Psych

__Scientific methodology__

•depends on this application of inferential statistics.

experiment

heart of scientific methodology is

Experiment

has been __designed to test a hypothesis__, and the resulting data must be analyzed.

sign test

is chosen because (1) it is easy to understand and (2) all of the major concepts concerning hypothesis testing can be illustrated clearly and simply.

Sign test

•__**It ignores the magnitude**__ of the different scores and __**considers only their direction or sign.**__

the essential features

•that __**there are paired scores in the conditions, and the differences between the paired scores are analyzed.**__

Hypothesis

* Guess/Hunch
* Educational Guess
* Intellectual Guess

Alternative Hypothesis

H1

research hypothesis

other term of alternative hypothesis

Alternative Hypothesis

•is the one that **claims the difference** in results between conditions is due to the independent variable.

Null Hypothesis

H0

Null Hypothesis

It is the **logical counterpart** of the alternative hypothesis such that if the \*\* is false, the alternative hypothesis must be true.

***reject the Ho***

*obt v* < *crit v = ?*

__**significant or reliable**__

•Rejecting the null hypothesis __**allows us to accept indirectly the alternative hypothesis.**__ When we reject it the __**results are ?**__

reject the null hypothesis

If the obtained probability turns out to be __**equal to or less than a critical probability level or alpha level we ?**__

**failing to reject H0**

If the obtained probability is **greater than the alpha level**, we conclude by **?**

fail to reject Ho, accept Ha

obt v > crit v =

**Type 1 error**

is defined as a decision to reject the null hypothesis when the null hypothesis is true.

False Positive

**Type 1 error**

**Type 2 error**

is defined as a decision to retain the null hypothesis when the null hypothesis is false.

**False Negative**

**Type 2 error**

**Alpha**

*limits the probability of making a Type I error.*

**Beta**

is defined as the *probability of making a Type II error.*

0\.05

Alpha levels are used, like \*\*\*\* or social sciences

0\.01

Alpha levels are used, like \*\*\*\* for clinical trials

**consider the consequences of making an error**

To determine a reasonable alpha level for an experiment, **we must ?**

***the probability of making a Type I error***

the more stringent the alpha level, decreases?

the probability of making a type II error

making alpha more stringent increases ?

non directional

•If the __**alternative hypothesis in ??**____,__ __**we evaluate obtained result or any even more extreme in both directions (both tails)**__.

__**directional**__

•If the __**alternative hypothesis is ??, we evaluate only the tail of the distribution that is in the direction specified by H1**__

__**two-tailed probability**__

•This probability is called a __**__**__value because the outcomes we evaluate occur under both tails of the distribution.

**one-tailed probability**

The probability is called a **___** because all of the outcomes we are evaluating are __**under one tail of the distribution.**__

__*significant - statistically significant*__

If we are able to reject the null hypothesis the results are?

**William Sealy Gossett**

Student's t Test by:

z test

* mean and standard deviation is known
* N __>__ 30
* 1 curve for all sample size, normal curve

t test

* standard deviation is unknown - solve for estimates of s
* N __

Degrees of freedom

is the number of scores that are free to vary in calculating the statistic

**Parametric Test**

* Depends considerably on population characteristics
* They are robust tests, do not greatly disturb the sampling distribution of its statistic
* They are more powerful and versatile
* Ratio/Interval Scaling

nonparametic test

* Depends little on knowing population distributions, they are often referred to as ***distribution-free tests.***
* *Nominal or Ordinal Scaling*
* *If extreme violation of an assumption of the pramaetric test or* __*inappropriate scaling is used*__,

Chi-square

One of main uses is in determining whether two categorical variable are independent or are related.

***Contingency table***

is  two-way table showing the contingency between two variables where the variables have been classified into __**mutually exclusive**__ categories and the __**cell entries are frequencies**__.

Mann-Whitney U Test

Alternative for t test independent groups; atleast ordinal scaling;

Kruskal-Wallis Test

Alternative for one-way ANOVA; atleast ordinal scaling of DV

__**Confidence Interval**__

is a range that probably contains the population value.

__**Confidence Limits**__

are the values that bound the confidence interval

ANALYSIS OF VARIANCE

anova

R.A. Fisher

**F test** *by*

F test

* Can be used to form two independent estimates of the population variance
* Appropriate occurs when analyzing the data from experiment that use two or more conditions or groups (more common to encounter experiments that involve three or more groups.

F test

Anova is also known as ___ test?

F distribution

Anova uses what distribution?

T test

Wilcoxon signed-rank test is also known as __ test?

T distribution

Wilcoxon signed-rank test uses what distribution?

U test

Mann-Whitney Test is also known as __ test?

U distribution

Mann-Whitney Test uses what distribution?

H test

Kruskal-Wallis Test is also known as __ test?

x2 distribution

Kruskal-Wallis Test uses what distribution?

small effect

0\.00-0.20

medium effect

0\.21-0.79

large effect

< 0.80

**1.**  ***p*** **value** __**

to know if the result is significant

**Null-hypothesis approach**

does not tell the size or the effect

**Confidence-interval approach**

affirm that the IV has a real effect and at the same time gives us an estimate of the size of the real effect;

95% and 99%

is the commonly use confidence interval

1\. normal distribution 2. homogeneity of variance

assumption for t test