Beststyle is a leading clothing brand with multiple retail stores across India. Their outlets are well spread in tier 1 and 2 cities of India. Moreover, within the tier 1 cities, they have maintained a balance of opening stores in high-stress malls as well as old market bazaar set-ups. The management at Beststyle wishes to develop a marketing and operational strategy for the upcoming financial season wherein they wish to meet multiple objectives:

1. Plan strategies for the launch of the upcoming sales season

2. Discuss the possibilities of opening new stores

3. Plan the opening of new clothes and accessories sections

4. Expand overall sales

The management decides to consult its analytics team to strategise a plan to meet the above objectives. The head of the analytics team wants to conduct a statistical analysis to understand the factors driving the sales of the company. To understand which factors drive sales, the attributes of the customers must be examined. The organisation has past years data of sales of its 500 stores. Information about customer attributes is also provided in the data frame. The details of the data frame are presented below.

To conduct the statistical analysis, the analytics team decides to obtain different statistical information holding descriptive, inferential or analytical significance. You have recently joined as a business analyst at Beststyle and you have been assigned to the above-mentioned project. Your manager provides you certain tasks to obtain different statistical information. Your tasks related to obtaining information about descriptive, inferential, and analytical statistics are provided in sections A, B, and C, respectively. Your manager insists that the statistical information you obtain must hold some managerial significance as well.

