 1-R Inc.
Next, Calculate GoF Model: SQRT average communality x average R-squares.
And run blinfolding for assess predictive relevance ( > 0 or < 0).
Regards,
Hengky

[Lavinia]

Hello,

I am also writing my master thesis, and I am unsure about how to interpret path coefficients. Can someone help me with this issue or give me some references? I would really appreciate it. After I ran the PLS algorithm I got two negative path coefficients (-0.271 and -0.022) and two under 0.05 (0.037 and 0.023). The rest are 0.455, 0.174, 0.281, 0.531, 0.547 and 0.331. Does that mean that 4 of my hypotheses are not supported?

Thank you very much!

[Hengkov]

Hi Lavinia,
Next, run bootstrap and look significant T-statistics for testing hypothesis.
Regards,
Hengky

[ruchi]

If my hypothesis is H1-"Cost of service has a negative effect on adoption of service" and after conducting PLS result comes out as statistically significant but positive i..e cost of service has a positive effect on adoption , then how to state the hypothesis- " Hypothesis H1 is rejected OR Hypothesis H1 is supported but with opposite effect . What is the correct way of stating the finding.

Thanks
Warm Regards
Ruchita

[Hengkov]

Hi Ruchi,

H0 accept, H1 reject because Type II error. T-statistic not significant (incorrect significant).

Regards,
Hengky