Scenario: The Western Cape Department of Health realised tha…
Scenario: The Western Cape Department of Health realised that worker morale was low and healthcare staff was generally dissatisfied, which led to high turnover. To help motivate employees to improve worker morale and ultimately improve service delivery, you are requested to advise the department on the best strategy. What strategy would you advise the department to implement?
Scenario: The Western Cape Department of Health realised tha…
Questions
Scenаriо: The Western Cаpe Depаrtment оf Health realised that wоrker morale was low and healthcare staff was generally dissatisfied, which led to high turnover. To help motivate employees to improve worker morale and ultimately improve service delivery, you are requested to advise the department on the best strategy. What strategy would you advise the department to implement?
Relish is the trаnscriptiоn fаctоr thаt increases the transcriptiоn of Anti-Microbial Peptide (AMP) gene expression in flies. You want to use RNAi to decrease the expression of relish in photoreceptor neurons to see if this modifies neurodegeneration in the fly model of Alzheimer’s disease we discussed in class. You will use the Gal4-UAS system and make transgenic flies. You have the following DNA sequences: The Upstream Activating Sequence (UAS) The Gal4 sequence (GAL4) A “promoter” sequence that is used only in Drosophila photoreceptor neurons (GMR) A transgene that encodes an RNAi against Drosophila relish A transgene that encodes a mutant version of human tau (tauV377M) Arrange these sequences in the genomes of the two flies shown below so that neither fly expresses relish RNAi or tauV377M, but when mated, these flies can generate progeny that express RNAi against relish and tauV377M only in photoreceptors. Match the DNA sequence listed above with the letter of the correct box below. The UAS sequence will be used twice. I've filled in one box for you already. The DNA sequence in box 1 would be [GMR] The DNA sequence in box 2 would be [Gal4] The DNA sequence in box 3 would be [UAS] The DNA sequence in box 4 would be [relish] The DNA sequence in box 5 would be [UAS2] If you wanted to change the expression of relish and tau to all cells of the brain, which sequence would you need to change? [1]
Prоblem 1 (35 pоints) Principаl Cоmponent Anаlysis (PCA) wаs performed using the covariance matrix corresponding to the variables and . The resulting principal components are presented below. a. Compute the variance of the principal components and their pairwise covariances i.e. , for . (Hint: Recall , where is the matrix of eigenvectors and is the vector of the original variables) (10 points) b. Compute the correlation coefficients between the principal components and the original variables. Interpret the correlations. (10 points) c. Compute the proportion of the total variance explained by each principal component. (10 points) b. One of the goals of PCA is to reduce the dimension of the original data. For this analysis, how many principal components would you retain? Justify. (5 points) Problem 2 (30 points) Factor analysis was performed on the correlation matrix of the scores of 220 boys in six school subjects, namely, (French), (English), (History), (Arithmetic), (Algebra), and (Geometry). The two-factor solution from the factor analysis is shown below. Factor Loadings Subject F1 F2 French 0.55 0.43 English 0.57 0.29 History 0.39 0.45 Arithmetic 0.74 -0.27 Algebra 0.72 -0.21 Geometry 0.60 -0.13 a. Report the orthogonal factor model i.e. . (5 points) b. Calculate the communalities and interpret the values. (10 points) c. Calculate the correlation between the subjects and the common factors, i.e. for and . What subject(s) might carry the greatest weight in “naming” the common factors? Why? (10 points) d. Given the correlation matrix of the data Recall, that the orthogonal factor model implies that the correlation matrix , can be written in the form , where , is a matrix of the loadings and i.e., the covariance matrix of specific errors of the factor model. Compute and interpret the values. (5 points) Problem 3 (25 points) Consider the dissimilarity (distance) matrix between pairs of five items given below. Cluster the five objects using each of the following procedures. Draw the dendrograms and compare the results. Cut the dendrograms to produce to two clusters for each linkage method. Report the heights at which the two clusters are created for each linkage method. a. Single linkage hierarchical procedure. (5 points) b. Complete linkage hierarchical procedure. (5 points) c. Average linkage hierarchical procedure. (5 points) d. Which linkage method would you recommend? Justify your answer. (10 points) Problem 4 (10 points) Suppose we can measure three variables , and for six items A, B, C, D, E and F. The data are as follows. Use the -means clustering technique to divide the items into clusters. Start with the initial groups (ACD) and (BEF). Report the final clusters.