Data.xlsx

Project Information.docx

R_Script_Submission _Template.R

Submission Template.docx

Project Information Introduction Beststyle is a leading clothing brand with multiple retail stores across India. Their outlets are well spread in tier 1 and 2 cities of India. Moreover, within the tier 1 cities, they have maintained a balance of opening stores in high-stress malls as well as old market bazaar set-ups. The management at Beststyle wishes to develop a marketing and operational strategy for the upcoming financial season wherein they wish to meet multiple objectives: 1. Plan strategies for the launch of the upcoming sales season 2. Discuss the possibilities of opening new stores 3. Plan the opening of new clothes and accessories sections 4. Expand overall sales The management decides to consult its analytics team to strategise a plan to meet the above objectives. The head of the analytics team wants to conduct a statistical analysis to understand the factors driving the sales of the company. To understand which factors drive sales, the attributes of the customers must be examined. The organisation has past year's data of sales of its 500 stores. Information about customer attributes is also provided in the data frame. The details of the data frame are presented below. To conduct the statistical analysis, the analytics team decides to obtain different statistical information holding descriptive, inferential or analytical significance. You have recently joined as a business analyst at Beststyle and you have been assigned to the above-mentioned project. Your manager provides you certain tasks to obtain different statistical information. Your tasks related to obtaining information about descriptive, inferential, and analytical statistics are provided in sections A, B, and C, respectively. Your manager insists that the statistical information you obtain must hold some managerial significance as well. The names and description of the variables in the project are as given below. Store data StorelD Unique ID number of each store Sales Unit sales at each store Price Price charged for fashion clothes at every store CompPrice Price charged by competitors of the stores StoreLoc A factor with levels of Mall and Non-mall, which indicate the location of the store City A factor with levels of tier 1 and tier 2 to indicate the type of the store's city Advertising Local advertising budget for at each store Customer data Population Population size in the region of the store Income Community income level Age Average age of the local population Education Level of education at each store Part A Descriptive Statistics - Question 1 Marks Your Answer Question 2 Marks Your Answer Question 3 Marks Your Answer Question 4 Find the value of average sales obtained by BestStyle. Also, find and compare with average sales of stores in tier 1 and tier 2 cities. 1 marks Write your answer here Affluent locations record better sales, as they have more potential customers. If any store's location with a community income level higher than 80,000 can be considered affluent, then identify the difference between the average sales in affluent stores and that in the non-affluent stores. Also, what is the percentage of sales that is constituted by the affluent stores? 1 marks Write your answer here Beststyle plans to conduct an "end-of-summer" sale in September. To advertise the offers of the upcoming sale, the marketing team wants to launch a nation-wide campaign. They wants to run a country-wide marketing campaign. The marketing strategist believes that an understanding of customer attributes is the key to a successful campaign. One such useful attribute is 'customer education level'. Suggest an appropriate education level that can be used to target maximum locations through the campaign. 1 marks Write your answer here Suppose in the campaign customers are not categorised by 'education level', rather by 'age group'. The management of BestStyle believes that most of the customers are in the age group of 35-49 years. Suppose the age of the customers is normally distributed, with a mean of 42 years and a standard deviation of 3.5 years. What is the percentage of customers that falls between 35 and 49 years? List the steps of your working. Question 4 Marks Your Answer Question 5 Marks Your Answer Question 6 Marks Your Answer Suppose in the campaign customers are not categorised by 'education level', rather by 'age group'. The management of BestStyle believes that most of the customers are in the age group of 35-49 years. Suppose the age of the customers is normally distributed, with a mean of 42 years and a standard deviation of 3.5 years. What is the percentage of customers that falls between 35 and 49 years? List the steps of your working. 1 marks Write your answer here In a recent meeting with the customer feedback team, they reported some customers feel the prices of clothes at BestStyle are more volatile in comparison to its competitors. Are the customers right in feeling so? State the statistic you will use to answer this question and present your calculations in R. Also, comment upon the merits or demerits of volatility of prices. Note: For the R-code, please submit the R script separately as mentioned in the instructions 1 marks Write your answer here Describe and compare the advertising budget of BestStyle in mall vs non -mall stores. Use R for calculations and share your R-script. Also, comment upon the advantage or disadvantage of having a store mall. Note: For the R-code, please submit the R script separately as mentioned in the instructions 1 marks Write your answer here Question 7 Write an R code to plot a histogram illustrating the frequency distribution of the prices of clothes in the stores. Make sure to include the following in your R script: 1. The title of the plot as 'Frequency Distribution of Price charged by BestStyle' 2. The axes labelled as 'Frequency' and 'Price of Clothes' Note: