One-tailed or Two-tailed

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
Raja Rizal
PLS Junior User
Posts: 7
Joined: Tue Oct 27, 2015 3:17 pm
Real name and title: Raja Rizal Iskandar Raja Hisham, Mr.

One-tailed or Two-tailed

Post by Raja Rizal »

Hi Team Smart-PLS,

I have few questions that need expert's clarification.

1. I am wondering are there any articles applying PLS approach and at the same time use one-tailed testing in Smart-PLS?
2. Do we normally run path model using Two-tailed testing by default?
3. In the case of testing for moderating/interaction effect, is it always we have to select for one-tailed testing instead of two-tailed?

Thanks!
Raja Rizal
User avatar
cringle
SmartPLS Developer
Posts: 818
Joined: Tue Sep 20, 2005 9:13 am
Real name and title: Prof. Dr. Christian M. Ringle
Location: Hamburg (Germany)
Contact:

Re: One-tailed or Two-tailed

Post by cringle »

Thanks. The decision on one tailed and two-tailed testing depends on a priori assumption. If a relationship can only be positive and a negative outcome is impossible, then, you to one-tailed testing, otherwise two-tailed. In most cases, researchers assume that a relationship possibly is positive and negative.

Best
Christian
brill5
PLS Junior User
Posts: 2
Joined: Sun Sep 24, 2017 7:25 pm
Real name and title: Tom Brill

Re: One-tailed or Two-tailed

Post by brill5 »

May I ask for your help in explaining the difference in your response vs. Kock's (2015) findings. Kock: A one- tailed test is recommended if the coefficient is assumed to have a sign (positive or negative), which should be reflected in the hypothesis that refers to the corresponding association. If no assumptions are made about coefficient sign, a two-tailed test is recommended.

My hypothesis assumed a positive relationship between two constructs.
Post Reply