The scientific method

1. preparing the study

- Research question should have all components: independent, dependent variables, and subjects.
- hypothesis — nondirectional/directional…
- Literature review should be thoroughly done.

2. Conducting the study

- Execution of research procedure

It’s like a recipe… “Can I replicate the study? ” If I cannot replicate the study exactly, then it’s not well-explained in the paper. How this research set up or how this reserch to be carried out?

- selection of subjects and instruments

Sampling — the key point is **representation **of the population

Population: people who you are interested in. The group of people to whom the results can be generalized.

The population and the sample should have commonalities.

the research conclusion is on the population, not only on your samples.

**Kicking it up a notch? — **

to make something more exciting, intense, or interesting, as a food dish or a social gathering | |

Example: |
kick it up a notch with fresh garlic |

Descriptive statistics permit the researcher to meaningfully describe many, many scores with a small number of indices. If such indices are calculated for a sample drawn from a population, the resulting values are referred to as **statistics**; if they are calculated for an entire population, they are refered to as **parameters**.

parameters: numerical **estimates** on population based on the statistics

**Kids with autism… are they interested in exploring the function of the objects? **

Probability sampling?

stratified —set up strata –then random sampling from each group; to ascertain the representation for each sub-group

Cluster – randomly select group

Random assignment vs Random sampling

Random assignment : true experimental design’s prerequisite.

Study samples:

Descriptive study– 10% minimum

correlation:30

causal-comparative: 30 per each group

experimental: 15 per each group

—

reliability ?

Not reliable— not consistent… consistency… giving out similar results every time.

Validity?

What is supposed to measure… issue…