For the R-code, please submit the R script separately as mentioned in the instructions Marks 2 marks Your Answer Part B - Inferential Statistics Note: Use alpha = 0.05 if a value is not already mentioned. Question 1 Beststyle is planning to open new stores across the country. The senior management wishes to make this decisionbased on the overall average sales of each store rather than a sample average. As part of the analytics team, your managed has assigned to estimate the confidence interval for the overall sales achieved by Beststyle. Present your workings clearly and also discuss the significance of confidence limits in the decision-making for a new store. Marks 1 marks Your Answer Write your answer here Question 2 In the previous question, will increasing the number of stores in your sample make the confidence interval narrower or wider? What does it signify? Determine the sample sizes 'n' that is needed to restrict the range of the 95% confidence interval to 450. Marks 1 marks Your Answer Write your answer here Question 3 As part of the marketing campaign, BestStyle has decided to distribute pamphlets along with the local newspapers. The sales team has assumed an average population size of 275 while getting these pamphlets printed. Is this assumption justified? Use hypothesis testing to decide if 275 is a reasonable estimate of the population size. Marks 2 marks Your Answer Write your answer here Question 7 Write an R code to plot a histogram illustrating the frequency distribution of the prices of clothes in the stores. Make sure to include the following in your R script: 1. The title of the plot as 'Frequency Distribution of Price charged by BestStyle' 2. The axes labelled as 'Frequency' and 'Price of Clothes' Note: For the R-code, please submit the R script separately as mentioned in the instructions Marks 2 marks Your Answer Part B - Inferential Statistics Note: Use alpha = 0.05 if a value is not already mentioned. Question 1 Beststyle is planning to open new stores across the country. The senior management wishes to make this decisionbased on the overall average sales of each store rather than a sample average. As part of the analytics team, your managed has assigned to estimate the confidence interval for the overall sales achieved by Beststyle. Present your workings clearly and also discuss the significance of confidence limits in the decision-making for a new store. Marks 1 marks Your Answer Write your answer here Question 2 In the previous question, will increasing the number of stores in your sample make the confidence interval narrower or wider? What does it signify? Determine the sample sizes 'n' that is needed to restrict the range of the 95% confidence interval to 450. Marks 1 marks Your Answer Write your answer here Question 3 As part of the marketing campaign, BestStyle has decided to distribute pamphlets along with the local newspapers. The sales team has assumed an average population size of 275 while getting these pamphlets printed. Is this assumption justified? Use hypothesis testing to decide if 275 is a reasonable estimate of the population size. Question 6 Marks Your Answer Question 7 Marks Your Answer BestStyle has adopted a policy of price matching, i.e., pricing your product the same as your competitor's. Due to different cost structures, the price charged might not be homogenous across locations. Based on the sample, can you claim that on average, the pricing is consistent with the policy? Support your answer with appropriate reasoning. 2 marks Write your answer here You are interested in analysing the influence of the mall vs non-mall location of the store in tier and tier 2 cities. Using R, compute the proportion of mall vs non-mall locations in both tier 1 and tier 2 and complete the following table Shelving Mall Non-mall Location Tier 1 P(t1,m) P(t1,nm) Tier 2 P(t2,m) P(t2,nm) 0.64 (Hint: You can use either a subset of the data or the table function.) Further, based on the sample proportions computed above, can you claim that the population proportion of good shelving locations in rural regions is greater than that of urban regions? Give reason for your answer. 2 marks Write your answer here Question 4 Marks Your Answer Question 5 Marks As discussed earlier, a location is considered affluent if its income level exceeds 1,00,000. The company uses exclusive marketing strategies for such locations. However, instead of using 1,00,000, the marketing teams decided to use the mean income level for identifying affluent markets and proposed that the threshold be changed to 80,000. Is the team right in estimating the mean income? Suppose the standard deviation of income level is 20,000. Now, verify their claim using a 98% confidence level. State the test statistic used and list the steps involved. 2 marks Write your answer here In a business meeting, a sales representative claims that 'Not more than 70% of our stores are located in urban areas'. Since the marketing policies and resource allocation depends upon the distribution of stores, the management wants to verify her claim. State the null and alternative hypotheses that you would use here as well as the type of test applicable. List the steps and state the conclusion of your test. 2 marks Part C - Analytical Statistics Question 1 Marks Your Answer Question 2 Marks Your Answer The law of demand states that when the price of a good falls, its quantity demanded increases, and when the price of good rises, its quantity demanded decreases. Use an appropriate statistic to check if such a negative relationship exists between the price and quantity demanded or sales of clothes. Illustrate the relationship through a scatter plot in R. Note: For the R-code, please submit the R script separately as mentioned in the instructions 1 marks Write your answer here BestStyle is planning to expand to more locations. Setting up a new outlet involves a fixed cost. The company wants to evaluate the project based on the expected turnover. The management asks the business analyst to build a model for sales prediction using all the variables related to the store excluding variables labelled under customer data. Summarise your results in a regression table containing coefficients, standard errors and t-stats. (Let's call it Model I; the model name will be used as reference in further questions.) 