GW09 & 10 the t-statistic: study guide
 

 Note:  This study guide combines both GW 9 and GW 10.

 1  Identify and explain the major shortcoming of using the z-score as an inferential statistic.

 2  What statistic is used when the z-score cannot be used?  How does it differ from the z-score?

 3  Write the formulae for (1) a z-score and (2) a t-score.

 4  Sketch a graph depicting the differences between z-score distributions and t-score distributions.

 5  Identify and define df.
 6 Explain the role of df in each of the following:

    -- the ability of sample variance to estimate population variance.

    --the ability of the t statistic to approximate the z-score.

 7  Explain the relations among sample size, df, and the t and z distributions.

 8   Compare and contrast the t distribution to that of the z distribution, in terms of variability and shape.
 9  Explain the logic of the t formula, being sure to include comments about each of the following:
     [Remember to explain -- don't just name the parts!]

     What does the numerator measure?  What does the denominator measure? 

     Where would the effects of one's experimental "treatment" show up? 

     Where would the effects of individual differences and other "chance" factors show up? 
     Where would the effects of increasing sample size (N) appear?

     Where would efforts to reduce unwanted variability appear?

10 What do the terms "significant" and "not significant" mean in scientific reports?

11 Identify the assumptions for the t statistic and note the ways to ensure that they are met.

12 Compare and contrast the t-test and z-test in terms of versatility & power.