Lecture Communication research: Asking questions, finding answers (4e) Chapter 11: Testing for relationships

Lecture Communication research: Asking questions, finding answers (4e) Chapter 10: Testing for differences. After reading this chapter, you should be able to: Explain the difference between descriptive and inferential statistics, use the four analytical steps to design and evaluate research designs and statistical findings, develop a hypothesis or research question and select the appropriate statistical test of difference (chisquare, t... Đề tài Hoàn thiện công tác quản trị nhân sự tại Công ty TNHH Mộc Khải Tuyên được nghiên cứu nhằm giúp công ty TNHH Mộc Khải Tuyên làm rõ được thực trạng công tác quản trị nhân sự trong công ty như thế nào từ đó đề ra các giải pháp giúp công ty hoàn thiện công tác quản trị nhân sự tốt hơn trong thời gian tới.

TESTING FOR RELATIONSHIPS

Chapter 11

• 2 continuous variables

Regression

• 2 or more continuous level variables

BASIC ASSUMPTIONS

 Data collected from sample to draw conclusion about population

 Data from normally distributed population

 Appropriate variables are selected to be tested using theoretical models

 Participants randomly selected

ALTERNATIVE AND NULL HYPOTHESES

 Inferential statistics test the likelihood that the

alternative hypothesis is true and the null hypothesis

is not

 Significance level of 05 is generally the criterion for

this decision

 If p  05, then alternative hypothesis accepted

 If p > 05, then null hypothesis is retained

FOUR ANALYTICAL STEPS

1 Statistical test determines if a relationship

exists

2 Examine results to determine if the

relationship found is the one predicted

3 Is the relationship significant?

4 Evaluate the process and procedures of

collecting data

 Also known as Pearson product-moment correlation

coefficient

 Represented by r

 Correlation reveals one of the following:

 Scores on both variables increase or decrease

 Scores on one variable increase while scores on the other

variable decrease

 There is no pattern or relationship

 Correlation coefficient or r reveals the degree to which

two continuous level variables are related

 Participants provide measures of two variables

 If p of the r statistic is  05

 relationship is significant

 hypothesis or research question accepted

 Correlation cannot necessarily determine causation

INTERPRETING THE COEFFICIENT

Direction of relationship

Positive– both variables

increase or both

variables decrease

Negative – one variable

increases while the

other decreases

Relationship strength

< 30 – weak or slight

relationship

.30-.70 – moderate or

substantial relationship

>.70 – strong or dependable

relationship

SCALE OF CORRELATION

DEGREE OF SHARED VARIANCE

 r 2 – represents the

percentage of variance

two variables have in

common

 Known as coefficient of

determination

 Found by squaring r

• .2 or -.2 = 04 r 2

• .3 or -.3 = 09 r 2

• .4 or -.4 = 16 r 2

• .5 or -.5 = 25 r 2

• .6 or -.6 = 36 r 2

• .7 or -.7 = 49 r 2

• .8 or -.8 = 64 r 2

• .9 or -.9 = 81 r 2

CORRELATION MATRIX

LIMITS OF CORRELATION

 Examines relationship between only 2 variables

 Any relationship is presumed to be linear

 Limited in the degree to which inferences can

be made

 Correlation does not necessarily equal causation

 Causation depends on the logic of relationship

 Predicts some variables by knowing others

 Assesses influence of several continuous level

predictor, or IVs, on a single continuous criterion, or DV

 Used to examine causation without experimentation

 “Variance accounted for”

 the % of variance in the criterion variable accounted for by

the predictor variable

LINEAR REGRESSION

 Regression line – line drawn through the data

points that best summarizes the relationship

between the IV and DV

 The better the fit of the line, the higher R

 Adjusted R 2 – the proportion of variance

explained or accounted for on the DV by the IV

BETA WEIGHTS

 Also known as beta coefficients

 Represented by β

 Allows comparison among variables of different measuring units

 Range from +1.00 to –1.00

MULTIPLE REGRESSION

 Tests for significant relationship between one

DV and multiple IVs

 Independently

 As a group

 Use beta weights to interpret the relative

contribution of each IV

STRUCTURAL EQUATION MODELING

 Exogenous variable

 Endogenous variable

 Is the theoretical model different from associations found in the data?

STATISTICAL TEST OF RELATIONSHIP

CAUTION IN USING STATISTICS

 Use and interpretation of statistical tests is subjective

 Many variations of each test

 Researcher must interpret statistical result

 Are the results worth interpreting statistically?

 Was appropriate statistical test selected and used?

 Are the results statistically significant?

 Are the results socially significant?