4 marks Write your answer here Std Error T-Stats (Intercept) Price CompPrice StoreLoc City Advertising Coefficient L Question 3 Marks Your Answer Question 4 Marks Your Answer Question 5 Marks Your Answer A sales analyst goes through the regression output of Model 1 and interprets these results to mean that the value of competitor prices has no effect on the sales. Is this an appropriate conclusion? Give reasons for your answer. 1 marks Write your answer here Using Model I, which you built in question 2, discuss the interpretation of the coefficient of advertising budget. Is it consistent with the belief that stores which have higher advertising budget have higher sales? 1 marks Write your answer here Suppose instead of the previous model, the management wants to predict sales using all variables in customer data as well as price, advertising, competitor's prices and store location as independent variables. Summarize the regression results in a table in the format shared. Let's call it Model - II. Also interpret the R-squared value of this regression. 4 marks Write your answer here Std Error T-Stats (Intercept) Population Income Age Education Price Comp Price StoreLocNon- mall Advertising Coefficient Question 6 Marks Your Answer Question 7 Marks Your Answer Question 8 Marks Your Answer Question 9 Marks Your Answer Question 10 Marks Your Answer Does the combination of predictors in Model II (question 5) explain a significant variation in the response? State the appropriate test that you would use to answer this and show the steps involved. 2 marks Write your answer here Keeping other variables constant, what would be the expected increase in sales if BestStyle increases its advertising budget by 100 in a store? Use Model II (question 5) to answer this question. 1 marks Write your answer here Consider the two multiple linear regression models that we estimated: Model I (question 1) and Model II (question 5). Which is a better model for predicting sales, and why? 1 marks Write your answer here Interpret the coefficient of the store location in the advanced model. Suppose the company incurs a cost of 3,000 in transforming the store from a mall to non-mall location. On the basis of regression in Model II (question 5), would you recommend BestStyle to make this investment? Give reasons for your answer. 3 marks Write your answer here Using the regression equation from Model II (question 5), calculate the predicted sales numbers and create a scatter plot of actual vs predicted numbers in R. Note: For the R-code, please submit the R script separately as mentioned in the instructions 2 marks Project Information Introduction Beststyle is a leading clothing brand with multiple retail stores across India. Their outlets are well spread in tier 1 and 2 cities of India. Moreover, within the tier 1 cities, they have maintained a balance of opening stores in high-stress malls as well as old market bazaar set-ups. The management at Beststyle wishes to develop a marketing and operational strategy for the upcoming financial season wherein they wish to meet multiple objectives: 1. Plan strategies for the launch of the upcoming sales season 2. Discuss the possibilities of opening new stores 3. Plan the opening of new clothes and accessories sections 4. Expand overall sales The management decides to consult its analytics team to strategise a plan to meet the above objectives. The head of the analytics team wants to conduct a statistical analysis to understand the factors driving the sales of the company. To understand which factors drive sales, the attributes of the customers must be examined. The organisation has past year's data of sales of its 500 stores. Information about customer attributes is also provided in the data frame. The details of the data frame are presented below. To conduct the statistical analysis, the analytics team decides to obtain different statistical information holding descriptive, inferential or analytical significance. You have recently joined as a business analyst at Beststyle and you have been assigned to the above-mentioned project. Your manager provides you certain tasks to obtain different statistical information. Your tasks related to obtaining information about descriptive, inferential, and analytical statistics are provided in sections A, B, and C, respectively. Your manager insists that the statistical information you obtain must hold some managerial significance as well. The names and description of the variables in the project are as given below. Store data StorelD Unique ID number of each store Sales Unit sales at each store Price Price charged for fashion clothes at every store CompPrice Price charged by competitors of the stores StoreLoc A factor with levels of Mall and Non-mall, which indicate the location of the store City A factor with levels of tier 1 and tier 2 to indicate the type of the store's city Advertising Local advertising budget for at each store Customer data Population Population size in the region of the store Income Community income level Age Average age of the local population Education Level of education at each store Part A Descriptive Statistics - Question 1 Marks Your Answer Question 2 Marks Your Answer Question 3 Marks Your Answer Question 4 Find the value of average sales obtained by BestStyle. Also, find and compare with average sales of stores in tier 1 and tier 2 cities. 