Applied Statistics for Psychology

Name (first and last):   Type your name here

Term (ex: 2103C): Type class term here

Phone area code (ex: 225): Type the area code for the phone you use most often

MM570 Applied Statistics for Psychology

Unit 9 Assignment

This is a course level assessment assignment. MM570-5: Interpret the output from an appropriate test of hypothesis for a particular context.

HINTS AND HELP

Dataset: Psych_Data.xlsx can be found in the Virtual Office. You will use this data set to answer all of the questions in the Assignment.  When working with the data set, you will use the same question answers as you entered above.

Note: When asked to include the interpretation of the results and final conclusions, be sure to include a snippet of all results, an interpretation of the meaning of the results, and final conclusions that a common person can understand.  Make sure the conclusions are written in context based on the content in the question. Make sure you use complete sentences, paragraph form (double spacing not required), proper grammar, and correct spelling. Incomplete responses will lose points. Include any Excel results that you use relevant to your solution.

Hint: For ANOVA Ha= verbatim “at least one mean is different. “You are asked to determine “appropriate” tests and methods, and to make calculations. This means that you will have to determine which tests or methods are best and why. When asked for your p-value, if your Excel output shows something like 2.735E-15 (scientific notation for 2.735 x 10^(-15), you can just put the p-value is “near zero.” For your decision responses, you will want to compare your p-value (rounded to four decimal places) to 0.05 and state whether you will reject Ho or fail to reject Ho.

Use the Microsoft Excel Data Analysis tool pack when provided raw data sets.

The following online calculators will assist you in your calculations.

Normal distribution Z Score: Normal Distribution (onlinestatbook.com)

T-distribution T Score: UsableStats: 2 Sample t-test Calculator

F-distribution (Comparing more than two groups) ANOVA: VassarStats: Statistical Computation Web Site

Post-hoc  test (to identify difference in groups, POST ANOVA): VassarStats: Statistical Computation Web Site

Any problem to requires an equation calculation: Desmos | Scientific Calculator

***Assume alpha = .05 for all questions on this assignment***

1. Compare the different Medical Insurance status of subjects in the Psych_Data.xlsx data set to determine if there is a statistically significant difference in the mean Anxiety Scores (anx_score) between the different groups (Yes – has insurance and No – doesn’t have insurance). Be sure to state the type of test, state the Ho and Ha, include all relevant Excel results and plots, and write final conclusions for the full results of the test in context. Be sure that your final conclusions are written in common terms for an average person to understand.

(a) What type of hypothesis test will you run?

(b) State the Ho and Ha.

(c) Include descriptive statistics (mean, standard deviation, sample size) AND an appropriate graphical display that allows you to visually compare the Anxiety Scores for the two Medical Insurance groups. Copy/paste the numerical summaries and graph here AND describe the similarities and differences in the Anxiety Scores of the two groups (address central tendency and variation of the two groups in your discussion).

(d) Give the test statistic, p-value, and decision from your test results.

(e) Write a full conclusion (in context) for the results on this test in a way that can be understood by a non-statistical person. This answer will be at least 100 words or more.

2. Compare the different Socioeconomic Levels (ses_level) of the students in the Psych_Data.xlsx dataset to determine if there is a statistically significant difference in the mean  Suicide Risk Levels (suicidal_inv) between the different SES levels. Be sure to state the type of test, state the Ho and Ha, include all relevant Excel results and plots, and write final conclusions for the full results of the test in context. Be sure that your final conclusions are written in common terms for an average person to understand.

(a) What type of hypothesis test will you run?

(b) State the Ho and Ha.

(c) Include descriptive statistics (mean, standard deviation, sample size) AND an appropriate graphical display that allows you to visually compare the Suicide Risk Levels for the three SES groups. Copy/paste the numerical summaries and graph here AND describe the similarities and differences in the Suicide Risk Levels of the three groups (address central tendency and variation of the three groups in your discussion).

(d) Give the test statistic, p-value, and decision from your test results. Would a post-hoc be necessary – why or why not?

(e) Write a full conclusion (in context) for the results on this test in a way that can be understood by a non-statistical person. This answer will be at least 100 words or more.

3. Use the techniques of correlation and regression to investigate the relationship between Depression Level (dep_scale) and Anxiety Score (anx_score). Let the independent variable be Depression Level, and let the dependent variable be Anxiety Score.

  • Create a scatterplot to display this relationship. Use the graph to describe the relationship between the two variables in terms of shape and direction.
  • Generate the appropriate regression analysis in Excel and paste your results here.
  • What is the value of the correlation coefficient?  Is there a positive or negative association?  Is the association weak, moderate, or strong?
  • Based on the Excel output above, is there convincing evidence of a significant linear relationship between Anxiety Score and Depression Level (yes or no)?  Explain how you know.
  • Using your Excel output above, write the prediction equation (should be in the form ). Then, using your equation, predict the Anxiety Score for a subject with a Depression Level of 3.4 (round your answer to two decimal places). SHOW WORK for your calculation.

4. From the Psych_Data.xlsx dataset, use the Before Therapy (pre_ther) and After Therapy (post_ther) scores to answer the question: “Does a short-term integrated therapy method lead to an improvement in one’s mental health status?” Assume the (pre_ther) and (post_ther) scores are appropriate measures of one’s mental health state and the higher the score, the better one’s overall mental health.

(a) What type of hypothesis test will you run?

(b) State the Ho and Ha.

(c) Give the test statistic, p-value, and decision from your test results.

(d) Write a full conclusion (in context) for the results on this test in a way that can be understood by a non-statistical person. This answer will be at least 100 words or more.

5. From the Psych_Data.xlsx dataset, use the ethnicity and therapy_pref variables to determine whether there is evidence of a significant association between ethnicity and preferred therapy method (individual, group, mixed).

(a) What type of hypothesis test will you run?

(b) State the Ho and Ha.

(c)  Include an appropriate graphical display that allows you to visually assess the association between ethnicity and therapy preference. Copy/paste the graph here. Comment on any association that appears to be present.

(d) Give the test statistic, p-value, and decision from your test results.

(e) Write a full conclusion (in context) for the results on this test in a way that can be understood by a non-statistical person. This answer will be at least 100 words or more.