week 2 & 3 quita

profileJordanjameire
CooperMarquitaSOCI603A2.docx

Mock Study 1: One Sample t-Test

Null Hypothesis (Ho): The mean number of activities of daily living (ADL) performed after group therapy by depressed clients is not significantly different from 15.

H0: µ = 15

Alternative Hypothesis (H1): The mean number activities of daily living performed after group therapy by depressed clients is significantly different from 15.

H1: µ ≠ 15

The researchers want to know whether the mean is different from 15, in either direction. The test is, therefore, two-tailed.

Levels of Significance

Significance Level (i): α = 0.05

Significance Level (ii): α = 0.01

Results of Analysis

The P-Value: The two-sided p = 0.122

Decision at α = 0.05: Since p = 0.122 > 0.05 alpha level of significance, we fail to reject the null hypothesis.

Interpretation: There is no sufficient evidence to conclude that the mean ADL score after therapy is significantly different from 15.

Decision at α = 0.01: Since p = 0.122 > 0.01 alpha level of significance, we fail to reject the null hypothesis.

Interpretation: There is no sufficient evidence to conclude that the mean ADL score after therapy is significantly different from 15.

Recommendation: Even though the sample mean beat the typical by 1.65, the difference was not statistically significant at both 0.05 and 0.01 alpha levels of significance. This means that group therapy does not produce statistically significant difference in ADL scores. The behavioral scientists should thus not recommend it (group therapy) based on the study.

Mock Study 2: paired-samples t-test

Null Hypothesis (Ho): There is no significant difference in mean ADL scores before and after group therapy.

Alternative Hypothesis (H1): There is a significant difference in mean ADL scores before and after group therapy.

Leven of significance

α = 0.05

Results of Analysis

The P-Value: The two-sided p = 0.002

Decision at α = 0.05: Since p = 0.002 < 0.05 alpha level of significance, we reject the null hypothesis in favor of the alternative hypothesis.

Interpretation: There is a statistically significant difference in ADL scores before and after group therapy. The increased mean score of 14.90 from 10.60 suggests improved performance in activities of daily living.

Recommendation: The researchers should consider recommending group therapy because participants of the study showed statistically significant improvement in their ADL scores after they had done therapy.

Mock Study 3: Independent-Samples t-Test

Null Hypothesis (Ho): There is no significant difference in job satisfaction scores between employees who participated in counselling and those who did not.

Alternative Hypothesis (H1): There is a significant difference in job satisfaction scores between employees who participated in counselling and those who did not.

Level of significance

α = 0.01

Results of Analysis

The P-Values: When equal variances are assumed, the two-sided p = 0.105. The p-value is 0.108 when equal variances are not assumed.

Decision at α = 0.01: Since both p = 0.105 and p = 0.108 are > 0.01 alpha level of significance, we fail to reject the null hypothesis.

Interpretation: There is no sufficient statistical evidence to conclude that the job satisfaction scores of the two groups (those who took counselling and those who did not) differ significantly.

Recommendation: Based on the evaluation of the null hypothesis, the researcher should not recommend counselling as a method to improve job satisfaction following industrial accidents.

Mock Study 4: One-Way ANOVA

Null Hypothesis (Ho): There is no statistically significant difference in mean daily hours of watching TV among the racial groups.

Alternative Hypothesis (H1): There is a statistically significant difference in the mean daily hours of watching TV among at least two racial groups.

Level of significance

α = 0.05

Results of Analysis

The P-Value: < 0.001

Decision at α = 0.05: Since p (< 0.001) < 0.05 alpha level of significance, we reject the null hypothesis in favor of the alternative hypothesis.

Interpretation: There is statistically significant difference in the mean daily hours of watching TV among the racial groups. Black respondents recorded more tv-watching hours, followed by White respondents and then the Other category came in last.

Recommendation: Based on the evaluation of the null hypothesis, the advertising firm should target each racial group differently since their TV-watching habits differ in terms of length of TV-watching hours.

ANOVA vs. t-Tests

Usually, a one-way ANOVA is appropriate when testing for an overall difference among group means in a single analysis just like in this case where we are comparing the means of three independent racial groups. t-Tests are inappropriate for such circumstances because it would involve conducting several separate t-tests thereby increasing the risk of incorrectly finding a significant difference. In other words, it would increase the risk of getting a Type I error.

Mock Study 5: Chi-Square Test of Independence

Null Hypothesis (Ho): There is no significant association between confidence in Congress and political party affiliation.

Alternative Hypothesis (H1): There is a significant association between confidence in Congress and political party affiliation.

Level of significance

α = 0.05

Results of Analysis

Decision at α = 0.05: Since p = 0.006 < 0.05 alpha level of significance, we reject the null hypothesis in favor of the alternative hypothesis.

Interpretation: There is statistically significant association between confidence in Congress and political party affiliation. This suggests that confidence in Congress varies by party political affiliation.

Observation: The observed frequencies differ significantly from the expected frequencies. With regards to this study, a respondent’s confidence in Congress varies according to their political party affiliation. The test, however, shows an association rather than proof that party affiliation causes differences in confidence.

Mock Study 6: Linear Regression

Null Hypothesis (Ho): There is no significant linear relationship between age and hours of TV watched per day

Alternative Hypothesis (H1): There is a significant linear relationship between age and hours of TV watched per day

Level of significance

α = 0.05

Results of Analysis

Decision at α = 0.05: Since p = 0.001 < 0.05 alpha level of significance, we reject the null hypothesis in favor of the alternative hypothesis.

Interpretation: There is a significant linear relationship between age and hours of TV watched per day. This means that an increase in age increases the TV-Watching hours.

Regression Equation

What does this tell us?

For every additional year of age, the predicted length of watching tv increases by roughly 2 mins or 0.033 hours/day. However, according to the adjusted r-squared (0.029), age only explains about 2.9% of the variation in TV-watching hours. As such, it is not a good predictor of TV watch-time.

image5.png

image6.png

image7.png

image8.png

image9.png

image10.png

image11.png

image12.png

image13.png

image14.png

image15.png

image1.png

image2.png

image3.png

image4.png