1 marks Write your answer here Affluent locations record better sales, as they have more potential customers. If any store's location with a community income level higher than 80,000 can be considered affluent, then identify the difference between the average sales in affluent stores and that in the non-affluent stores. Also, what is the percentage of sales that is constituted by the affluent stores? 1 marks Write your answer here Beststyle plans to conduct an "end-of-summer" sale in September. To advertise the offers of the upcoming sale, the marketing team wants to launch a nation-wide campaign. They wants to run a country-wide marketing campaign. The marketing strategist believes that an understanding of customer attributes is the key to a successful campaign. One such useful attribute is 'customer education level'. Suggest an appropriate education level that can be used to target maximum locations through the campaign. 1 marks Write your answer here Suppose in the campaign customers are not categorised by 'education level', rather by 'age group'. The management of BestStyle believes that most of the customers are in the age group of 35-49 years. Suppose the age of the customers is normally distributed, with a mean of 42 years and a standard deviation of 3.5 years. What is the percentage of customers that falls between 35 and 49 years? List the steps of your working. Question 4 Marks Your Answer Question 5 Marks Your Answer Question 6 Marks Your Answer Suppose in the campaign customers are not categorised by 'education level', rather by 'age group'. The management of BestStyle believes that most of the customers are in the age group of 35-49 years. Suppose the age of the customers is normally distributed, with a mean of 42 years and a standard deviation of 3.5 years. What is the percentage of customers that falls between 35 and 49 years? List the steps of your working. 1 marks Write your answer here In a recent meeting with the customer feedback team, they reported some customers feel the prices of clothes at BestStyle are more volatile in comparison to its competitors. Are the customers right in feeling so? State the statistic you will use to answer this question and present your calculations in R. Also, comment upon the merits or demerits of volatility of prices. Note: For the R-code, please submit the R script separately as mentioned in the instructions 1 marks Write your answer here Describe and compare the advertising budget of BestStyle in mall vs non -mall stores. Use R for calculations and share your R-script. Also, comment upon the advantage or disadvantage of having a store mall. Note: For the R-code, please submit the R script separately as mentioned in the instructions 1 marks Write your answer here Question 7 Write an R code to plot a histogram illustrating the frequency distribution of the prices of clothes in the stores. Make sure to include the following in your R script: 1. The title of the plot as 'Frequency Distribution of Price charged by BestStyle' 2. The axes labelled as 'Frequency' and 'Price of Clothes' Note: For the R-code, please submit the R script separately as mentioned in the instructions Marks 2 marks Your Answer Part B - Inferential Statistics Note: Use alpha = 0.05 if a value is not already mentioned. Question 1 Beststyle is planning to open new stores across the country. The senior management wishes to make this decisionbased on the overall average sales of each store rather than a sample average. As part of the analytics team, your managed has assigned to estimate the confidence interval for the overall sales achieved by Beststyle. Present your workings clearly and also discuss the significance of confidence limits in the decision-making for a new store. Marks 1 marks Your Answer Write your answer here Question 2 In the previous question, will increasing the number of stores in your sample make the confidence interval narrower or wider? What does it signify? Determine the sample sizes 'n' that is needed to restrict the range of the 95% confidence interval to 450. Marks 1 marks Your Answer Write your answer here Question 3 As part of the marketing campaign, BestStyle has decided to distribute pamphlets along with the local newspapers. The sales team has assumed an average population size of 275 while getting these pamphlets printed. Is this assumption justified? Use hypothesis testing to decide if 275 is a reasonable estimate of the population size. Marks 2 marks Your Answer Write your answer here Question 7 Write an R code to plot a histogram illustrating the frequency distribution of the prices of clothes in the stores. Make sure to include the following in your R script: 1. The title of the plot as 'Frequency Distribution of Price charged by BestStyle' 2. The axes labelled as 'Frequency' and 'Price of Clothes' Note: For the R-code, please submit the R script separately as mentioned in the instructions Marks 2 marks Your Answer Part B - Inferential Statistics Note: Use alpha = 0.05 if a value is not already mentioned. Question 1 Beststyle is planning to open new stores across the country. The senior management wishes to make this decisionbased on the overall average sales of each store rather than a sample average. As part of the analytics team, your managed has assigned to estimate the confidence interval for the overall sales achieved by Beststyle. Present your workings clearly and also discuss the significance of confidence limits in the decision-making for a new store. Marks 1 marks Your Answer Write your answer here Question 2 In the previous question, will increasing the number of stores in your sample make the confidence interval narrower or wider? What does it signify? Determine the sample sizes 'n' that is needed to restrict the range of the 95% confidence interval to 450. Marks 1 marks Your Answer Write your answer here Question 3 As part of the marketing campaign, BestStyle has decided to distribute pamphlets along with the local newspapers. The sales team has assumed an average population size of 275 while getting these pamphlets printed. Is this assumption justified? Use hypothesis testing to decide if 275 is a reasonable estimate of the population size. Question 6 Marks Your Answer Question 7 Marks Your Answer BestStyle has adopted a policy of price matching, i.e., pricing your product the same as your competitor's. Due to different cost structures, the price charged might not be homogenous across locations. Based on the sample, can you claim that on average, the pricing is consistent with the policy? Support your answer with appropriate reasoning. 