Difference between test statistics and t-statistics?

In on of the practice tests on the CFA site you have to calculate the test statistic. The standard error is unknown, but the t-statistics is given as 4,28 and the coeffisient as 1,0264.

Exercise: "Based on the results in Exhibit 1, the value of the test statistic relating to Hamilton’s null hypothesis about the value of the coefficient on SPREAD is closest to:

Answer:

The null hypothesis is H0: bspread = 1. The calculated value of the t-statistic is t = (1.0264 – 1.0)/standard error. The standard error is 1.0264/4.28 = 0.24. The calculated value for t = (1.0264 – 1.0)/0.24 = 0.11.

What is the difference between the t-statistics (which is given in the exercise) and the test-statistics calculated as 0,11?

Just to start-- a test statistic is a standardized value calculated based on a sample and hypothesis. Some examples: f, t, z, chi-square, and others are all types of test statistics.

In this problem, though, they are asking specifically about a t-test. Generally, a given regression output has t-statistics calculated. These values are calculated assuming that bi = 0. If you want to test a different hypothesis, i.e. bi=1, you need to calculate that yourself. This problem is an example of that case. The t-stat of 4,28 is for the test of hypothesis that the coefficient = 0. The t-stat of 0,11 is for the test of hypothesis where the coefficient =1.

Hopefully, the difference is more clear.

Ok thanks a lot. So any t-stat from a regression output is always assuming that H0 --> Bi = 0?

Exactly.