2 marks Write your answer here You are interested in analysing the influence of the mall vs non-mall location of the store in tier and tier 2 cities. Using R, compute the proportion of mall vs non-mall locations in both tier 1 and tier 2 and complete the following table Shelving Mall Non-mall Location Tier 1 P(t1,m) P(t1,nm) Tier 2 P(t2,m) P(t2,nm) 0.64 (Hint: You can use either a subset of the data or the table function.) Further, based on the sample proportions computed above, can you claim that the population proportion of good shelving locations in rural regions is greater than that of urban regions? Give reason for your answer. 2 marks Write your answer here Question 4 Marks Your Answer Question 5 Marks As discussed earlier, a location is considered affluent if its income level exceeds 1,00,000. The company uses exclusive marketing strategies for such locations. However, instead of using 1,00,000, the marketing teams decided to use the mean income level for identifying affluent markets and proposed that the threshold be changed to 80,000. Is the team right in estimating the mean income? Suppose the standard deviation of income level is 20,000. Now, verify their claim using a 98% confidence level. State the test statistic used and list the steps involved. 2 marks Write your answer here In a business meeting, a sales representative claims that 'Not more than 70% of our stores are located in urban areas'. Since the marketing policies and resource allocation depends upon the distribution of stores, the management wants to verify her claim. State the null and alternative hypotheses that you would use here as well as the type of test applicable. List the steps and state the conclusion of your test. 2 marks Part C - Analytical Statistics Question 1 Marks Your Answer Question 2 Marks Your Answer The law of demand states that when the price of a good falls, its quantity demanded increases, and when the price of good rises, its quantity demanded decreases. Use an appropriate statistic to check if such a negative relationship exists between the price and quantity demanded or sales of clothes. Illustrate the relationship through a scatter plot in R. Note: For the R-code, please submit the R script separately as mentioned in the instructions 1 marks Write your answer here BestStyle is planning to expand to more locations. Setting up a new outlet involves a fixed cost. The company wants to evaluate the project based on the expected turnover. The management asks the business analyst to build a model for sales prediction using all the variables related to the store excluding variables labelled under customer data. Summarise your results in a regression table containing coefficients, standard errors and t-stats. (Let's call it Model I; the model name will be used as reference in further questions.) 4 marks Write your answer here Std Error T-Stats (Intercept) Price CompPrice StoreLoc City Advertising Coefficient L Question 3 Marks Your Answer Question 4 Marks Your Answer Question 5 Marks Your Answer A sales analyst goes through the regression output of Model 1 and interprets these results to mean that the value of competitor prices has no effect on the sales. Is this an appropriate conclusion? Give reasons for your answer. 1 marks Write your answer here Using Model I, which you built in question 2, discuss the interpretation of the coefficient of advertising budget. Is it consistent with the belief that stores which have higher advertising budget have higher sales? 1 marks Write your answer here Suppose instead of the previous model, the management wants to predict sales using all variables in customer data as well as price, advertising, competitor's prices and store location as independent variables. Summarize the regression results in a table in the format shared. Let's call it Model - II. Also interpret the R-squared value of this regression. 4 marks Write your answer here Std Error T-Stats (Intercept) Population Income Age Education Price Comp Price StoreLocNon- mall Advertising Coefficient Question 6 Marks Your Answer Question 7 Marks Your Answer Question 8 Marks Your Answer Question 9 Marks Your Answer Question 10 Marks Your Answer Does the combination of predictors in Model II (question 5) explain a significant variation in the response? State the appropriate test that you would use to answer this and show the steps involved. 2 marks Write your answer here Keeping other variables constant, what would be the expected increase in sales if BestStyle increases its advertising budget by 100 in a store? Use Model II (question 5) to answer this question. 1 marks Write your answer here Consider the two multiple linear regression models that we estimated: Model I (question 1) and Model II (question 5). Which is a better model for predicting sales, and why? 1 marks Write your answer here Interpret the coefficient of the store location in the advanced model. Suppose the company incurs a cost of 3,000 in transforming the store from a mall to non-mall location. On the basis of regression in Model II (question 5), would you recommend BestStyle to make this investment? Give reasons for your answer. 3 marks Write your answer here Using the regression equation from Model II (question 5), calculate the predicted sales numbers and create a scatter plot of actual vs predicted numbers in R. Note: For the R-code, please submit the R script separately as mentioned in the instructions 2 marks